diff --git a/evidence/world_class/templates/provider-holdout.intake.json b/evidence/world_class/templates/provider-holdout.intake.json
index f8faf6e3..fffc33c5 100644
--- a/evidence/world_class/templates/provider-holdout.intake.json
+++ b/evidence/world_class/templates/provider-holdout.intake.json
@@ -18,7 +18,10 @@
   "provenance": {
     "provider": "openai",
     "model": "gpt-4.1-mini",
-    "run_command": "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+    "run_command": "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+    "credential_env": "OPENAI_API_KEY",
+    "model_env": "YAO_OUTPUT_EVAL_MODEL",
+    "model_default": "gpt-4.1-mini",
     "credential_material_committed": false
   },
   "privacy": {
diff --git a/registry/index.json b/registry/index.json
index 821559be..deb93c8c 100644
--- a/registry/index.json
+++ b/registry/index.json
@@ -1,6 +1,6 @@
 {
   "schema_version": "2.0",
-  "generated_at": "2026-06-16",
+  "generated_at": "2026-06-13",
   "package_count": 1,
   "packages": [
     {
@@ -16,7 +16,7 @@
         "vscode"
       ],
       "package_metadata": "registry/packages/yao-meta-skill.json",
-      "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+      "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
     }
   ]
 }
diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json
index 7c7784df..091a666d 100644
--- a/registry/packages/yao-meta-skill.json
+++ b/registry/packages/yao-meta-skill.json
@@ -16,7 +16,7 @@
   "trust_level": "local",
   "license": "MIT",
   "checksums": {
-    "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+    "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
     "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81"
   },
   "compatibility": {
@@ -53,5 +53,5 @@
     "install_simulated": true,
     "install_simulation": "reports/install_simulation.json"
   },
-  "generated_at": "2026-06-16"
+  "generated_at": "2026-06-13"
 }
diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json
index 71fe0fda..14f57abc 100644
--- a/reports/adoption_drift_report.json
+++ b/reports/adoption_drift_report.json
@@ -1,7 +1,7 @@
 {
   "ok": true,
   "schema_version": "2.0",
-  "generated_at": "2026-06-16",
+  "generated_at": "2026-06-16T00:06:24Z",
   "skill_dir": ".",
   "privacy_contract": {
     "storage": "local-first",
@@ -25,14 +25,14 @@
   },
   "summary": {
     "event_count": 1,
-    "adoption_sample_count": 0,
-    "activation_count": 0,
-    "accepted_count": 0,
+    "adoption_sample_count": 1,
+    "activation_count": 1,
+    "accepted_count": 1,
     "edited_count": 0,
     "rejected_count": 0,
     "missed_count": 0,
     "failed_count": 0,
-    "adoption_rate": 0,
+    "adoption_rate": 100.0,
     "missed_trigger_count": 0,
     "wrong_trigger_count": 0,
     "bad_output_count": 0,
@@ -41,7 +41,7 @@
     "review_overdue_count": 0,
     "risk_band": "low",
     "event_types": {
-      "review_event": 1
+      "skill_activation": 1
     },
     "failure_types": {},
     "source_types": {
@@ -53,31 +53,31 @@
     {
       "skill": "yao-meta-skill",
       "events": 1,
-      "adoption_events": 0,
-      "accepted": 0,
+      "adoption_events": 1,
+      "accepted": 1,
       "edited": 0,
       "rejected": 0,
       "missed": 0,
-      "adoption_rate": 0
+      "adoption_rate": 100.0
     }
   ],
   "next_iteration_candidates": [],
   "recent_events": [
     {
       "command": "unknown",
-      "event": "review_event",
+      "event": "skill_activation",
       "skill": "yao-meta-skill",
       "source": "manual",
       "version": "1.1.0",
-      "activation_type": "manual",
-      "outcome": "reviewed",
+      "activation_type": "explicit",
+      "outcome": "accepted",
       "failure_type": "none",
-      "timestamp": "2026-06-13T12:00:00Z"
+      "timestamp": "2026-06-13T10:00:00Z"
     }
   ],
   "failures": [],
   "artifacts": {
-    "events_jsonl": "reports/telemetry_events.jsonl",
+    "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl",
     "json": "reports/adoption_drift_report.json",
     "markdown": "reports/adoption_drift_report.md"
   }
diff --git a/reports/adoption_drift_report.md b/reports/adoption_drift_report.md
index 91b31983..206372c9 100644
--- a/reports/adoption_drift_report.md
+++ b/reports/adoption_drift_report.md
@@ -5,9 +5,9 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
 ## Summary
 
 - Events: `1`
-- Adoption samples: `0`
-- Activation events: `0`
-- Adoption rate: `0`
+- Adoption samples: `1`
+- Activation events: `1`
+- Adoption rate: `100.0`
 - Missed trigger signals: `0`
 - Bad output signals: `0`
 - Script error signals: `0`
@@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
 
 | Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate |
 | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
-| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 |
+| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 |
 
 ## Next Iteration Candidates
 
@@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
 
 ## Recent Metadata Events
 
-- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none`
+- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none`
diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json
index a11d367f..aa6895cc 100644
--- a/reports/architecture_maintainability.json
+++ b/reports/architecture_maintainability.json
@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-16",
+  "generated_at": "2026-06-13",
   "skill_dir": ".",
   "summary": {
     "python_file_count": 191,
@@ -29,6 +29,13 @@
       "severity": "pass",
       "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
     },
+    {
+      "path": "tests/verify_world_class_evidence_intake.py",
+      "lines": 874,
+      "kind": "test",
+      "severity": "pass",
+      "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
+    },
     {
       "path": "scripts/yao_cli_parser.py",
       "lines": 870,
@@ -36,16 +43,9 @@
       "severity": "pass",
       "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
     },
-    {
-      "path": "tests/verify_world_class_evidence_intake.py",
-      "lines": 867,
-      "kind": "test",
-      "severity": "pass",
-      "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
-    },
     {
       "path": "tests/verify_review_studio.py",
-      "lines": 834,
+      "lines": 836,
       "kind": "test",
       "severity": "pass",
       "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
@@ -115,6 +115,13 @@
       "severity": "pass",
       "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
     },
+    {
+      "path": "tests/verify_world_class_evidence_intake.py",
+      "lines": 874,
+      "kind": "test",
+      "severity": "pass",
+      "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
+    },
     {
       "path": "scripts/yao_cli_parser.py",
       "lines": 870,
@@ -122,16 +129,9 @@
       "severity": "pass",
       "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
     },
-    {
-      "path": "tests/verify_world_class_evidence_intake.py",
-      "lines": 867,
-      "kind": "test",
-      "severity": "pass",
-      "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
-    },
     {
       "path": "tests/verify_review_studio.py",
-      "lines": 834,
+      "lines": 836,
       "kind": "test",
       "severity": "pass",
       "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md
index 577048d0..3d9b3475 100644
--- a/reports/architecture_maintainability.md
+++ b/reports/architecture_maintainability.md
@@ -1,6 +1,6 @@
 # Architecture Maintainability
 
-Generated at: `2026-06-16`
+Generated at: `2026-06-13`
 
 ## Summary
 
@@ -30,9 +30,9 @@ No file-size hotspots found.
 | File | Lines | Kind | Recommended next split |
 | --- | ---: | --- | --- |
 | `tests/verify_yao_cli.py` | `899` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
+| `tests/verify_world_class_evidence_intake.py` | `874` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
 | `scripts/yao_cli_parser.py` | `870` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
-| `tests/verify_world_class_evidence_intake.py` | `867` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
-| `tests/verify_review_studio.py` | `834` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
+| `tests/verify_review_studio.py` | `836` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
 | `scripts/render_world_class_preflight.py` | `814` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
 | `scripts/render_evidence_consistency.py` | `808` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
 | `scripts/skill_report_model.py` | `800` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
@@ -45,9 +45,9 @@ No file-size hotspots found.
 | File | Lines | Kind | Severity |
 | --- | ---: | --- | --- |
 | `tests/verify_yao_cli.py` | `899` | `test` | `pass` |
+| `tests/verify_world_class_evidence_intake.py` | `874` | `test` | `pass` |
 | `scripts/yao_cli_parser.py` | `870` | `internal-module` | `pass` |
-| `tests/verify_world_class_evidence_intake.py` | `867` | `test` | `pass` |
-| `tests/verify_review_studio.py` | `834` | `test` | `pass` |
+| `tests/verify_review_studio.py` | `836` | `test` | `pass` |
 | `scripts/render_world_class_preflight.py` | `814` | `cli-script` | `pass` |
 | `scripts/render_evidence_consistency.py` | `808` | `cli-script` | `pass` |
 | `scripts/skill_report_model.py` | `800` | `internal-module` | `pass` |
diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json
index 6ebcec65..332952f1 100644
--- a/reports/benchmark_reproducibility.json
+++ b/reports/benchmark_reproducibility.json
@@ -3,22 +3,35 @@
   "ok": true,
   "generated_at": "2026-06-16",
   "skill_dir": ".",
-  "commit": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
+  "commit": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
   "git_status": {
     "available": true,
-    "dirty": false,
-    "changed_file_count": 0,
-    "sample": [],
+    "dirty": true,
+    "changed_file_count": 64,
+    "sample": [
+      " M evidence/world_class/templates/provider-holdout.intake.json",
+      " M registry/index.json",
+      " M registry/packages/yao-meta-skill.json",
+      " M reports/adoption_drift_report.json",
+      " M reports/adoption_drift_report.md",
+      " M reports/architecture_maintainability.json",
+      " M reports/architecture_maintainability.md",
+      " M reports/benchmark_reproducibility.json",
+      " M reports/benchmark_reproducibility.md",
+      " M reports/compiled_targets.json",
+      " M reports/context_budget.json",
+      " M reports/context_budget.md"
+    ],
     "scope": "generation-time status before this report is written"
   },
   "summary": {
     "reproducibility_ready": true,
-    "release_lock_ready": true,
+    "release_lock_ready": false,
     "methodology_complete": true,
     "required_artifact_count": 25,
     "missing_artifact_count": 0,
-    "evidence_bundle_sha256": "7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1",
-    "source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+    "evidence_bundle_sha256": "95c6335a413934f197ca1595747c312701edb6028e8fc2ffed6cc4755c0a8d1f",
+    "source_contract_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
     "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
     "output_case_count": 5,
     "failure_disclosure_count": 3,
@@ -34,29 +47,30 @@
     "world_class_task_count": 4,
     "world_class_ledger_pending_count": 4,
     "world_class_source_check_count": 13,
-    "world_class_source_pass_count": 6,
-    "world_class_source_blocked_count": 7,
+    "world_class_source_pass_count": 7,
+    "world_class_source_blocked_count": 6,
     "public_claim_ready": false,
-    "public_claim_blocker_count": 4,
-    "working_tree_dirty": false,
-    "changed_file_count": 0
+    "public_claim_blocker_count": 5,
+    "working_tree_dirty": true,
+    "changed_file_count": 64
   },
   "public_claim": {
     "ready": false,
     "scope": "public benchmark or world-class readiness claim",
     "blockers": [
+      "release lock is not clean or commit is unavailable",
       "provider-backed model holdout evidence is incomplete",
       "human blind-review adjudication is incomplete",
       "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
-      "world-class source checks are not all accepted (6/13 pass, 7 blocked)"
+      "world-class source checks are not all accepted (7/13 pass, 6 blocked)"
     ],
     "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
   },
   "release_lock": {
-    "ready": true,
-    "commit": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
+    "ready": false,
+    "commit": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
     "status_scope": "generation-time status before this report is written",
-    "reason": "clean generation-time HEAD"
+    "reason": "working tree was dirty at generation time"
   },
   "evidence_bundle": {
     "algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -64,7 +78,7 @@
     "existing_count": 25,
     "missing_count": 0,
     "missing_paths": [],
-    "sha256": "7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1"
+    "sha256": "95c6335a413934f197ca1595747c312701edb6028e8fc2ffed6cc4755c0a8d1f"
   },
   "methodology": {
     "path": "reports/benchmark_methodology.md",
@@ -138,7 +152,7 @@
       "path": "reports/output_execution_runs.json",
       "exists": true,
       "bytes": 7967,
-      "sha256": "ab66dfd1a1f2fca481752aa164271a8c4f419cab9653f45dd63d1c73011713bb"
+      "sha256": "072e7ff6ef9c938f9b876bd950a69ede0c3d87939fc79f10c0b69b6df250c45d"
     },
     {
       "label": "blind_review",
@@ -173,21 +187,21 @@
       "path": "reports/security_trust_report.json",
       "exists": true,
       "bytes": 118486,
-      "sha256": "ca53fbf5fa66f574d34603b160c3c3a264b015ba2722deb930b5accb94b52af8"
+      "sha256": "390ddd84dcfb27f7d1c6a3e6216c526ff1ec1ca86c11ea22dfdcdc0403e71cda"
     },
     {
       "label": "python_compatibility",
       "path": "reports/python_compatibility.json",
       "exists": true,
       "bytes": 25199,
-      "sha256": "18c8a142c8108071bc453367c1fd3589b3368c098d5fc27f4b1d11c19f0bfb92"
+      "sha256": "dbd04851a3a6a14273a2e62823ee6d1d181d2e91b88c8c34d2a1b5ca284bc35a"
     },
     {
       "label": "registry_audit",
       "path": "reports/registry_audit.json",
       "exists": true,
       "bytes": 3183,
-      "sha256": "7f980caf507c7d094401a18194eeeb7480de3a924326b6d0c97e07b33e3fb64f"
+      "sha256": "7762378b6fe7a3228b24e6a69499efb8e7ea3c394de1c9714c4d886fc38857ff"
     },
     {
       "label": "package_verification",
@@ -200,78 +214,78 @@
       "label": "install_simulation",
       "path": "reports/install_simulation.json",
       "exists": true,
-      "bytes": 8604,
-      "sha256": "aa45be12d2a94664dce95884668839d58808eaad70de90cfb1e96939e9e3a3c0"
+      "bytes": 8758,
+      "sha256": "ba0b8b088b64b1b60715075da4502048c50b2b00d922c6cc7bd3456dca148b34"
     },
     {
       "label": "skill_os2_audit",
       "path": "reports/skill_os2_audit.json",
       "exists": true,
       "bytes": 14310,
-      "sha256": "a4dfc4e3af1167e3d6ced9444c41bc6cd2133bb67942fedba94c046814bf7866"
+      "sha256": "6187a8850680edd24e84161003d3d06379f5f9665ad1ed6e509b661283c62a44"
     },
     {
       "label": "world_class_evidence_plan",
       "path": "reports/world_class_evidence_plan.json",
       "exists": true,
-      "bytes": 20554,
-      "sha256": "38e95161404d2dc9a1c7bf3c1ee213a051ced5444deb01b0a01e557a4321021d"
+      "bytes": 20828,
+      "sha256": "af3c3f101ad992820bf36ddb14b02e7404ef16411567c483f86eed530ca45f62"
     },
     {
       "label": "world_class_evidence_ledger",
       "path": "reports/world_class_evidence_ledger.json",
       "exists": true,
-      "bytes": 21587,
-      "sha256": "d08019f31a7811ee747392f24a11902f173201054894c0338d80b45543c88d18"
+      "bytes": 21721,
+      "sha256": "6c135aced3443b88cc45009957386b566be80fd5c7f261361163dada861dab43"
     },
     {
       "label": "world_class_evidence_intake",
       "path": "reports/world_class_evidence_intake.json",
       "exists": true,
-      "bytes": 19178,
-      "sha256": "4a9119aba62b7cbc9f6b434c33f58a73d2fd623e1f4ed67c3ca994f23025a317"
+      "bytes": 19319,
+      "sha256": "69afd0ff3d49ba9e1ea57248e41cfe62a0abfdf06fd0f997ed3008a5656c2566"
     },
     {
       "label": "world_class_evidence_preflight",
       "path": "reports/world_class_evidence_preflight.json",
       "exists": true,
-      "bytes": 41071,
-      "sha256": "37fd4b91f92ceda3a5873431d5629b33c7909c10fbdc465eaad546e45562328f"
+      "bytes": 41202,
+      "sha256": "97924dd4be88bedd734bb0530765ce5ea6e10a92d2a17807c14b2aae5b66f960"
     },
     {
       "label": "world_class_submission_review",
       "path": "reports/world_class_submission_review.json",
       "exists": true,
-      "bytes": 13658,
-      "sha256": "6aaf868374ba134afbb4d4bf9c0339604ab41b7439379241359b83c279e9207f"
+      "bytes": 13655,
+      "sha256": "17def7ba6982d834e13ce3896dd9093019eec3ee8d2fa5b283ef8d6b17b19be0"
     },
     {
       "label": "world_class_operator_runbook",
       "path": "reports/world_class_operator_runbook.json",
       "exists": true,
-      "bytes": 24330,
-      "sha256": "40d1796964450e55bbaea98e46b0aa3433693e0b532c89b77ce5279c020570ff"
+      "bytes": 24403,
+      "sha256": "f2e53f857320f4c98faa8375e6b4758a8b6b291497578ec9adb14baeb6ee169c"
     },
     {
       "label": "world_class_operator_runbook_markdown",
       "path": "reports/world_class_operator_runbook.md",
       "exists": true,
-      "bytes": 15360,
-      "sha256": "ebfa3a4b528044bdf40f8931a246b54eb7cf37afe55bc02cad95f6e04ea4efa0"
+      "bytes": 15424,
+      "sha256": "337fb764b98ad2707f5a0d7bba88b9c5401256d7be00f8f3dc478e89e3bcb6c2"
     },
     {
       "label": "world_class_operator_runbook_html",
       "path": "reports/world_class_operator_runbook.html",
       "exists": true,
-      "bytes": 21284,
-      "sha256": "eb6c4506b0f25f01eef077c7c65bfe3f3230d3991b0db3befa8798768254373f"
+      "bytes": 21348,
+      "sha256": "ca72c65b437b2211d08b9d463c9a33a7993b4e388bb75f62757ead4dfcf81a49"
     },
     {
       "label": "world_class_claim_guard",
       "path": "reports/world_class_claim_guard.json",
       "exists": true,
       "bytes": 18406,
-      "sha256": "704aba252d55e9b9f546392ce7f51b91f3b74d3384501d7f80a74e14c5b50acd"
+      "sha256": "25206d72ff919a2a4ce398b80a602028ab5f6a43648b5d3b690b3fdd02f49280"
     }
   ],
   "missing_artifacts": [],
diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md
index 2681b29f..22700a8b 100644
--- a/reports/benchmark_reproducibility.md
+++ b/reports/benchmark_reproducibility.md
@@ -1,18 +1,18 @@
 # Benchmark Reproducibility
 
 Generated at: `2026-06-16`
-Commit: `4b2767900bbbbb962d2b11a92610951c3a0a0f0e`
-Working tree dirty at generation: `false`
-Evidence bundle SHA256: `7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1`
+Commit: `54851019f53f3ee3f508dedfc0daaf192d6bc6ad`
+Working tree dirty at generation: `true`
+Evidence bundle SHA256: `95c6335a413934f197ca1595747c312701edb6028e8fc2ffed6cc4755c0a8d1f`
 
 ## Summary
 
 - reproducibility ready: `true`
-- release lock ready: `true`
+- release lock ready: `false`
 - methodology complete: `true`
 - required artifacts: `25`
 - missing artifacts: `0`
-- source contract sha256: `db36e8f9d7d6`
+- source contract sha256: `a5f307ba8e89`
 - archive sha256: `996e36863203`
 - output cases: `5`
 - disclosed failure cases: `3`
@@ -20,10 +20,10 @@ Evidence bundle SHA256: `7ef645993fc40e21528099046d09056d87af293c171850a84acbcab
 - provider evidence complete: `false`
 - human review complete: `false`
 - world-class ready: `false`
-- world-class source checks: `6` pass / `13` total; `7` blocked
+- world-class source checks: `7` pass / `13` total; `6` blocked
 - public claim ready: `false`
-- public claim blockers: `4`
-- changed files at generation: `0`
+- public claim blockers: `5`
+- changed files at generation: `64`
 
 This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
 
@@ -35,22 +35,23 @@ This report proves local benchmark reproducibility only. It keeps external provi
 
 | Blocker |
 | --- |
+| release lock is not clean or commit is unavailable |
 | provider-backed model holdout evidence is incomplete |
 | human blind-review adjudication is incomplete |
 | world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
-| world-class source checks are not all accepted (6/13 pass, 7 blocked) |
+| world-class source checks are not all accepted (7/13 pass, 6 blocked) |
 
 ## Release Lock
 
-- ready: `true`
-- reason: clean generation-time HEAD
+- ready: `false`
+- reason: working tree was dirty at generation time
 - status scope: generation-time status before this report is written
 
 ## Evidence Bundle
 
 - algorithm: `sha256(path,label,exists,artifact_sha256)`
 - artifacts: `25` / `25`
-- sha256: `7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1`
+- sha256: `95c6335a413934f197ca1595747c312701edb6028e8fc2ffed6cc4755c0a8d1f`
 
 ## Methodology Sections
 
@@ -72,26 +73,26 @@ This report proves local benchmark reproducibility only. It keeps external provi
 | output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` |
 | output_schema | `evals/output/schema.json` | present | `8ee340c95064` |
 | output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` |
-| output_execution | `reports/output_execution_runs.json` | present | `ab66dfd1a1f2` |
+| output_execution | `reports/output_execution_runs.json` | present | `072e7ff6ef9c` |
 | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
 | review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` |
 | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
 | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
-| trust_report | `reports/security_trust_report.json` | present | `ca53fbf5fa66` |
-| python_compatibility | `reports/python_compatibility.json` | present | `18c8a142c810` |
-| registry_audit | `reports/registry_audit.json` | present | `7f980caf507c` |
+| trust_report | `reports/security_trust_report.json` | present | `390ddd84dcfb` |
+| python_compatibility | `reports/python_compatibility.json` | present | `dbd04851a3a6` |
+| registry_audit | `reports/registry_audit.json` | present | `7762378b6fe7` |
 | package_verification | `reports/package_verification.json` | present | `bbe73152879c` |
-| install_simulation | `reports/install_simulation.json` | present | `aa45be12d2a9` |
-| skill_os2_audit | `reports/skill_os2_audit.json` | present | `a4dfc4e3af11` |
-| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `38e95161404d` |
-| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `d08019f31a78` |
-| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `4a9119aba62b` |
-| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `37fd4b91f92c` |
-| world_class_submission_review | `reports/world_class_submission_review.json` | present | `6aaf868374ba` |
-| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `40d179696445` |
-| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `ebfa3a4b5280` |
-| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `eb6c4506b0f2` |
-| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `704aba252d55` |
+| install_simulation | `reports/install_simulation.json` | present | `ba0b8b088b64` |
+| skill_os2_audit | `reports/skill_os2_audit.json` | present | `6187a8850680` |
+| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `af3c3f101ad9` |
+| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `6c135aced344` |
+| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `69afd0ff3d49` |
+| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `97924dd4be88` |
+| world_class_submission_review | `reports/world_class_submission_review.json` | present | `17def7ba6982` |
+| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `f2e53f857320` |
+| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `337fb764b98a` |
+| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `ca72c65b437b` |
+| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `25206d72ff91` |
 
 ## Reproduction Commands
 
diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json
index eeb3e744..78d28a9b 100644
--- a/reports/compiled_targets.json
+++ b/reports/compiled_targets.json
@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-16",
+  "generated_at": "2026-06-13",
   "skill_dir": ".",
   "summary": {
     "target_count": 5,
diff --git a/reports/context_budget.json b/reports/context_budget.json
index ff3cb719..f68f25cb 100644
--- a/reports/context_budget.json
+++ b/reports/context_budget.json
@@ -6,15 +6,15 @@
     "context_budget_tier": "production",
     "context_budget_limit": 1000,
     "skill_body_tokens": 797,
-    "other_text_tokens": 1045126,
+    "other_text_tokens": 1046015,
     "estimated_initial_load_tokens": 990,
-    "estimated_total_text_tokens": 1045923,
-    "deferred_resource_tokens": 484750,
+    "estimated_total_text_tokens": 1046812,
+    "deferred_resource_tokens": 484786,
     "deferred_resource_warn_threshold": 120000,
     "deferred_resource_dirs": [
       {
         "path": "scripts",
-        "estimated_tokens": 424772,
+        "estimated_tokens": 424808,
         "file_count": 122
       },
       {
@@ -36,7 +36,7 @@
     "large_deferred_resource_dirs": [
       {
         "path": "scripts",
-        "estimated_tokens": 424772,
+        "estimated_tokens": 424808,
         "file_count": 122
       }
     ],
@@ -59,7 +59,7 @@
           ],
           "missing": [],
           "path": "scripts",
-          "estimated_tokens": 424772,
+          "estimated_tokens": 424808,
           "file_count": 122,
           "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
         }
diff --git a/reports/context_budget.md b/reports/context_budget.md
index 62ca623e..5817f898 100644
--- a/reports/context_budget.md
+++ b/reports/context_budget.md
@@ -2,7 +2,7 @@
 
 | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
 | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
-| root | `.` | `production` | 1000 | 990 | 797 | 484750 | `governed` | scripts:424772 | 131.3 | - | ok |
+| root | `.` | `production` | 1000 | 990 | 797 | 484786 | `governed` | scripts:424808 | 131.3 | - | ok |
 | complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok |
 | governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok |
 
diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json
index 358900ea..e4dd2c98 100644
--- a/reports/context_budget_summary.json
+++ b/reports/context_budget_summary.json
@@ -8,11 +8,11 @@
       "budget_limit": 1000,
       "initial_tokens": 990,
       "skill_body_tokens": 797,
-      "deferred_resource_tokens": 484750,
+      "deferred_resource_tokens": 484786,
       "large_deferred_resource_dirs": [
         {
           "path": "scripts",
-          "estimated_tokens": 424772,
+          "estimated_tokens": 424808,
           "file_count": 122
         }
       ],
@@ -35,7 +35,7 @@
             ],
             "missing": [],
             "path": "scripts",
-            "estimated_tokens": 424772,
+            "estimated_tokens": 424808,
             "file_count": 122,
             "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
           }
diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json
index 1f554e24..acbf3621 100644
--- a/reports/evidence_consistency.json
+++ b/reports/evidence_consistency.json
@@ -189,12 +189,12 @@
       "status": "pass",
       "expected": {
         "status": "pass",
-        "detail": "initial load 990/1000; deferred 484750/120000; top deferred scripts 424772; resource governance governed; quality density 131.3",
+        "detail": "initial load 990/1000; deferred 484786/120000; top deferred scripts 424808; resource governance governed; quality density 131.3",
         "evidence": "reports/context_budget.json"
       },
       "actual": {
         "status": "pass",
-        "detail": "initial load 990/1000; deferred 484750/120000; top deferred scripts 424772; resource governance governed; quality density 131.3",
+        "detail": "initial load 990/1000; deferred 484786/120000; top deferred scripts 424808; resource governance governed; quality density 131.3",
         "evidence": "reports/context_budget.json"
       },
       "paths": [
@@ -207,8 +207,8 @@
       "key": "benchmark-release-lock-self-consistency",
       "label": "Benchmark release lock matches git dirty state",
       "status": "pass",
-      "expected": true,
-      "actual": true,
+      "expected": false,
+      "actual": false,
       "paths": [
         "reports/benchmark_reproducibility.json"
       ],
@@ -248,8 +248,8 @@
       "key": "overview-benchmark-commit",
       "label": "overview embeds the benchmark commit",
       "status": "pass",
-      "expected": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
-      "actual": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
+      "expected": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
+      "actual": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
       "paths": [
         "reports/benchmark_reproducibility.json",
         "reports/skill-overview.json"
@@ -261,30 +261,30 @@
       "label": "overview embeds benchmark summary fields",
       "status": "pass",
       "expected": {
-        "release_lock_ready": true,
+        "release_lock_ready": false,
         "required_artifact_count": 25,
         "missing_artifact_count": 0,
-        "source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+        "source_contract_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
         "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
         "world_class_ledger_pending_count": 4,
         "world_class_source_check_count": 13,
-        "world_class_source_pass_count": 6,
-        "world_class_source_blocked_count": 7,
+        "world_class_source_pass_count": 7,
+        "world_class_source_blocked_count": 6,
         "public_claim_ready": false,
-        "public_claim_blocker_count": 4
+        "public_claim_blocker_count": 5
       },
       "actual": {
-        "release_lock_ready": true,
+        "release_lock_ready": false,
         "required_artifact_count": 25,
         "missing_artifact_count": 0,
-        "source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+        "source_contract_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
         "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
         "world_class_ledger_pending_count": 4,
         "world_class_source_check_count": 13,
-        "world_class_source_pass_count": 6,
-        "world_class_source_blocked_count": 7,
+        "world_class_source_pass_count": 7,
+        "world_class_source_blocked_count": 6,
         "public_claim_ready": false,
-        "public_claim_blocker_count": 4
+        "public_claim_blocker_count": 5
       },
       "paths": [
         "reports/benchmark_reproducibility.json",
@@ -298,13 +298,13 @@
       "status": "pass",
       "expected": {
         "event_count": 1,
-        "adoption_sample_count": 0,
-        "activation_count": 0,
-        "accepted_count": 0,
-        "adoption_rate": 0,
+        "adoption_sample_count": 1,
+        "activation_count": 1,
+        "accepted_count": 1,
+        "adoption_rate": 100.0,
         "risk_band": "low",
         "event_types": {
-          "review_event": 1
+          "skill_activation": 1
         },
         "source_types": {
           "manual": 1
@@ -312,13 +312,13 @@
       },
       "actual": {
         "event_count": 1,
-        "adoption_sample_count": 0,
-        "activation_count": 0,
-        "accepted_count": 0,
-        "adoption_rate": 0,
+        "adoption_sample_count": 1,
+        "activation_count": 1,
+        "accepted_count": 1,
+        "adoption_rate": 100.0,
         "risk_band": "low",
         "event_types": {
-          "review_event": 1
+          "skill_activation": 1
         },
         "source_types": {
           "manual": 1
@@ -341,8 +341,8 @@
         "human_pending_count": 1,
         "external_pending_count": 3,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "ready_to_claim_world_class": false,
         "decision": "evidence-pending"
       },
@@ -353,8 +353,8 @@
         "human_pending_count": 1,
         "external_pending_count": 3,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "ready_to_claim_world_class": false,
         "decision": "evidence-pending"
       },
@@ -374,7 +374,7 @@
         "pending_count": 4,
         "accepted_count": 0,
         "source_check_count": 13,
-        "source_pass_count": 6
+        "source_pass_count": 7
       },
       "actual": {
         "ready": false,
@@ -382,7 +382,7 @@
         "pending_count": 4,
         "accepted_count": 0,
         "source_check_count": 13,
-        "source_pass_count": 6
+        "source_pass_count": 7
       },
       "paths": [
         "reports/world_class_evidence_ledger.json",
@@ -394,8 +394,8 @@
       "key": "interpretation-benchmark-commit",
       "label": "interpretation embeds the benchmark commit",
       "status": "pass",
-      "expected": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
-      "actual": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
+      "expected": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
+      "actual": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
       "paths": [
         "reports/benchmark_reproducibility.json",
         "reports/skill-interpretation.json"
@@ -407,30 +407,30 @@
       "label": "interpretation embeds benchmark summary fields",
       "status": "pass",
       "expected": {
-        "release_lock_ready": true,
+        "release_lock_ready": false,
         "required_artifact_count": 25,
         "missing_artifact_count": 0,
-        "source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+        "source_contract_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
         "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
         "world_class_ledger_pending_count": 4,
         "world_class_source_check_count": 13,
-        "world_class_source_pass_count": 6,
-        "world_class_source_blocked_count": 7,
+        "world_class_source_pass_count": 7,
+        "world_class_source_blocked_count": 6,
         "public_claim_ready": false,
-        "public_claim_blocker_count": 4
+        "public_claim_blocker_count": 5
       },
       "actual": {
-        "release_lock_ready": true,
+        "release_lock_ready": false,
         "required_artifact_count": 25,
         "missing_artifact_count": 0,
-        "source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+        "source_contract_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
         "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
         "world_class_ledger_pending_count": 4,
         "world_class_source_check_count": 13,
-        "world_class_source_pass_count": 6,
-        "world_class_source_blocked_count": 7,
+        "world_class_source_pass_count": 7,
+        "world_class_source_blocked_count": 6,
         "public_claim_ready": false,
-        "public_claim_blocker_count": 4
+        "public_claim_blocker_count": 5
       },
       "paths": [
         "reports/benchmark_reproducibility.json",
@@ -444,13 +444,13 @@
       "status": "pass",
       "expected": {
         "event_count": 1,
-        "adoption_sample_count": 0,
-        "activation_count": 0,
-        "accepted_count": 0,
-        "adoption_rate": 0,
+        "adoption_sample_count": 1,
+        "activation_count": 1,
+        "accepted_count": 1,
+        "adoption_rate": 100.0,
         "risk_band": "low",
         "event_types": {
-          "review_event": 1
+          "skill_activation": 1
         },
         "source_types": {
           "manual": 1
@@ -458,13 +458,13 @@
       },
       "actual": {
         "event_count": 1,
-        "adoption_sample_count": 0,
-        "activation_count": 0,
-        "accepted_count": 0,
-        "adoption_rate": 0,
+        "adoption_sample_count": 1,
+        "activation_count": 1,
+        "accepted_count": 1,
+        "adoption_rate": 100.0,
         "risk_band": "low",
         "event_types": {
-          "review_event": 1
+          "skill_activation": 1
         },
         "source_types": {
           "manual": 1
@@ -487,8 +487,8 @@
         "human_pending_count": 1,
         "external_pending_count": 3,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "ready_to_claim_world_class": false,
         "decision": "evidence-pending"
       },
@@ -499,8 +499,8 @@
         "human_pending_count": 1,
         "external_pending_count": 3,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "ready_to_claim_world_class": false,
         "decision": "evidence-pending"
       },
@@ -520,7 +520,7 @@
         "pending_count": 4,
         "accepted_count": 0,
         "source_check_count": 13,
-        "source_pass_count": 6
+        "source_pass_count": 7
       },
       "actual": {
         "ready": false,
@@ -528,7 +528,7 @@
         "pending_count": 4,
         "accepted_count": 0,
         "source_check_count": 13,
-        "source_pass_count": 6
+        "source_pass_count": 7
       },
       "paths": [
         "reports/world_class_evidence_ledger.json",
@@ -1327,7 +1327,7 @@
         "external_pending_count": 3,
         "human_pending_count": 1,
         "source_check_count": 13,
-        "source_pass_count": 6,
+        "source_pass_count": 7,
         "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
         "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
         "entries": [
@@ -1386,8 +1386,7 @@
             "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
             "summary_en": "Real external-client metadata-only events have not been imported yet.",
             "blocked_checks": [
-              "External events",
-              "Adoption sample"
+              "External events"
             ]
           }
         ]
@@ -1401,7 +1400,7 @@
         "external_pending_count": 3,
         "human_pending_count": 1,
         "source_check_count": 13,
-        "source_pass_count": 6,
+        "source_pass_count": 7,
         "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
         "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
         "entries": [
@@ -1460,8 +1459,7 @@
             "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
             "summary_en": "Real external-client metadata-only events have not been imported yet.",
             "blocked_checks": [
-              "External events",
-              "Adoption sample"
+              "External events"
             ]
           }
         ]
@@ -1811,15 +1809,15 @@
       "expected": {
         "world_class_ledger_pending_count": 4,
         "world_class_source_check_count": 13,
-        "world_class_source_pass_count": 6,
-        "world_class_source_blocked_count": 7,
+        "world_class_source_pass_count": 7,
+        "world_class_source_blocked_count": 6,
         "public_claim_ready": false
       },
       "actual": {
         "world_class_ledger_pending_count": 4,
         "world_class_source_check_count": 13,
-        "world_class_source_pass_count": 6,
-        "world_class_source_blocked_count": 7,
+        "world_class_source_pass_count": 7,
+        "world_class_source_blocked_count": 6,
         "public_claim_ready": false
       },
       "paths": [
@@ -1835,8 +1833,8 @@
       "expected": {
         "pending_count": 4,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "ready_to_claim_world_class": false,
         "preflight_counts_as_evidence": false,
         "credential_value_exposed": false
@@ -1844,8 +1842,8 @@
       "actual": {
         "pending_count": 4,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "ready_to_claim_world_class": false,
         "preflight_counts_as_evidence": false,
         "credential_value_exposed": false
@@ -2099,8 +2097,8 @@
         "human_pending_count": 1,
         "external_pending_count": 3,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "plan_keys": [
           "human-adjudication",
           "native-client-telemetry",
@@ -2248,8 +2246,8 @@
         "human_pending_count": 1,
         "external_pending_count": 3,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "plan_keys": [
           "human-adjudication",
           "native-client-telemetry",
diff --git a/reports/install_simulation.json b/reports/install_simulation.json
index 77949e2e..35db4587 100644
--- a/reports/install_simulation.json
+++ b/reports/install_simulation.json
@@ -1,11 +1,11 @@
 {
   "ok": true,
   "schema_version": "2.0",
-  "generated_at": "2026-06-16",
+  "generated_at": "2026-06-13",
   "skill_dir": ".",
-  "package_dir": "dist",
-  "install_root": "dist/install-simulation/simulate-yao-meta-skill",
-  "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
+  "package_dir": "tests/tmp_review_studio/dist",
+  "install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill",
+  "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
   "summary": {
     "archive_present": true,
     "archive_entry_count": 647,
@@ -26,7 +26,7 @@
     {
       "id": "archive-present",
       "status": "pass",
-      "detail": "Package archive exists: dist/yao-meta-skill.zip"
+      "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip"
     },
     {
       "id": "archive-safe-paths",
@@ -272,9 +272,9 @@
   "failures": [],
   "warnings": [],
   "artifacts": {
-    "archive": "dist/yao-meta-skill.zip",
-    "package_manifest": "dist/manifest.json",
-    "json": "reports/install_simulation.json",
-    "markdown": "reports/install_simulation.md"
+    "archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip",
+    "package_manifest": "tests/tmp_review_studio/dist/manifest.json",
+    "json": "tests/tmp_review_studio/install_simulation.json",
+    "markdown": "tests/tmp_review_studio/install_simulation.md"
   }
 }
diff --git a/reports/install_simulation.md b/reports/install_simulation.md
index 6750e007..b0d16dae 100644
--- a/reports/install_simulation.md
+++ b/reports/install_simulation.md
@@ -1,7 +1,7 @@
 # Install Simulation
 
 - OK: `True`
-- Package directory: `dist`
+- Package directory: `tests/tmp_review_studio/dist`
 - Archive extracted: `True`
 - Entrypoint loaded: `True`
 - Manifest loaded: `True`
@@ -16,7 +16,7 @@
 
 | Check | Status | Detail |
 | --- | --- | --- |
-| `archive-present` | `pass` | Package archive exists: dist/yao-meta-skill.zip |
+| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip |
 | `archive-safe-paths` | `pass` | Archive has no absolute or parent-traversal entries |
 | `single-top-level` | `pass` | Archive top-level directory is yao-meta-skill |
 | `entrypoint-load` | `pass` | Installed SKILL.md frontmatter is readable |
diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json
index 59ca0b81..ec5cf0ca 100644
--- a/reports/output_execution_runs.json
+++ b/reports/output_execution_runs.json
@@ -34,7 +34,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 35.96,
+      "duration_ms": 46.38,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -62,7 +62,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 34.37,
+      "duration_ms": 45.36,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -85,7 +85,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 35.25,
+      "duration_ms": 48.62,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -113,7 +113,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 35.14,
+      "duration_ms": 43.77,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -136,7 +136,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 35.63,
+      "duration_ms": 43.21,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -164,7 +164,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 34.11,
+      "duration_ms": 40.08,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -187,7 +187,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 29.98,
+      "duration_ms": 46.12,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -214,7 +214,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 30.13,
+      "duration_ms": 43.65,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -237,7 +237,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 30.48,
+      "duration_ms": 40.54,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -266,7 +266,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 30.28,
+      "duration_ms": 40.25,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md
index 96f53c6f..69660ccc 100644
--- a/reports/output_execution_runs.md
+++ b/reports/output_execution_runs.md
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
 
 | Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
 | --- | --- | --- | --- | ---: | ---: | ---: | --- |
-| skill-package-contract | baseline | command | local-output-eval-runner | 35.96 | 33 | 0.0 | pass |
-| skill-package-contract | with_skill | command | local-output-eval-runner | 34.37 | 73 | 100.0 | pass |
-| output-eval-expectation | baseline | command | local-output-eval-runner | 35.25 | 36 | 0.0 | pass |
-| output-eval-expectation | with_skill | command | local-output-eval-runner | 35.14 | 80 | 100.0 | pass |
-| ir-before-packaging | baseline | command | local-output-eval-runner | 35.63 | 33 | 0.0 | pass |
-| ir-before-packaging | with_skill | command | local-output-eval-runner | 34.11 | 80 | 100.0 | pass |
-| near-neighbor-boundary | baseline | command | local-output-eval-runner | 29.98 | 36 | 0.0 | pass |
-| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.13 | 65 | 100.0 | pass |
-| file-backed-governed-package | baseline | command | local-output-eval-runner | 30.48 | 37 | 0.0 | pass |
-| file-backed-governed-package | with_skill | command | local-output-eval-runner | 30.28 | 98 | 100.0 | pass |
+| skill-package-contract | baseline | command | local-output-eval-runner | 46.38 | 33 | 0.0 | pass |
+| skill-package-contract | with_skill | command | local-output-eval-runner | 45.36 | 73 | 100.0 | pass |
+| output-eval-expectation | baseline | command | local-output-eval-runner | 48.62 | 36 | 0.0 | pass |
+| output-eval-expectation | with_skill | command | local-output-eval-runner | 43.77 | 80 | 100.0 | pass |
+| ir-before-packaging | baseline | command | local-output-eval-runner | 43.21 | 33 | 0.0 | pass |
+| ir-before-packaging | with_skill | command | local-output-eval-runner | 40.08 | 80 | 100.0 | pass |
+| near-neighbor-boundary | baseline | command | local-output-eval-runner | 46.12 | 36 | 0.0 | pass |
+| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 43.65 | 65 | 100.0 | pass |
+| file-backed-governed-package | baseline | command | local-output-eval-runner | 40.54 | 37 | 0.0 | pass |
+| file-backed-governed-package | with_skill | command | local-output-eval-runner | 40.25 | 98 | 100.0 | pass |
 
 ## Next Fixes
 
diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json
index d7673b36..cc2eb6eb 100644
--- a/reports/python_compatibility.json
+++ b/reports/python_compatibility.json
@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-16",
+  "generated_at": "2026-06-13",
   "root": ".",
   "summary": {
     "target_python": "3.11",
diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md
index c7b3e7ff..fa4cccc5 100644
--- a/reports/python_compatibility.md
+++ b/reports/python_compatibility.md
@@ -1,6 +1,6 @@
 # Python Compatibility
 
-Generated at: `2026-06-16`
+Generated at: `2026-06-13`
 
 ## Summary
 
diff --git a/reports/registry_audit.json b/reports/registry_audit.json
index 4bb4130b..e3a1df6e 100644
--- a/reports/registry_audit.json
+++ b/reports/registry_audit.json
@@ -21,7 +21,7 @@
     "trust_level": "local",
     "license": "MIT",
     "checksums": {
-      "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+      "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
       "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81"
     },
     "compatibility": {
@@ -58,11 +58,11 @@
       "install_simulated": true,
       "install_simulation": "reports/install_simulation.json"
     },
-    "generated_at": "2026-06-16"
+    "generated_at": "2026-06-13"
   },
   "index": {
     "schema_version": "2.0",
-    "generated_at": "2026-06-16",
+    "generated_at": "2026-06-13",
     "package_count": 1,
     "packages": [
       {
@@ -78,7 +78,7 @@
           "vscode"
         ],
         "package_metadata": "registry/packages/yao-meta-skill.json",
-        "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+        "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
       }
     ]
   },
diff --git a/reports/registry_audit.md b/reports/registry_audit.md
index 8bed3682..3f15feaa 100644
--- a/reports/registry_audit.md
+++ b/reports/registry_audit.md
@@ -6,7 +6,7 @@
 - Maturity: `governed`
 - Owner: `Yao Team`
 - License: `MIT`
-- Package SHA256: `db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336`
+- Package SHA256: `a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f`
 - Archive SHA256: `996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81`
 - Install simulated: `True`
 
diff --git a/reports/review-studio.html b/reports/review-studio.html
index 18201830..dca66210 100644
--- a/reports/review-studio.html
+++ b/reports/review-studio.html
@@ -740,22 +740,22 @@
 
     <section>
       <h2>核心指标</h2>
-      <div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>122 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>194 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>899 largest lines; 10 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>647 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
+      <div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>122 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>194 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>899 largest lines; 10 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock false</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>647 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
     </section>
 
     <section>
       <h2>审查闸门</h2>
-      <div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 484750/120000; top deferred scripts 424772; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 122 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 194 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>191 Python files; 0 hotspots; 10 watchlist files; 0 blockers; largest 899 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
+      <div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 484786/120000; top deferred scripts 424808; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 122 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 194 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>191 Python files; 0 hotspots; 10 watchlist files; 0 blockers; largest 899 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
     </section>
 
     <div class="twocol">
       <section><h2>阻断事项</h2><p class='muted'>无。</p></section>
-      <section><h2>关注事项</h2><ul class='issues'><li><strong>输出实验</strong><span>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</span></li><li><strong>人工批准</strong><span>0 active waivers; 1 warning gates still need reviewer decision</span></li><li><strong>世界证据</strong><span>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</span></li></ul></section>
+      <section><h2>关注事项</h2><ul class='issues'><li><strong>输出实验</strong><span>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</span></li><li><strong>人工批准</strong><span>0 active waivers; 1 warning gates still need reviewer decision</span></li><li><strong>世界证据</strong><span>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true</span></li></ul></section>
     </div>
 
     <section id="actions">
       <h2>修复动作</h2>
-      <div class="actions-grid"><article class='action-card warn'><div><span>关注</span><h3>输出实验</h3></div><p>补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。</p><small>没有输出质量和人工盲评证据时，Skill 只能证明会触发，不能证明输出真的更好且经得起审查。</small><dl><dt>修复位置</dt><dd>evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md</dd><dt>验证命令</dt><dd><code>python3 scripts/adjudicate_output_review.py --write-template &amp;&amp; python3 scripts/yao.py output-review</code></dd></dl><ul class='source-ref-list'><li><a href='../evals/output/cases.jsonl'>evals/output/cases.jsonl:1</a><small>output eval cases · eval</small><blockquote>{&quot;id&quot;:&quot;skill-package-contract&quot;,&quot;prompt&quot;:&quot;Turn this repeated workflow into a reusable team skill package.&quot;,&quot;baseline_output&quot;:&quot;I can write a prompt for that workflow and include a s…</blockquote></li><li><a href='output_quality_scorecard.md'>reports/output_quality_scorecard.md:1</a><small>output scorecard · report · pattern: # Output</small><blockquote># Output Quality Scorecard</blockquote></li><li><a href='output_execution_runs.md'>reports/output_execution_runs.md:1</a><small>output execution runs · report · pattern: # Output Execution</small><blockquote># Output Execution Runs</blockquote></li><li><a href='output_blind_review_pack.md'>reports/output_blind_review_pack.md:1</a><small>blind A/B review pack · report · pattern: # Output Blind</small><blockquote># Output Blind A/B Review Pack</blockquote></li><li><a href='output_review_kit.html'>reports/output_review_kit.html:6</a><small>reviewer cockpit · report · pattern: Output Review Kit</small><blockquote>&lt;title&gt;Output Review Kit&lt;/title&gt;</blockquote></li><li><a href='output_review_adjudication.md'>reports/output_review_adjudication.md:1</a><small>review adjudication · report · pattern: # Output Review</small><blockquote># Output Review Adjudication</blockquote></li></ul><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>打开证据</a></footer></article><article class='action-card warn'><div><span>关注</span><h3>人工批准</h3></div><p>对保留的 warning 写入 reviewer、理由、范围和到期时间，或修掉 warning。</p><small>warning 可以被接受，但必须可审计、会过期，并且不能掩盖 blocker。</small><dl><dt>修复位置</dt><dd>reports/review_waivers.md</dd><dt>验证命令</dt><dd><code>python3 scripts/render_review_waivers.py .</code></dd></dl><ul class='source-ref-list'><li><a href='review_waivers.md'>reports/review_waivers.md:1</a><small>waiver ledger · report · pattern: # Review</small><blockquote># Review Waivers</blockquote></li><li><a href='../references/review-waiver-method.md'>references/review-waiver-method.md:1</a><small>waiver method · method · pattern: # Review</small><blockquote># Review Waiver Method</blockquote></li></ul><footer>reports/review_waivers.json <a href='review_waivers.md'>打开证据</a></footer></article><article class='action-card warn with-evidence'><div><span>关注</span><h3>世界证据</h3></div><p>补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据，或明确本次发布不声明 world-class 完成。</p><small>世界级结论必须来自已接受的外部/人工证据；计划、metadata fallback、待评审和本地命令都不能替代完成证据。</small><dl><dt>修复位置</dt><dd>reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md</dd><dt>验证命令</dt><dd><code>python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions &amp;&amp; python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions &amp;&amp; python3 scripts/yao.py review-studio .</code></dd></dl><section class='action-evidence-panel'><h4>证据采集</h4><p>以下条目仍需真实外部或人工证据；提交文件、校验命令和阻断检查必须同时闭环。</p><div class='action-evidence-grid'><article class='action-evidence-item pending'><div><span>pending · external</span><h4>Provider Holdout</h4></div><p>model-executed 0; token-observed 0</p><dl><dt>提交</dt><dd><code>evidence/world_class/submissions/provider-holdout.json</code></dd><dt>模板</dt><dd><code>evidence/world_class/templates/provider-holdout.intake.json</code></dd><dt>阻断</dt><dd>2 blocked / 1 pass</dd><dt>下一步</dt><dd>Run provider-backed holdout cases with real credentials and commit only aggregate evidence.</dd></dl><section><h5>阻断检查</h5><ul class='action-evidence-checks'><li class='action-evidence-check blocked'><span>Provider model run</span><code>model_executed_count: 0 / &gt;0</code><small>Run provider-backed output-exec with real credentials.</small></li><li class='action-evidence-check blocked'><span>Token usage observed</span><code>token_observed_count: 0 / &gt;0</code><small>Provider execution should return non-estimated token usage.</small></li></ul></section><details class='action-command-details'><summary>操作命令</summary><ul class='action-command-list'><li><span>准备提交</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions</code></li><li><span>校验入口</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>审查提交</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>刷新台账</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li></ul></details><details class='action-runbook-details'><summary>首要步骤</summary><ol class='action-runbook-list'><li>YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=&lt;redacted&gt; python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.</li></ol></details><details class='action-collection-details'><summary>采集契约</summary><div class='action-collection-grid'><section><h5>来源要求</h5><ul><li>provider-backed model run</li><li>observed timing</li><li>observed token metadata</li></ul></section><section><h5>通过条件</h5><ul><li>reports/output_execution_runs.json summary.model_executed_count &gt; 0</li><li>reports/output_execution_runs.json summary.timing_observed_count &gt; 0</li><li>reports/output_execution_runs.json summary.token_observed_count &gt; 0</li><li>reports/skill_os2_audit.json item provider-holdout status becomes pass</li></ul></section><section><h5>证据资产</h5><ul><li>reports/output_execution_runs.json</li><li>reports/output_execution_runs.md</li><li>reports/skill_os2_audit.json</li><li>evidence/world_class/intake.schema.json</li><li>evidence/world_class/templates/provider-holdout.intake.json</li></ul></section><section><h5>资产角色</h5><p class='muted'>source: <code>world-class-submission-kit</code>; counts as evidence: <code>false</code>; prefill counts as evidence: <code>false</code></p><ul class='action-artifact-roles'><li><strong>submission-ref</strong><span>1 / 1 ready</span><code>artifact_refs: true</code><small>Rows marked submission-ref are the aggregate paths expected in artifact_refs.</small></li><li><strong>supporting-evidence</strong><span>6 / 6 ready</span><code>artifact_refs: false</code><small>Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.</small></li></ul></section><section><h5>隐私边界</h5><ul><li>Do not commit provider credentials or environment dumps.</li><li>The output execution report records output hashes and aggregate run metadata, not raw provider prompts.</li></ul></section></div></details></article><article class='action-evidence-item pending'><div><span>pending · human</span><h4>Human Adjudication</h4></div><p>0/5 decisions; pending 5</p><dl><dt>提交</dt><dd><code>evidence/world_class/submissions/human-adjudication.json</code></dd><dt>模板</dt><dd><code>evidence/world_class/templates/human-adjudication.intake.json</code></dd><dt>阻断</dt><dd>2 blocked / 2 pass</dd><dt>下一步</dt><dd>Record real A/B choices in the decision template, then regenerate adjudication.</dd></dl><section><h5>阻断检查</h5><ul class='action-evidence-checks'><li class='action-evidence-check blocked'><span>No pending decisions</span><code>pending_count: 5 / ==0</code><small>Record a reviewer choice for every pair.</small></li><li class='action-evidence-check blocked'><span>Judgments complete</span><code>judgment_count: 0 / ==pair_count</code><small>Every pair needs one valid human judgment.</small></li></ul></section><details class='action-command-details'><summary>操作命令</summary><ul class='action-command-list'><li><span>准备提交</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions</code></li><li><span>校验入口</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>审查提交</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>刷新台账</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li></ul></details><details class='action-runbook-details'><summary>首要步骤</summary><ol class='action-runbook-list'><li>python3 scripts/yao.py output-review-kit --write-template</li><li>Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.</li><li>python3 scripts/adjudicate_output_review.py --write-template</li></ol></details><details class='action-collection-details'><summary>采集契约</summary><div class='action-collection-grid'><section><h5>来源要求</h5><ul><li>real reviewer identity</li><li>blind A/B decisions</li><li>answer key unopened until decisions exist</li></ul></section><section><h5>通过条件</h5><ul><li>reports/output_review_adjudication.json summary.pending_count == 0</li><li>reports/output_review_adjudication.json summary.judgment_count == summary.pair_count</li><li>reports/output_review_adjudication.json summary.invalid_decision_count == 0</li><li>reports/skill_os2_audit.json item human-adjudication status becomes pass</li></ul></section><section><h5>证据资产</h5><ul><li>reports/output_blind_review_pack.md</li><li>reports/output_review_kit.md</li><li>reports/output_review_decisions.json</li><li>reports/output_review_adjudication.json</li><li>reports/output_review_adjudication.md</li></ul></section><section><h5>资产角色</h5><p class='muted'>source: <code>world-class-submission-kit</code>; counts as evidence: <code>false</code>; prefill counts as evidence: <code>false</code></p><ul class='action-artifact-roles'><li><strong>submission-ref</strong><span>2 / 2 ready</span><code>artifact_refs: true</code><small>Rows marked submission-ref are the aggregate paths expected in artifact_refs.</small></li><li><strong>supporting-evidence</strong><span>8 / 8 ready</span><code>artifact_refs: false</code><small>Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.</small></li></ul></section><section><h5>隐私边界</h5><ul><li>Reviewer decisions should not include raw user data or private customer detail.</li><li>The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.</li><li>Keep the answer key separate until after decisions are recorded.</li></ul></section></div></details></article><article class='action-evidence-item pending'><div><span>pending · external</span><h4>Native Permission Enforcement</h4></div><p>native-enforced targets 0; installer-enforced targets 4</p><dl><dt>提交</dt><dd><code>evidence/world_class/submissions/native-permission-enforcement.json</code></dd><dt>模板</dt><dd><code>evidence/world_class/templates/native-permission-enforcement.intake.json</code></dd><dt>阻断</dt><dd>1 blocked / 2 pass</dd><dt>下一步</dt><dd>Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.</dd></dl><section><h5>阻断检查</h5><ul class='action-evidence-checks'><li class='action-evidence-check blocked'><span>Native enforcement</span><code>native_enforcement_count: 0 / &gt;0</code><small>Collect real target-client or external runtime guard proof.</small></li></ul></section><details class='action-command-details'><summary>操作命令</summary><ul class='action-command-list'><li><span>准备提交</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions</code></li><li><span>校验入口</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>审查提交</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>刷新台账</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li></ul></details><details class='action-runbook-details'><summary>首要步骤</summary><ol class='action-runbook-list'><li>Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.</li><li>Update the generated target adapter only when the guard is actually enforced by that target.</li><li>python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip</li></ol></details><details class='action-collection-details'><summary>采集契约</summary><div class='action-collection-grid'><section><h5>来源要求</h5><ul><li>real target client or external installer runtime guard</li><li>native enforcement flag or externally accepted guard proof</li><li>residual risk retained for fallback targets</li></ul></section><section><h5>通过条件</h5><ul><li>reports/runtime_permission_probes.json summary.native_enforcement_count &gt; 0</li><li>reports/runtime_permission_probes.json summary.failure_count == 0</li><li>reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence</li><li>reports/skill_os2_audit.json item native-permission-enforcement status becomes pass</li></ul></section><section><h5>证据资产</h5><ul><li>dist/targets/*/adapter.json</li><li>reports/runtime_permission_probes.json</li><li>reports/runtime_permission_probes.md</li><li>reports/install_simulation.json</li><li>reports/install_simulation.md</li></ul></section><section><h5>资产角色</h5><p class='muted'>source: <code>world-class-submission-kit</code>; counts as evidence: <code>false</code>; prefill counts as evidence: <code>false</code></p><ul class='action-artifact-roles'><li><strong>submission-ref</strong><span>2 / 2 ready</span><code>artifact_refs: true</code><small>Rows marked submission-ref are the aggregate paths expected in artifact_refs.</small></li><li><strong>supporting-evidence</strong><span>11 / 11 ready</span><code>artifact_refs: false</code><small>Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.</small></li></ul></section><section><h5>隐私边界</h5><ul><li>Do not mark native_enforcement true for metadata-only fallbacks.</li><li>Keep residual risks visible for targets that still rely on operator enforcement.</li></ul></section></div></details></article><article class='action-evidence-item pending'><div><span>pending · external</span><h4>Native Client Telemetry</h4></div><p>external source events 0; adoption samples 0</p><dl><dt>提交</dt><dd><code>evidence/world_class/submissions/native-client-telemetry.json</code></dd><dt>模板</dt><dd><code>evidence/world_class/templates/native-client-telemetry.intake.json</code></dd><dt>阻断</dt><dd>2 blocked / 1 pass</dd><dt>下一步</dt><dd>Install a real client against the native host and import production metadata-only events.</dd></dl><section><h5>阻断检查</h5><ul class='action-evidence-checks'><li class='action-evidence-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='action-evidence-check blocked'><span>Adoption sample</span><code>adoption_sample_count: 0 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li></ul></section><details class='action-command-details'><summary>操作命令</summary><ul class='action-command-list'><li><span>准备提交</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions</code></li><li><span>校验入口</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>审查提交</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>刷新台账</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li></ul></details><details class='action-runbook-details'><summary>首要步骤</summary><ol class='action-runbook-list'><li>python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://&lt;extension-id&gt;/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li></ol></details><details class='action-collection-details'><summary>采集契约</summary><div class='action-collection-grid'><section><h5>来源要求</h5><ul><li>real external client source</li><li>metadata-only event</li><li>local-first import path</li></ul></section><section><h5>通过条件</h5><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></section><section><h5>证据资产</h5><ul><li>reports/adoption_drift_report.json</li><li>reports/adoption_drift_report.md</li><li>reports/telemetry_hook_recipes.json</li><li>scripts/telemetry_native_host.py</li><li>evidence/world_class/intake.schema.json</li></ul></section><section><h5>资产角色</h5><p class='muted'>source: <code>world-class-submission-kit</code>; counts as evidence: <code>false</code>; prefill counts as evidence: <code>false</code></p><ul class='action-artifact-roles'><li><strong>submission-ref</strong><span>2 / 2 ready</span><code>artifact_refs: true</code><small>Rows marked submission-ref are the aggregate paths expected in artifact_refs.</small></li><li><strong>supporting-evidence</strong><span>6 / 6 ready</span><code>artifact_refs: false</code><small>Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.</small></li></ul></section><section><h5>隐私边界</h5><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></section></div></details></article></div></section><ul class='source-ref-list'><li><a href='world_class_evidence_ledger.md'>reports/world_class_evidence_ledger.md:1</a><small>world-class evidence ledger · report · pattern: # World-Class Evidence Ledger</small><blockquote># World-Class Evidence Ledger</blockquote></li><li><a href='world_class_evidence_plan.md'>reports/world_class_evidence_plan.md:1</a><small>world-class evidence plan · report · pattern: # World-Class Evidence Plan</small><blockquote># World-Class Evidence Plan</blockquote></li><li><a href='world_class_evidence_intake.md'>reports/world_class_evidence_intake.md:1</a><small>world-class evidence intake · report · pattern: # World-Class Evidence Intake</small><blockquote># World-Class Evidence Intake</blockquote></li><li><a href='world_class_submission_review.md'>reports/world_class_submission_review.md:1</a><small>world-class submission review · report · pattern: # World-Class Submission Review</small><blockquote># World-Class Submission Review</blockquote></li><li><a href='world_class_claim_guard.md'>reports/world_class_claim_guard.md:1</a><small>world-class claim guard · report · pattern: # World-Class Claim Guard</small><blockquote># World-Class Claim Guard</blockquote></li><li><a href='../evidence/world_class/intake.schema.json'>evidence/world_class/intake.schema.json:4</a><small>evidence intake schema · schema · pattern: Yao World-Class Evidence Intake</small><blockquote>&quot;title&quot;: &quot;Yao World-Class Evidence Intake&quot;,</blockquote></li><li><a href='../evidence/world_class/templates/provider-holdout.intake.json'>evidence/world_class/templates/provider-holdout.intake.json:3</a><small>provider intake template · template · pattern: provider-holdout</small><blockquote>&quot;evidence_key&quot;: &quot;provider-holdout&quot;,</blockquote></li><li><a href='../evidence/world_class/templates/human-adjudication.intake.json'>evidence/world_class/templates/human-adjudication.intake.json:3</a><small>human intake template · template · pattern: human-adjudication</small><blockquote>&quot;evidence_key&quot;: &quot;human-adjudication&quot;,</blockquote></li><li><a href='../evidence/world_class/templates/native-permission-enforcement.intake.json'>evidence/world_class/templates/native-permission-enforcement.intake.json:3</a><small>permission intake template · template · pattern: native-permission-enforcement</small><blockquote>&quot;evidence_key&quot;: &quot;native-permission-enforcement&quot;,</blockquote></li><li><a href='../evidence/world_class/templates/native-client-telemetry.intake.json'>evidence/world_class/templates/native-client-telemetry.intake.json:3</a><small>telemetry intake template · template · pattern: native-client-telemetry</small><blockquote>&quot;evidence_key&quot;: &quot;native-client-telemetry&quot;,</blockquote></li><li><a href='skill_os2_audit.md'>reports/skill_os2_audit.md:1</a><small>Skill OS 2.0 audit · report · pattern: # Skill OS</small><blockquote># Skill OS 2.0 Audit</blockquote></li><li><a href='output_review_decisions.json'>reports/output_review_decisions.json:6</a><small>human review decisions · report · pattern: winner_variant</small><blockquote>&quot;winner_variant&quot;: &quot;Use A or B after reading the blind review pack. Leave blank when pending.&quot;,</blockquote></li><li><a href='runtime_permission_probes.md'>reports/runtime_permission_probes.md:1</a><small>runtime permission probes · report · pattern: # Runtime</small><blockquote># Runtime Permission Probes</blockquote></li><li><a href='adoption_drift_report.md'>reports/adoption_drift_report.md:1</a><small>adoption drift · report · pattern: # Adoption</small><blockquote># Adoption And Drift Report</blockquote></li></ul><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>打开证据</a></footer></article></div>
+      <div class="actions-grid"><article class='action-card warn'><div><span>关注</span><h3>输出实验</h3></div><p>补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。</p><small>没有输出质量和人工盲评证据时，Skill 只能证明会触发，不能证明输出真的更好且经得起审查。</small><dl><dt>修复位置</dt><dd>evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md</dd><dt>验证命令</dt><dd><code>python3 scripts/adjudicate_output_review.py --write-template &amp;&amp; python3 scripts/yao.py output-review</code></dd></dl><ul class='source-ref-list'><li><a href='../evals/output/cases.jsonl'>evals/output/cases.jsonl:1</a><small>output eval cases · eval</small><blockquote>{&quot;id&quot;:&quot;skill-package-contract&quot;,&quot;prompt&quot;:&quot;Turn this repeated workflow into a reusable team skill package.&quot;,&quot;baseline_output&quot;:&quot;I can write a prompt for that workflow and include a s…</blockquote></li><li><a href='output_quality_scorecard.md'>reports/output_quality_scorecard.md:1</a><small>output scorecard · report · pattern: # Output</small><blockquote># Output Quality Scorecard</blockquote></li><li><a href='output_execution_runs.md'>reports/output_execution_runs.md:1</a><small>output execution runs · report · pattern: # Output Execution</small><blockquote># Output Execution Runs</blockquote></li><li><a href='output_blind_review_pack.md'>reports/output_blind_review_pack.md:1</a><small>blind A/B review pack · report · pattern: # Output Blind</small><blockquote># Output Blind A/B Review Pack</blockquote></li><li><a href='output_review_kit.html'>reports/output_review_kit.html:6</a><small>reviewer cockpit · report · pattern: Output Review Kit</small><blockquote>&lt;title&gt;Output Review Kit&lt;/title&gt;</blockquote></li><li><a href='output_review_adjudication.md'>reports/output_review_adjudication.md:1</a><small>review adjudication · report · pattern: # Output Review</small><blockquote># Output Review Adjudication</blockquote></li></ul><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>打开证据</a></footer></article><article class='action-card warn'><div><span>关注</span><h3>人工批准</h3></div><p>对保留的 warning 写入 reviewer、理由、范围和到期时间，或修掉 warning。</p><small>warning 可以被接受，但必须可审计、会过期，并且不能掩盖 blocker。</small><dl><dt>修复位置</dt><dd>reports/review_waivers.md</dd><dt>验证命令</dt><dd><code>python3 scripts/render_review_waivers.py .</code></dd></dl><ul class='source-ref-list'><li><a href='review_waivers.md'>reports/review_waivers.md:1</a><small>waiver ledger · report · pattern: # Review</small><blockquote># Review Waivers</blockquote></li><li><a href='../references/review-waiver-method.md'>references/review-waiver-method.md:1</a><small>waiver method · method · pattern: # Review</small><blockquote># Review Waiver Method</blockquote></li></ul><footer>reports/review_waivers.json <a href='review_waivers.md'>打开证据</a></footer></article><article class='action-card warn with-evidence'><div><span>关注</span><h3>世界证据</h3></div><p>补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据，或明确本次发布不声明 world-class 完成。</p><small>世界级结论必须来自已接受的外部/人工证据；计划、metadata fallback、待评审和本地命令都不能替代完成证据。</small><dl><dt>修复位置</dt><dd>reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md</dd><dt>验证命令</dt><dd><code>python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions &amp;&amp; python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions &amp;&amp; python3 scripts/yao.py review-studio .</code></dd></dl><section class='action-evidence-panel'><h4>证据采集</h4><p>以下条目仍需真实外部或人工证据；提交文件、校验命令和阻断检查必须同时闭环。</p><div class='action-evidence-grid'><article class='action-evidence-item pending'><div><span>pending · external</span><h4>Provider Holdout</h4></div><p>model-executed 0; token-observed 0</p><dl><dt>提交</dt><dd><code>evidence/world_class/submissions/provider-holdout.json</code></dd><dt>模板</dt><dd><code>evidence/world_class/templates/provider-holdout.intake.json</code></dd><dt>阻断</dt><dd>2 blocked / 1 pass</dd><dt>下一步</dt><dd>Run provider-backed holdout cases with real credentials and commit only aggregate evidence.</dd></dl><section><h5>阻断检查</h5><ul class='action-evidence-checks'><li class='action-evidence-check blocked'><span>Provider model run</span><code>model_executed_count: 0 / &gt;0</code><small>Run provider-backed output-exec with real credentials.</small></li><li class='action-evidence-check blocked'><span>Token usage observed</span><code>token_observed_count: 0 / &gt;0</code><small>Provider execution should return non-estimated token usage.</small></li></ul></section><details class='action-command-details'><summary>操作命令</summary><ul class='action-command-list'><li><span>准备提交</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions</code></li><li><span>校验入口</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>审查提交</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>刷新台账</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li></ul></details><details class='action-runbook-details'><summary>首要步骤</summary><ol class='action-runbook-list'><li>Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.</li><li>export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}</li><li>python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60</li></ol></details><details class='action-collection-details'><summary>采集契约</summary><div class='action-collection-grid'><section><h5>来源要求</h5><ul><li>provider-backed model run</li><li>observed timing</li><li>observed token metadata</li></ul></section><section><h5>通过条件</h5><ul><li>reports/output_execution_runs.json summary.model_executed_count &gt; 0</li><li>reports/output_execution_runs.json summary.timing_observed_count &gt; 0</li><li>reports/output_execution_runs.json summary.token_observed_count &gt; 0</li><li>reports/skill_os2_audit.json item provider-holdout status becomes pass</li></ul></section><section><h5>证据资产</h5><ul><li>reports/output_execution_runs.json</li><li>reports/output_execution_runs.md</li><li>reports/skill_os2_audit.json</li><li>evidence/world_class/intake.schema.json</li><li>evidence/world_class/templates/provider-holdout.intake.json</li></ul></section><section><h5>资产角色</h5><p class='muted'>source: <code>world-class-submission-kit</code>; counts as evidence: <code>false</code>; prefill counts as evidence: <code>false</code></p><ul class='action-artifact-roles'><li><strong>submission-ref</strong><span>1 / 1 ready</span><code>artifact_refs: true</code><small>Rows marked submission-ref are the aggregate paths expected in artifact_refs.</small></li><li><strong>supporting-evidence</strong><span>6 / 6 ready</span><code>artifact_refs: false</code><small>Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.</small></li></ul></section><section><h5>隐私边界</h5><ul><li>Do not commit provider credentials or environment dumps.</li><li>The output execution report records output hashes and aggregate run metadata, not raw provider prompts.</li></ul></section></div></details></article><article class='action-evidence-item pending'><div><span>pending · human</span><h4>Human Adjudication</h4></div><p>0/5 decisions; pending 5</p><dl><dt>提交</dt><dd><code>evidence/world_class/submissions/human-adjudication.json</code></dd><dt>模板</dt><dd><code>evidence/world_class/templates/human-adjudication.intake.json</code></dd><dt>阻断</dt><dd>2 blocked / 2 pass</dd><dt>下一步</dt><dd>Record real A/B choices in the decision template, then regenerate adjudication.</dd></dl><section><h5>阻断检查</h5><ul class='action-evidence-checks'><li class='action-evidence-check blocked'><span>No pending decisions</span><code>pending_count: 5 / ==0</code><small>Record a reviewer choice for every pair.</small></li><li class='action-evidence-check blocked'><span>Judgments complete</span><code>judgment_count: 0 / ==pair_count</code><small>Every pair needs one valid human judgment.</small></li></ul></section><details class='action-command-details'><summary>操作命令</summary><ul class='action-command-list'><li><span>准备提交</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions</code></li><li><span>校验入口</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>审查提交</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>刷新台账</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li></ul></details><details class='action-runbook-details'><summary>首要步骤</summary><ol class='action-runbook-list'><li>python3 scripts/yao.py output-review-kit --write-template</li><li>Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.</li><li>python3 scripts/adjudicate_output_review.py --write-template</li></ol></details><details class='action-collection-details'><summary>采集契约</summary><div class='action-collection-grid'><section><h5>来源要求</h5><ul><li>real reviewer identity</li><li>blind A/B decisions</li><li>answer key unopened until decisions exist</li></ul></section><section><h5>通过条件</h5><ul><li>reports/output_review_adjudication.json summary.pending_count == 0</li><li>reports/output_review_adjudication.json summary.judgment_count == summary.pair_count</li><li>reports/output_review_adjudication.json summary.invalid_decision_count == 0</li><li>reports/skill_os2_audit.json item human-adjudication status becomes pass</li></ul></section><section><h5>证据资产</h5><ul><li>reports/output_blind_review_pack.md</li><li>reports/output_review_kit.md</li><li>reports/output_review_decisions.json</li><li>reports/output_review_adjudication.json</li><li>reports/output_review_adjudication.md</li></ul></section><section><h5>资产角色</h5><p class='muted'>source: <code>world-class-submission-kit</code>; counts as evidence: <code>false</code>; prefill counts as evidence: <code>false</code></p><ul class='action-artifact-roles'><li><strong>submission-ref</strong><span>2 / 2 ready</span><code>artifact_refs: true</code><small>Rows marked submission-ref are the aggregate paths expected in artifact_refs.</small></li><li><strong>supporting-evidence</strong><span>8 / 8 ready</span><code>artifact_refs: false</code><small>Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.</small></li></ul></section><section><h5>隐私边界</h5><ul><li>Reviewer decisions should not include raw user data or private customer detail.</li><li>The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.</li><li>Keep the answer key separate until after decisions are recorded.</li></ul></section></div></details></article><article class='action-evidence-item pending'><div><span>pending · external</span><h4>Native Permission Enforcement</h4></div><p>native-enforced targets 0; installer-enforced targets 4</p><dl><dt>提交</dt><dd><code>evidence/world_class/submissions/native-permission-enforcement.json</code></dd><dt>模板</dt><dd><code>evidence/world_class/templates/native-permission-enforcement.intake.json</code></dd><dt>阻断</dt><dd>1 blocked / 2 pass</dd><dt>下一步</dt><dd>Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.</dd></dl><section><h5>阻断检查</h5><ul class='action-evidence-checks'><li class='action-evidence-check blocked'><span>Native enforcement</span><code>native_enforcement_count: 0 / &gt;0</code><small>Collect real target-client or external runtime guard proof.</small></li></ul></section><details class='action-command-details'><summary>操作命令</summary><ul class='action-command-list'><li><span>准备提交</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions</code></li><li><span>校验入口</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>审查提交</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>刷新台账</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li></ul></details><details class='action-runbook-details'><summary>首要步骤</summary><ol class='action-runbook-list'><li>Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.</li><li>Update the generated target adapter only when the guard is actually enforced by that target.</li><li>python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip</li></ol></details><details class='action-collection-details'><summary>采集契约</summary><div class='action-collection-grid'><section><h5>来源要求</h5><ul><li>real target client or external installer runtime guard</li><li>native enforcement flag or externally accepted guard proof</li><li>residual risk retained for fallback targets</li></ul></section><section><h5>通过条件</h5><ul><li>reports/runtime_permission_probes.json summary.native_enforcement_count &gt; 0</li><li>reports/runtime_permission_probes.json summary.failure_count == 0</li><li>reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence</li><li>reports/skill_os2_audit.json item native-permission-enforcement status becomes pass</li></ul></section><section><h5>证据资产</h5><ul><li>dist/targets/*/adapter.json</li><li>reports/runtime_permission_probes.json</li><li>reports/runtime_permission_probes.md</li><li>reports/install_simulation.json</li><li>reports/install_simulation.md</li></ul></section><section><h5>资产角色</h5><p class='muted'>source: <code>world-class-submission-kit</code>; counts as evidence: <code>false</code>; prefill counts as evidence: <code>false</code></p><ul class='action-artifact-roles'><li><strong>submission-ref</strong><span>2 / 2 ready</span><code>artifact_refs: true</code><small>Rows marked submission-ref are the aggregate paths expected in artifact_refs.</small></li><li><strong>supporting-evidence</strong><span>11 / 11 ready</span><code>artifact_refs: false</code><small>Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.</small></li></ul></section><section><h5>隐私边界</h5><ul><li>Do not mark native_enforcement true for metadata-only fallbacks.</li><li>Keep residual risks visible for targets that still rely on operator enforcement.</li></ul></section></div></details></article><article class='action-evidence-item pending'><div><span>pending · external</span><h4>Native Client Telemetry</h4></div><p>external source events 0; adoption samples 1</p><dl><dt>提交</dt><dd><code>evidence/world_class/submissions/native-client-telemetry.json</code></dd><dt>模板</dt><dd><code>evidence/world_class/templates/native-client-telemetry.intake.json</code></dd><dt>阻断</dt><dd>1 blocked / 2 pass</dd><dt>下一步</dt><dd>Install a real client against the native host and import production metadata-only events.</dd></dl><section><h5>阻断检查</h5><ul class='action-evidence-checks'><li class='action-evidence-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li></ul></section><details class='action-command-details'><summary>操作命令</summary><ul class='action-command-list'><li><span>准备提交</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions</code></li><li><span>校验入口</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>审查提交</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>刷新台账</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li></ul></details><details class='action-runbook-details'><summary>首要步骤</summary><ol class='action-runbook-list'><li>python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://&lt;extension-id&gt;/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li></ol></details><details class='action-collection-details'><summary>采集契约</summary><div class='action-collection-grid'><section><h5>来源要求</h5><ul><li>real external client source</li><li>metadata-only event</li><li>local-first import path</li></ul></section><section><h5>通过条件</h5><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></section><section><h5>证据资产</h5><ul><li>reports/adoption_drift_report.json</li><li>reports/adoption_drift_report.md</li><li>reports/telemetry_hook_recipes.json</li><li>scripts/telemetry_native_host.py</li><li>evidence/world_class/intake.schema.json</li></ul></section><section><h5>资产角色</h5><p class='muted'>source: <code>world-class-submission-kit</code>; counts as evidence: <code>false</code>; prefill counts as evidence: <code>false</code></p><ul class='action-artifact-roles'><li><strong>submission-ref</strong><span>2 / 2 ready</span><code>artifact_refs: true</code><small>Rows marked submission-ref are the aggregate paths expected in artifact_refs.</small></li><li><strong>supporting-evidence</strong><span>6 / 6 ready</span><code>artifact_refs: false</code><small>Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.</small></li></ul></section><section><h5>隐私边界</h5><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></section></div></details></article></div></section><ul class='source-ref-list'><li><a href='world_class_evidence_ledger.md'>reports/world_class_evidence_ledger.md:1</a><small>world-class evidence ledger · report · pattern: # World-Class Evidence Ledger</small><blockquote># World-Class Evidence Ledger</blockquote></li><li><a href='world_class_evidence_plan.md'>reports/world_class_evidence_plan.md:1</a><small>world-class evidence plan · report · pattern: # World-Class Evidence Plan</small><blockquote># World-Class Evidence Plan</blockquote></li><li><a href='world_class_evidence_intake.md'>reports/world_class_evidence_intake.md:1</a><small>world-class evidence intake · report · pattern: # World-Class Evidence Intake</small><blockquote># World-Class Evidence Intake</blockquote></li><li><a href='world_class_submission_review.md'>reports/world_class_submission_review.md:1</a><small>world-class submission review · report · pattern: # World-Class Submission Review</small><blockquote># World-Class Submission Review</blockquote></li><li><a href='world_class_claim_guard.md'>reports/world_class_claim_guard.md:1</a><small>world-class claim guard · report · pattern: # World-Class Claim Guard</small><blockquote># World-Class Claim Guard</blockquote></li><li><a href='../evidence/world_class/intake.schema.json'>evidence/world_class/intake.schema.json:4</a><small>evidence intake schema · schema · pattern: Yao World-Class Evidence Intake</small><blockquote>&quot;title&quot;: &quot;Yao World-Class Evidence Intake&quot;,</blockquote></li><li><a href='../evidence/world_class/templates/provider-holdout.intake.json'>evidence/world_class/templates/provider-holdout.intake.json:3</a><small>provider intake template · template · pattern: provider-holdout</small><blockquote>&quot;evidence_key&quot;: &quot;provider-holdout&quot;,</blockquote></li><li><a href='../evidence/world_class/templates/human-adjudication.intake.json'>evidence/world_class/templates/human-adjudication.intake.json:3</a><small>human intake template · template · pattern: human-adjudication</small><blockquote>&quot;evidence_key&quot;: &quot;human-adjudication&quot;,</blockquote></li><li><a href='../evidence/world_class/templates/native-permission-enforcement.intake.json'>evidence/world_class/templates/native-permission-enforcement.intake.json:3</a><small>permission intake template · template · pattern: native-permission-enforcement</small><blockquote>&quot;evidence_key&quot;: &quot;native-permission-enforcement&quot;,</blockquote></li><li><a href='../evidence/world_class/templates/native-client-telemetry.intake.json'>evidence/world_class/templates/native-client-telemetry.intake.json:3</a><small>telemetry intake template · template · pattern: native-client-telemetry</small><blockquote>&quot;evidence_key&quot;: &quot;native-client-telemetry&quot;,</blockquote></li><li><a href='skill_os2_audit.md'>reports/skill_os2_audit.md:1</a><small>Skill OS 2.0 audit · report · pattern: # Skill OS</small><blockquote># Skill OS 2.0 Audit</blockquote></li><li><a href='output_review_decisions.json'>reports/output_review_decisions.json:6</a><small>human review decisions · report · pattern: winner_variant</small><blockquote>&quot;winner_variant&quot;: &quot;Use A or B after reading the blind review pack. Leave blank when pending.&quot;,</blockquote></li><li><a href='runtime_permission_probes.md'>reports/runtime_permission_probes.md:1</a><small>runtime permission probes · report · pattern: # Runtime</small><blockquote># Runtime Permission Probes</blockquote></li><li><a href='adoption_drift_report.md'>reports/adoption_drift_report.md:1</a><small>adoption drift · report · pattern: # Adoption</small><blockquote># Adoption And Drift Report</blockquote></li></ul><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>打开证据</a></footer></article></div>
     </section>
 
     <section id="annotations">
@@ -807,12 +807,12 @@
     </section>
 
     <section class="twocol">
-      <div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 484750/120000; top deferred scripts 424772; resource governance governed; quality density 131.3</p></div>
+      <div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 484786/120000; top deferred scripts 424808; resource governance governed; quality density 131.3</p></div>
       <div class="panel"><h2>编译证据</h2><p>Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.</p></div>
     </section>
 
     <section id="trust" class="twocol">
-      <div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>122</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336</code></dd></div></dl></div>
+      <div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>122</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f</code></dd></div></dl></div>
       <div class="panel"><h2>安全边界</h2><p>高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。</p></div>
     </section>
 
@@ -837,14 +837,14 @@
     </section>
 
     <section id="telemetry" class="twocol">
-      <div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p></div>
-      <div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>0</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
+      <div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p></div>
+      <div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>100</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
     </section>
 
     
     <section class="twocol">
-      <div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
-      <div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>1</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
+      <div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
+      <div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>1</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
     </section>
 
 
@@ -856,19 +856,19 @@
         <div class="panel"><h2>批准台账</h2><dl class='kv-grid'><div><dt>Waiver Count</dt><dd>0</dd></div><div><dt>Active Count</dt><dd>0</dd></div><div><dt>Expired Count</dt><dd>0</dd></div><div><dt>Invalid Count</dt><dd>0</dd></div><div><dt>覆盖 Gate</dt><dd>0</dd></div></dl></div>
       </div>
       <h3 class="section-subtitle">批准候选</h3>
-      <div class='waiver-candidate-grid'><article class='waiver-card allowed'><div><span>可批准 · needs-reviewer-decision</span><h3>Output Lab</h3></div><p>review pending 5; model-executed 0; output failures 0</p><dl><dt>Gate</dt><dd><code>output-lab</code></dd><dt>证据</dt><dd><code>reports/output_review_adjudication.md</code></dd><dt>选项</dt><dd>accepted-risk, false-positive, temporary-exception</dd><dt>边界</dt><dd>Does not count as provider, human, or public world-class completion evidence.</dd></dl><div class='waiver-review'><h4>审查条件</h4><ul><li>Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.</li><li>Reviewer names the release scope and expiry date.</li><li>Reviewer links output_review_adjudication or output_execution evidence.</li></ul></div><div class='waiver-command'><span>建议命令</span><code>python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer &quot;&lt;reviewer&gt;&quot; --reason &quot;Output Lab has pending human/provider evidence; accepted only for this bounded review scope.&quot; --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md</code></div></article><article class='waiver-card blocked'><div><span>不可批准 · cannot-waive</span><h3>World-Class Evidence</h3></div><p>4 pending evidence entries; 1 human pending; 3 external pending</p><dl><dt>Gate</dt><dd><code>world-class-evidence</code></dd><dt>证据</dt><dd><code>reports/world_class_evidence_ledger.md</code></dd><dt>选项</dt><dd>无</dd><dt>边界</dt><dd>Non-waivable completion boundary.</dd></dl><div class='waiver-review'><h4>审查条件</h4><ul><li>Do not use a waiver to claim public world-class readiness.</li><li>Either submit accepted ledger evidence or state that this release does not claim world-class completion.</li><li>Keep claim guard active until ledger summary.ready_to_claim_world_class is true.</li></ul></div><div class='waiver-command'><span>建议命令</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions &amp;&amp; python3 scripts/yao.py world-class-claim-guard .</code></div></article></div>
+      <div class='waiver-candidate-grid'><article class='waiver-card allowed'><div><span>可批准 · needs-reviewer-decision</span><h3>Output Lab</h3></div><p>review pending 5; model-executed 0; output failures 0</p><dl><dt>Gate</dt><dd><code>output-lab</code></dd><dt>证据</dt><dd><code>reports/output_review_adjudication.md</code></dd><dt>选项</dt><dd>accepted-risk, false-positive, temporary-exception</dd><dt>边界</dt><dd>Does not count as provider, human, or public world-class completion evidence.</dd></dl><div class='waiver-review'><h4>审查条件</h4><ul><li>Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.</li><li>Reviewer names the release scope and expiry date.</li><li>Reviewer links output_review_adjudication or output_execution evidence.</li></ul></div><div class='waiver-command'><span>建议命令</span><code>python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer &quot;&lt;reviewer&gt;&quot; --reason &quot;Output Lab has pending human/provider evidence; accepted only for this bounded review scope.&quot; --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md</code></div></article><article class='waiver-card blocked'><div><span>不可批准 · cannot-waive</span><h3>World-Class Evidence</h3></div><p>4 pending evidence entries; 1 human pending; 3 external pending</p><dl><dt>Gate</dt><dd><code>world-class-evidence</code></dd><dt>证据</dt><dd><code>reports/world_class_evidence_ledger.md</code></dd><dt>选项</dt><dd>无</dd><dt>边界</dt><dd>Non-waivable completion boundary.</dd></dl><div class='waiver-review'><h4>审查条件</h4><ul><li>Do not use a waiver to claim public world-class readiness.</li><li>Either submit accepted ledger evidence or state that this release does not claim world-class completion.</li><li>Keep claim guard active until ledger summary.ready_to_claim_world_class is true.</li></ul></div><div class='waiver-command'><span>建议命令</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions &amp;&amp; python3 scripts/yao.py world-class-claim-guard .</code></div></article></div>
     </section>
 
     <section id="world-class">
       <h2>世界证据</h2>
       <p class="muted">这里列出每个 world-class 证据项的当前状态、完成定义、证据来源、隐私约束和下一步；计划、metadata fallback、待评审和本地命令不会被当成完成证据。</p>
-      <div class='world-evidence-grid'><article class='world-evidence-card pending'><div><span>待补证 · external</span><h3>Provider Holdout</h3></div><p>Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.</p><dl><dt>负责人</dt><dd>operator with provider credentials</dd><dt>当前状态</dt><dd>model-executed 0; token-observed 0</dd><dt>下一步</dt><dd>Run provider-backed holdout cases with real credentials and commit only aggregate evidence.</dd><dt>观测值</dt><dd>model_executed_count: 0; timing_observed_count: 10; token_observed_count: 0; accepted: False</dd><dt>提交态</dt><dd>status: missing; path: evidence/world_class/submissions/provider-holdout.json; attested_real_evidence: False; privacy_contract_satisfied: False</dd></dl><section class='world-runbook-panel'><h4>执行步骤</h4><ul><li>YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=&lt;redacted&gt; python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section><div class='world-evidence-columns'><div><h4>完成定义</h4><ul><li>reports/output_execution_runs.json summary.model_executed_count &gt; 0</li><li>reports/output_execution_runs.json summary.timing_observed_count &gt; 0</li><li>reports/output_execution_runs.json summary.token_observed_count &gt; 0</li><li>reports/skill_os2_audit.json item provider-holdout status becomes pass</li></ul></div><div><h4>证据来源</h4><ul><li>reports/output_execution_runs.json</li><li>reports/output_execution_runs.md</li><li>reports/skill_os2_audit.json</li><li>evidence/world_class/intake.schema.json</li><li>evidence/world_class/templates/provider-holdout.intake.json</li><li>reports/world_class_evidence_intake.json</li><li>reports/world_class_evidence_intake.md</li></ul></div><div><h4>隐私约束</h4><ul><li>Do not commit provider credentials or environment dumps.</li><li>The output execution report records output hashes and aggregate run metadata, not raw provider prompts.</li></ul></div></div><section class='world-source-panel'><h4>源证据检查</h4><ul class='world-source-checks'><li class='world-source-check blocked'><span>Provider model run</span><code>model_executed_count: 0 / &gt;0</code><small>Run provider-backed output-exec with real credentials.</small></li><li class='world-source-check pass'><span>Timing observed</span><code>timing_observed_count: 10 / &gt;0</code><small>Provider execution should record timing metadata.</small></li><li class='world-source-check blocked'><span>Token usage observed</span><code>token_observed_count: 0 / &gt;0</code><small>Provider execution should return non-estimated token usage.</small></li></ul></section></article><article class='world-evidence-card pending'><div><span>待补证 · human</span><h3>Human Adjudication</h3></div><p>Record real blind A/B reviewer decisions before claiming human output review completion.</p><dl><dt>负责人</dt><dd>human reviewer</dd><dt>当前状态</dt><dd>0/5 decisions; pending 5</dd><dt>下一步</dt><dd>Record real A/B choices in the decision template, then regenerate adjudication.</dd><dt>观测值</dt><dd>pair_count: 5; judgment_count: 0; pending_count: 5; invalid_decision_count: 0; answer_revealed_count: 0; accepted: False</dd><dt>提交态</dt><dd>status: missing; path: evidence/world_class/submissions/human-adjudication.json; attested_real_evidence: False; privacy_contract_satisfied: False</dd></dl><section class='world-runbook-panel'><h4>执行步骤</h4><ul><li>python3 scripts/yao.py output-review-kit --write-template</li><li>Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.</li><li>python3 scripts/adjudicate_output_review.py --write-template</li><li>Record reviewer choices in a separate JSON, JSONL, or CSV decision source with case_id, winner_variant, confidence, and reason only.</li><li>python3 scripts/yao.py output-review-import --input &lt;reviewer-decisions.json&gt; --run-adjudication</li><li>python3 scripts/yao.py output-review</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section><div class='world-evidence-columns'><div><h4>完成定义</h4><ul><li>reports/output_review_adjudication.json summary.pending_count == 0</li><li>reports/output_review_adjudication.json summary.judgment_count == summary.pair_count</li><li>reports/output_review_adjudication.json summary.invalid_decision_count == 0</li><li>reports/skill_os2_audit.json item human-adjudication status becomes pass</li></ul></div><div><h4>证据来源</h4><ul><li>reports/output_blind_review_pack.md</li><li>reports/output_review_kit.md</li><li>reports/output_review_decisions.json</li><li>reports/output_review_adjudication.json</li><li>reports/output_review_adjudication.md</li><li>scripts/import_output_review_decisions.py</li><li>evidence/world_class/intake.schema.json</li><li>evidence/world_class/templates/human-adjudication.intake.json</li><li>reports/world_class_evidence_intake.json</li><li>reports/world_class_evidence_intake.md</li></ul></div><div><h4>隐私约束</h4><ul><li>Reviewer decisions should not include raw user data or private customer detail.</li><li>The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.</li><li>Keep the answer key separate until after decisions are recorded.</li></ul></div></div><section class='world-source-panel'><h4>源证据检查</h4><ul class='world-source-checks'><li class='world-source-check pass'><span>Review pairs exist</span><code>pair_count: 5 / &gt;0</code><small>Generate the blind A/B review pack.</small></li><li class='world-source-check blocked'><span>No pending decisions</span><code>pending_count: 5 / ==0</code><small>Record a reviewer choice for every pair.</small></li><li class='world-source-check blocked'><span>Judgments complete</span><code>judgment_count: 0 / ==pair_count</code><small>Every pair needs one valid human judgment.</small></li><li class='world-source-check pass'><span>No invalid decisions</span><code>invalid_decision_count: 0 / ==0</code><small>Fix malformed winner/confidence entries.</small></li></ul></section></article><article class='world-evidence-card pending'><div><span>待补证 · external</span><h3>Native Permission Enforcement</h3></div><p>Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.</p><dl><dt>负责人</dt><dd>target client or installer integrator</dd><dt>当前状态</dt><dd>native-enforced targets 0; installer-enforced targets 4</dd><dt>下一步</dt><dd>Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.</dd><dt>观测值</dt><dd>native_enforcement_count: 0; metadata_fallback_count: 4; installer_enforcement_pass_count: 4; installer_permission_failure_count: 0; installer_enforcement_ready: True; residual_risk_count: 4; failure_count: 0; accepted: False</dd><dt>提交态</dt><dd>status: missing; path: evidence/world_class/submissions/native-permission-enforcement.json; attested_real_evidence: False; privacy_contract_satisfied: False</dd></dl><section class='world-runbook-panel'><h4>执行步骤</h4><ul><li>Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.</li><li>Update the generated target adapter only when the guard is actually enforced by that target.</li><li>python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip</li><li>python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation</li><li>python3 scripts/yao.py runtime-permissions . --package-dir dist</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section><div class='world-evidence-columns'><div><h4>完成定义</h4><ul><li>reports/runtime_permission_probes.json summary.native_enforcement_count &gt; 0</li><li>reports/runtime_permission_probes.json summary.failure_count == 0</li><li>reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence</li><li>reports/skill_os2_audit.json item native-permission-enforcement status becomes pass</li></ul></div><div><h4>证据来源</h4><ul><li>dist/targets/*/adapter.json</li><li>reports/runtime_permission_probes.json</li><li>reports/runtime_permission_probes.md</li><li>reports/install_simulation.json</li><li>reports/install_simulation.md</li><li>security/permission_policy.json</li><li>evidence/world_class/intake.schema.json</li><li>evidence/world_class/templates/native-permission-enforcement.intake.json</li><li>reports/world_class_evidence_intake.json</li><li>reports/world_class_evidence_intake.md</li></ul></div><div><h4>隐私约束</h4><ul><li>Do not mark native_enforcement true for metadata-only fallbacks.</li><li>Keep residual risks visible for targets that still rely on operator enforcement.</li></ul></div></div><section class='world-source-panel'><h4>源证据检查</h4><ul class='world-source-checks'><li class='world-source-check blocked'><span>Native enforcement</span><code>native_enforcement_count: 0 / &gt;0</code><small>Collect real target-client or external runtime guard proof.</small></li><li class='world-source-check pass'><span>Probe failures</span><code>failure_count: 0 / ==0</code><small>Runtime permission probes must stay clean.</small></li><li class='world-source-check pass'><span>Installer support</span><code>installer_enforcement_ready: True / true</code><small>Installer enforcement is supporting evidence, not native proof.</small></li></ul></section></article><article class='world-evidence-card pending'><div><span>待补证 · external</span><h3>Native Client Telemetry</h3></div><p>Import production metadata-only events from a real external client into the local drift loop.</p><dl><dt>负责人</dt><dd>Browser/Chrome/IDE/provider client integrator</dd><dt>当前状态</dt><dd>external source events 0; adoption samples 0</dd><dt>下一步</dt><dd>Install a real client against the native host and import production metadata-only events.</dd><dt>观测值</dt><dd>external_source_events: 0; adoption_sample_count: 0; raw_content_allowed: False; risk_band: low; accepted: False</dd><dt>提交态</dt><dd>status: missing; path: evidence/world_class/submissions/native-client-telemetry.json; attested_real_evidence: False; privacy_contract_satisfied: False</dd></dl><section class='world-runbook-panel'><h4>执行步骤</h4><ul><li>python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://&lt;extension-id&gt;/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li><li>python3 scripts/yao.py skill-atlas --workspace-root .</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section><div class='world-evidence-columns'><div><h4>完成定义</h4><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></div><div><h4>证据来源</h4><ul><li>reports/adoption_drift_report.json</li><li>reports/adoption_drift_report.md</li><li>reports/telemetry_hook_recipes.json</li><li>scripts/telemetry_native_host.py</li><li>evidence/world_class/intake.schema.json</li><li>evidence/world_class/templates/native-client-telemetry.intake.json</li><li>reports/world_class_evidence_intake.json</li><li>reports/world_class_evidence_intake.md</li></ul></div><div><h4>隐私约束</h4><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></div></div><section class='world-source-panel'><h4>源证据检查</h4><ul class='world-source-checks'><li class='world-source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='world-source-check blocked'><span>Adoption sample</span><code>adoption_sample_count: 0 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='world-source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section></article></div>
+      <div class='world-evidence-grid'><article class='world-evidence-card pending'><div><span>待补证 · external</span><h3>Provider Holdout</h3></div><p>Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.</p><dl><dt>负责人</dt><dd>operator with provider credentials</dd><dt>当前状态</dt><dd>model-executed 0; token-observed 0</dd><dt>下一步</dt><dd>Run provider-backed holdout cases with real credentials and commit only aggregate evidence.</dd><dt>观测值</dt><dd>model_executed_count: 0; timing_observed_count: 10; token_observed_count: 0; accepted: False</dd><dt>提交态</dt><dd>status: missing; path: evidence/world_class/submissions/provider-holdout.json; attested_real_evidence: False; privacy_contract_satisfied: False</dd></dl><section class='world-runbook-panel'><h4>执行步骤</h4><ul><li>Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.</li><li>export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}</li><li>python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section><div class='world-evidence-columns'><div><h4>完成定义</h4><ul><li>reports/output_execution_runs.json summary.model_executed_count &gt; 0</li><li>reports/output_execution_runs.json summary.timing_observed_count &gt; 0</li><li>reports/output_execution_runs.json summary.token_observed_count &gt; 0</li><li>reports/skill_os2_audit.json item provider-holdout status becomes pass</li></ul></div><div><h4>证据来源</h4><ul><li>reports/output_execution_runs.json</li><li>reports/output_execution_runs.md</li><li>reports/skill_os2_audit.json</li><li>evidence/world_class/intake.schema.json</li><li>evidence/world_class/templates/provider-holdout.intake.json</li><li>reports/world_class_evidence_intake.json</li><li>reports/world_class_evidence_intake.md</li></ul></div><div><h4>隐私约束</h4><ul><li>Do not commit provider credentials or environment dumps.</li><li>The output execution report records output hashes and aggregate run metadata, not raw provider prompts.</li></ul></div></div><section class='world-source-panel'><h4>源证据检查</h4><ul class='world-source-checks'><li class='world-source-check blocked'><span>Provider model run</span><code>model_executed_count: 0 / &gt;0</code><small>Run provider-backed output-exec with real credentials.</small></li><li class='world-source-check pass'><span>Timing observed</span><code>timing_observed_count: 10 / &gt;0</code><small>Provider execution should record timing metadata.</small></li><li class='world-source-check blocked'><span>Token usage observed</span><code>token_observed_count: 0 / &gt;0</code><small>Provider execution should return non-estimated token usage.</small></li></ul></section></article><article class='world-evidence-card pending'><div><span>待补证 · human</span><h3>Human Adjudication</h3></div><p>Record real blind A/B reviewer decisions before claiming human output review completion.</p><dl><dt>负责人</dt><dd>human reviewer</dd><dt>当前状态</dt><dd>0/5 decisions; pending 5</dd><dt>下一步</dt><dd>Record real A/B choices in the decision template, then regenerate adjudication.</dd><dt>观测值</dt><dd>pair_count: 5; judgment_count: 0; pending_count: 5; invalid_decision_count: 0; answer_revealed_count: 0; accepted: False</dd><dt>提交态</dt><dd>status: missing; path: evidence/world_class/submissions/human-adjudication.json; attested_real_evidence: False; privacy_contract_satisfied: False</dd></dl><section class='world-runbook-panel'><h4>执行步骤</h4><ul><li>python3 scripts/yao.py output-review-kit --write-template</li><li>Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.</li><li>python3 scripts/adjudicate_output_review.py --write-template</li><li>Record reviewer choices in a separate JSON, JSONL, or CSV decision source with case_id, winner_variant, confidence, and reason only.</li><li>python3 scripts/yao.py output-review-import --input &lt;reviewer-decisions.json&gt; --run-adjudication</li><li>python3 scripts/yao.py output-review</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section><div class='world-evidence-columns'><div><h4>完成定义</h4><ul><li>reports/output_review_adjudication.json summary.pending_count == 0</li><li>reports/output_review_adjudication.json summary.judgment_count == summary.pair_count</li><li>reports/output_review_adjudication.json summary.invalid_decision_count == 0</li><li>reports/skill_os2_audit.json item human-adjudication status becomes pass</li></ul></div><div><h4>证据来源</h4><ul><li>reports/output_blind_review_pack.md</li><li>reports/output_review_kit.md</li><li>reports/output_review_decisions.json</li><li>reports/output_review_adjudication.json</li><li>reports/output_review_adjudication.md</li><li>scripts/import_output_review_decisions.py</li><li>evidence/world_class/intake.schema.json</li><li>evidence/world_class/templates/human-adjudication.intake.json</li><li>reports/world_class_evidence_intake.json</li><li>reports/world_class_evidence_intake.md</li></ul></div><div><h4>隐私约束</h4><ul><li>Reviewer decisions should not include raw user data or private customer detail.</li><li>The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.</li><li>Keep the answer key separate until after decisions are recorded.</li></ul></div></div><section class='world-source-panel'><h4>源证据检查</h4><ul class='world-source-checks'><li class='world-source-check pass'><span>Review pairs exist</span><code>pair_count: 5 / &gt;0</code><small>Generate the blind A/B review pack.</small></li><li class='world-source-check blocked'><span>No pending decisions</span><code>pending_count: 5 / ==0</code><small>Record a reviewer choice for every pair.</small></li><li class='world-source-check blocked'><span>Judgments complete</span><code>judgment_count: 0 / ==pair_count</code><small>Every pair needs one valid human judgment.</small></li><li class='world-source-check pass'><span>No invalid decisions</span><code>invalid_decision_count: 0 / ==0</code><small>Fix malformed winner/confidence entries.</small></li></ul></section></article><article class='world-evidence-card pending'><div><span>待补证 · external</span><h3>Native Permission Enforcement</h3></div><p>Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.</p><dl><dt>负责人</dt><dd>target client or installer integrator</dd><dt>当前状态</dt><dd>native-enforced targets 0; installer-enforced targets 4</dd><dt>下一步</dt><dd>Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.</dd><dt>观测值</dt><dd>native_enforcement_count: 0; metadata_fallback_count: 4; installer_enforcement_pass_count: 4; installer_permission_failure_count: 0; installer_enforcement_ready: True; residual_risk_count: 4; failure_count: 0; accepted: False</dd><dt>提交态</dt><dd>status: missing; path: evidence/world_class/submissions/native-permission-enforcement.json; attested_real_evidence: False; privacy_contract_satisfied: False</dd></dl><section class='world-runbook-panel'><h4>执行步骤</h4><ul><li>Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.</li><li>Update the generated target adapter only when the guard is actually enforced by that target.</li><li>python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip</li><li>python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation</li><li>python3 scripts/yao.py runtime-permissions . --package-dir dist</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section><div class='world-evidence-columns'><div><h4>完成定义</h4><ul><li>reports/runtime_permission_probes.json summary.native_enforcement_count &gt; 0</li><li>reports/runtime_permission_probes.json summary.failure_count == 0</li><li>reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence</li><li>reports/skill_os2_audit.json item native-permission-enforcement status becomes pass</li></ul></div><div><h4>证据来源</h4><ul><li>dist/targets/*/adapter.json</li><li>reports/runtime_permission_probes.json</li><li>reports/runtime_permission_probes.md</li><li>reports/install_simulation.json</li><li>reports/install_simulation.md</li><li>security/permission_policy.json</li><li>evidence/world_class/intake.schema.json</li><li>evidence/world_class/templates/native-permission-enforcement.intake.json</li><li>reports/world_class_evidence_intake.json</li><li>reports/world_class_evidence_intake.md</li></ul></div><div><h4>隐私约束</h4><ul><li>Do not mark native_enforcement true for metadata-only fallbacks.</li><li>Keep residual risks visible for targets that still rely on operator enforcement.</li></ul></div></div><section class='world-source-panel'><h4>源证据检查</h4><ul class='world-source-checks'><li class='world-source-check blocked'><span>Native enforcement</span><code>native_enforcement_count: 0 / &gt;0</code><small>Collect real target-client or external runtime guard proof.</small></li><li class='world-source-check pass'><span>Probe failures</span><code>failure_count: 0 / ==0</code><small>Runtime permission probes must stay clean.</small></li><li class='world-source-check pass'><span>Installer support</span><code>installer_enforcement_ready: True / true</code><small>Installer enforcement is supporting evidence, not native proof.</small></li></ul></section></article><article class='world-evidence-card pending'><div><span>待补证 · external</span><h3>Native Client Telemetry</h3></div><p>Import production metadata-only events from a real external client into the local drift loop.</p><dl><dt>负责人</dt><dd>Browser/Chrome/IDE/provider client integrator</dd><dt>当前状态</dt><dd>external source events 0; adoption samples 1</dd><dt>下一步</dt><dd>Install a real client against the native host and import production metadata-only events.</dd><dt>观测值</dt><dd>external_source_events: 0; adoption_sample_count: 1; raw_content_allowed: False; risk_band: low; accepted: False</dd><dt>提交态</dt><dd>status: missing; path: evidence/world_class/submissions/native-client-telemetry.json; attested_real_evidence: False; privacy_contract_satisfied: False</dd></dl><section class='world-runbook-panel'><h4>执行步骤</h4><ul><li>python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://&lt;extension-id&gt;/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li><li>python3 scripts/yao.py skill-atlas --workspace-root .</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section><div class='world-evidence-columns'><div><h4>完成定义</h4><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></div><div><h4>证据来源</h4><ul><li>reports/adoption_drift_report.json</li><li>reports/adoption_drift_report.md</li><li>reports/telemetry_hook_recipes.json</li><li>scripts/telemetry_native_host.py</li><li>evidence/world_class/intake.schema.json</li><li>evidence/world_class/templates/native-client-telemetry.intake.json</li><li>reports/world_class_evidence_intake.json</li><li>reports/world_class_evidence_intake.md</li></ul></div><div><h4>隐私约束</h4><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></div></div><section class='world-source-panel'><h4>源证据检查</h4><ul class='world-source-checks'><li class='world-source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='world-source-check pass'><span>Adoption sample</span><code>adoption_sample_count: 1 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='world-source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section></article></div>
     </section>
 
     <section>
       <h2>提交清单</h2>
       <p class="muted">每张卡片给出模板、提交文件、准备命令、校验命令、收集要求、通过条件和隐私边界；只有真实 provider、真人、原生权限或真实客户端证据通过 intake 后，才进入 ledger review。</p>
-      <div class='world-intake-grid'><article class='world-intake-card awaiting-submission'><div><span>awaiting-submission · external</span><h3>Provider Holdout</h3></div><p>No real evidence submission has been provided yet.</p><dl><dt>负责人</dt><dd>operator with provider credentials</dd><dt>模板</dt><dd><code>evidence/world_class/templates/provider-holdout.intake.json</code></dd><dt>提交</dt><dd><code>evidence/world_class/submissions/provider-holdout.json</code></dd><dt>下一步</dt><dd>Run provider-backed holdout cases with real credentials and commit only aggregate evidence.</dd></dl><div class='world-intake-steps'><div><h4>操作命令</h4><ul class='world-intake-commands'><li><span>prepare_submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions</code></li><li><span>validate_intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>submission_review</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh_ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard_claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></div><div><h4>收集要求</h4><ul><li>provider-backed model run</li><li>observed timing</li><li>observed token metadata</li></ul></div><div><h4>执行步骤</h4><ul><li>YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=&lt;redacted&gt; python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></div><div><h4>通过条件</h4><ul><li>reports/output_execution_runs.json summary.model_executed_count &gt; 0</li><li>reports/output_execution_runs.json summary.timing_observed_count &gt; 0</li><li>reports/output_execution_runs.json summary.token_observed_count &gt; 0</li><li>reports/skill_os2_audit.json item provider-holdout status becomes pass</li></ul></div><div><h4>隐私边界</h4><ul><li>Do not commit provider credentials or environment dumps.</li><li>The output execution report records output hashes and aggregate run metadata, not raw provider prompts.</li></ul></div></div></article><article class='world-intake-card awaiting-submission'><div><span>awaiting-submission · human</span><h3>Human Adjudication</h3></div><p>No real evidence submission has been provided yet.</p><dl><dt>负责人</dt><dd>human reviewer</dd><dt>模板</dt><dd><code>evidence/world_class/templates/human-adjudication.intake.json</code></dd><dt>提交</dt><dd><code>evidence/world_class/submissions/human-adjudication.json</code></dd><dt>下一步</dt><dd>Record real A/B choices in the decision template, then regenerate adjudication.</dd></dl><div class='world-intake-steps'><div><h4>操作命令</h4><ul class='world-intake-commands'><li><span>prepare_submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions</code></li><li><span>validate_intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>submission_review</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh_ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard_claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></div><div><h4>收集要求</h4><ul><li>real reviewer identity</li><li>blind A/B decisions</li><li>answer key unopened until decisions exist</li></ul></div><div><h4>执行步骤</h4><ul><li>python3 scripts/yao.py output-review-kit --write-template</li><li>Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.</li><li>python3 scripts/adjudicate_output_review.py --write-template</li><li>Record reviewer choices in a separate JSON, JSONL, or CSV decision source with case_id, winner_variant, confidence, and reason only.</li><li>python3 scripts/yao.py output-review-import --input &lt;reviewer-decisions.json&gt; --run-adjudication</li><li>python3 scripts/yao.py output-review</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></div><div><h4>通过条件</h4><ul><li>reports/output_review_adjudication.json summary.pending_count == 0</li><li>reports/output_review_adjudication.json summary.judgment_count == summary.pair_count</li><li>reports/output_review_adjudication.json summary.invalid_decision_count == 0</li><li>reports/skill_os2_audit.json item human-adjudication status becomes pass</li></ul></div><div><h4>隐私边界</h4><ul><li>Reviewer decisions should not include raw user data or private customer detail.</li><li>The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.</li><li>Keep the answer key separate until after decisions are recorded.</li></ul></div></div></article><article class='world-intake-card awaiting-submission'><div><span>awaiting-submission · external</span><h3>Native Permission Enforcement</h3></div><p>No real evidence submission has been provided yet.</p><dl><dt>负责人</dt><dd>target client or installer integrator</dd><dt>模板</dt><dd><code>evidence/world_class/templates/native-permission-enforcement.intake.json</code></dd><dt>提交</dt><dd><code>evidence/world_class/submissions/native-permission-enforcement.json</code></dd><dt>下一步</dt><dd>Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.</dd></dl><div class='world-intake-steps'><div><h4>操作命令</h4><ul class='world-intake-commands'><li><span>prepare_submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions</code></li><li><span>validate_intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>submission_review</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh_ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard_claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></div><div><h4>收集要求</h4><ul><li>real target client or external installer runtime guard</li><li>native enforcement flag or externally accepted guard proof</li><li>residual risk retained for fallback targets</li></ul></div><div><h4>执行步骤</h4><ul><li>Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.</li><li>Update the generated target adapter only when the guard is actually enforced by that target.</li><li>python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip</li><li>python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation</li><li>python3 scripts/yao.py runtime-permissions . --package-dir dist</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></div><div><h4>通过条件</h4><ul><li>reports/runtime_permission_probes.json summary.native_enforcement_count &gt; 0</li><li>reports/runtime_permission_probes.json summary.failure_count == 0</li><li>reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence</li><li>reports/skill_os2_audit.json item native-permission-enforcement status becomes pass</li></ul></div><div><h4>隐私边界</h4><ul><li>Do not mark native_enforcement true for metadata-only fallbacks.</li><li>Keep residual risks visible for targets that still rely on operator enforcement.</li></ul></div></div></article><article class='world-intake-card awaiting-submission'><div><span>awaiting-submission · external</span><h3>Native Client Telemetry</h3></div><p>No real evidence submission has been provided yet.</p><dl><dt>负责人</dt><dd>Browser/Chrome/IDE/provider client integrator</dd><dt>模板</dt><dd><code>evidence/world_class/templates/native-client-telemetry.intake.json</code></dd><dt>提交</dt><dd><code>evidence/world_class/submissions/native-client-telemetry.json</code></dd><dt>下一步</dt><dd>Install a real client against the native host and import production metadata-only events.</dd></dl><div class='world-intake-steps'><div><h4>操作命令</h4><ul class='world-intake-commands'><li><span>prepare_submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions</code></li><li><span>validate_intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>submission_review</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh_ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard_claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></div><div><h4>收集要求</h4><ul><li>real external client source</li><li>metadata-only event</li><li>local-first import path</li></ul></div><div><h4>执行步骤</h4><ul><li>python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://&lt;extension-id&gt;/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li><li>python3 scripts/yao.py skill-atlas --workspace-root .</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></div><div><h4>通过条件</h4><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></div><div><h4>隐私边界</h4><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></div></div></article></div>
+      <div class='world-intake-grid'><article class='world-intake-card awaiting-submission'><div><span>awaiting-submission · external</span><h3>Provider Holdout</h3></div><p>No real evidence submission has been provided yet.</p><dl><dt>负责人</dt><dd>operator with provider credentials</dd><dt>模板</dt><dd><code>evidence/world_class/templates/provider-holdout.intake.json</code></dd><dt>提交</dt><dd><code>evidence/world_class/submissions/provider-holdout.json</code></dd><dt>下一步</dt><dd>Run provider-backed holdout cases with real credentials and commit only aggregate evidence.</dd></dl><div class='world-intake-steps'><div><h4>操作命令</h4><ul class='world-intake-commands'><li><span>prepare_submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions</code></li><li><span>validate_intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>submission_review</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh_ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard_claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></div><div><h4>收集要求</h4><ul><li>provider-backed model run</li><li>observed timing</li><li>observed token metadata</li></ul></div><div><h4>执行步骤</h4><ul><li>Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.</li><li>export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}</li><li>python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></div><div><h4>通过条件</h4><ul><li>reports/output_execution_runs.json summary.model_executed_count &gt; 0</li><li>reports/output_execution_runs.json summary.timing_observed_count &gt; 0</li><li>reports/output_execution_runs.json summary.token_observed_count &gt; 0</li><li>reports/skill_os2_audit.json item provider-holdout status becomes pass</li></ul></div><div><h4>隐私边界</h4><ul><li>Do not commit provider credentials or environment dumps.</li><li>The output execution report records output hashes and aggregate run metadata, not raw provider prompts.</li></ul></div></div></article><article class='world-intake-card awaiting-submission'><div><span>awaiting-submission · human</span><h3>Human Adjudication</h3></div><p>No real evidence submission has been provided yet.</p><dl><dt>负责人</dt><dd>human reviewer</dd><dt>模板</dt><dd><code>evidence/world_class/templates/human-adjudication.intake.json</code></dd><dt>提交</dt><dd><code>evidence/world_class/submissions/human-adjudication.json</code></dd><dt>下一步</dt><dd>Record real A/B choices in the decision template, then regenerate adjudication.</dd></dl><div class='world-intake-steps'><div><h4>操作命令</h4><ul class='world-intake-commands'><li><span>prepare_submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions</code></li><li><span>validate_intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>submission_review</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh_ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard_claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></div><div><h4>收集要求</h4><ul><li>real reviewer identity</li><li>blind A/B decisions</li><li>answer key unopened until decisions exist</li></ul></div><div><h4>执行步骤</h4><ul><li>python3 scripts/yao.py output-review-kit --write-template</li><li>Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.</li><li>python3 scripts/adjudicate_output_review.py --write-template</li><li>Record reviewer choices in a separate JSON, JSONL, or CSV decision source with case_id, winner_variant, confidence, and reason only.</li><li>python3 scripts/yao.py output-review-import --input &lt;reviewer-decisions.json&gt; --run-adjudication</li><li>python3 scripts/yao.py output-review</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></div><div><h4>通过条件</h4><ul><li>reports/output_review_adjudication.json summary.pending_count == 0</li><li>reports/output_review_adjudication.json summary.judgment_count == summary.pair_count</li><li>reports/output_review_adjudication.json summary.invalid_decision_count == 0</li><li>reports/skill_os2_audit.json item human-adjudication status becomes pass</li></ul></div><div><h4>隐私边界</h4><ul><li>Reviewer decisions should not include raw user data or private customer detail.</li><li>The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.</li><li>Keep the answer key separate until after decisions are recorded.</li></ul></div></div></article><article class='world-intake-card awaiting-submission'><div><span>awaiting-submission · external</span><h3>Native Permission Enforcement</h3></div><p>No real evidence submission has been provided yet.</p><dl><dt>负责人</dt><dd>target client or installer integrator</dd><dt>模板</dt><dd><code>evidence/world_class/templates/native-permission-enforcement.intake.json</code></dd><dt>提交</dt><dd><code>evidence/world_class/submissions/native-permission-enforcement.json</code></dd><dt>下一步</dt><dd>Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.</dd></dl><div class='world-intake-steps'><div><h4>操作命令</h4><ul class='world-intake-commands'><li><span>prepare_submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions</code></li><li><span>validate_intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>submission_review</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh_ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard_claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></div><div><h4>收集要求</h4><ul><li>real target client or external installer runtime guard</li><li>native enforcement flag or externally accepted guard proof</li><li>residual risk retained for fallback targets</li></ul></div><div><h4>执行步骤</h4><ul><li>Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.</li><li>Update the generated target adapter only when the guard is actually enforced by that target.</li><li>python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip</li><li>python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation</li><li>python3 scripts/yao.py runtime-permissions . --package-dir dist</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></div><div><h4>通过条件</h4><ul><li>reports/runtime_permission_probes.json summary.native_enforcement_count &gt; 0</li><li>reports/runtime_permission_probes.json summary.failure_count == 0</li><li>reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence</li><li>reports/skill_os2_audit.json item native-permission-enforcement status becomes pass</li></ul></div><div><h4>隐私边界</h4><ul><li>Do not mark native_enforcement true for metadata-only fallbacks.</li><li>Keep residual risks visible for targets that still rely on operator enforcement.</li></ul></div></div></article><article class='world-intake-card awaiting-submission'><div><span>awaiting-submission · external</span><h3>Native Client Telemetry</h3></div><p>No real evidence submission has been provided yet.</p><dl><dt>负责人</dt><dd>Browser/Chrome/IDE/provider client integrator</dd><dt>模板</dt><dd><code>evidence/world_class/templates/native-client-telemetry.intake.json</code></dd><dt>提交</dt><dd><code>evidence/world_class/submissions/native-client-telemetry.json</code></dd><dt>下一步</dt><dd>Install a real client against the native host and import production metadata-only events.</dd></dl><div class='world-intake-steps'><div><h4>操作命令</h4><ul class='world-intake-commands'><li><span>prepare_submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions</code></li><li><span>validate_intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>submission_review</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh_ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard_claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></div><div><h4>收集要求</h4><ul><li>real external client source</li><li>metadata-only event</li><li>local-first import path</li></ul></div><div><h4>执行步骤</h4><ul><li>python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://&lt;extension-id&gt;/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li><li>python3 scripts/yao.py skill-atlas --workspace-root .</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></div><div><h4>通过条件</h4><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></div><div><h4>隐私边界</h4><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></div></div></article></div>
     </section>
 
     <section class="twocol">
@@ -877,12 +877,12 @@
     </section>
 
     <section class="twocol">
-      <div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
-      <div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
+      <div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
+      <div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (7/13 pass, 6 blocked)</span></li></ul></div>
     </section>
 
     <section class="twocol">
-      <div class="panel"><h2>世界证据</h2><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p></div>
+      <div class="panel"><h2>世界证据</h2><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true</p></div>
       <div class="panel"><h2>证据台账</h2><dl class='kv-grid'><div><dt>Ledger Entry Count</dt><dd>4</dd></div><div><dt>Accepted Count</dt><dd>0</dd></div><div><dt>待审</dt><dd>4</dd></div><div><dt>Human Pending Count</dt><dd>1</dd></div><div><dt>External Pending Count</dt><dd>3</dd></div><div><dt>Overclaim Guard Active</dt><dd>是</dd></div><div><dt>Ready To Claim World Class</dt><dd>否</dd></div></dl></div>
     </section>
 
diff --git a/reports/review-studio.json b/reports/review-studio.json
index f18470ed..fc8aa114 100644
--- a/reports/review-studio.json
+++ b/reports/review-studio.json
@@ -43,7 +43,7 @@
       "key": "context-budget",
       "label": "上下文",
       "status": "pass",
-      "detail": "initial load 990/1000; deferred 484750/120000; top deferred scripts 424772; resource governance governed; quality density 131.3",
+      "detail": "initial load 990/1000; deferred 484786/120000; top deferred scripts 424808; resource governance governed; quality density 131.3",
       "evidence": "reports/context_budget.json",
       "link": "context_budget.md"
     },
@@ -107,7 +107,7 @@
       "key": "operations-loop",
       "label": "运营回路",
       "status": "pass",
-      "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true",
+      "detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false",
       "evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly",
       "link": "adoption_drift_report.md"
     },
@@ -123,7 +123,7 @@
       "key": "world-class-evidence",
       "label": "世界证据",
       "status": "warn",
-      "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true",
+      "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true",
       "evidence": "reports/world_class_evidence_ledger.json",
       "link": "world_class_evidence_ledger.md"
     },
@@ -166,7 +166,7 @@
       "key": "world-class-evidence",
       "label": "世界证据",
       "status": "warn",
-      "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true",
+      "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true",
       "evidence": "reports/world_class_evidence_ledger.json",
       "link": "world_class_evidence_ledger.md"
     }
@@ -494,9 +494,9 @@
             }
           ],
           "runbook": [
-            "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
-            "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
-            "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields."
+            "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+            "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+            "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60"
           ],
           "provenance_requirements": [
             "provider-backed model run",
@@ -771,12 +771,12 @@
           "category": "external",
           "status": "pending",
           "readiness": "awaiting-submission",
-          "current": "external source events 0; adoption samples 0",
+          "current": "external source events 0; adoption samples 1",
           "next_action": "Install a real client against the native host and import production metadata-only events.",
           "submission_path": "evidence/world_class/submissions/native-client-telemetry.json",
           "template_path": "evidence/world_class/templates/native-client-telemetry.intake.json",
-          "source_pass_count": 1,
-          "source_blocked_count": 2,
+          "source_pass_count": 2,
+          "source_blocked_count": 1,
           "blocked_checks": [
             {
               "label": "External events",
@@ -785,14 +785,6 @@
               "expected": ">0",
               "status": "blocked",
               "next_action": "Import at least one metadata-only event from a real client."
-            },
-            {
-              "label": "Adoption sample",
-              "field": "adoption_sample_count",
-              "actual": 0,
-              "expected": ">0",
-              "status": "blocked",
-              "next_action": "Telemetry must include adoption outcome evidence."
             }
           ],
           "commands": [
@@ -1337,7 +1329,7 @@
         "external_pending_count": 3,
         "human_pending_count": 1,
         "source_check_count": 13,
-        "source_pass_count": 6,
+        "source_pass_count": 7,
         "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
         "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
         "entries": [
@@ -1396,8 +1388,7 @@
             "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
             "summary_en": "Real external-client metadata-only events have not been imported yet.",
             "blocked_checks": [
-              "External events",
-              "Adoption sample"
+              "External events"
             ]
           }
         ]
@@ -1922,12 +1913,12 @@
         "ok": true,
         "summary": {
           "reproducibility_ready": true,
-          "release_lock_ready": true,
+          "release_lock_ready": false,
           "methodology_complete": true,
           "required_artifact_count": 25,
           "missing_artifact_count": 0,
-          "evidence_bundle_sha256": "7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1",
-          "source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+          "evidence_bundle_sha256": "95c6335a413934f197ca1595747c312701edb6028e8fc2ffed6cc4755c0a8d1f",
+          "source_contract_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
           "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
           "output_case_count": 5,
           "failure_disclosure_count": 3,
@@ -1943,14 +1934,14 @@
           "world_class_task_count": 4,
           "world_class_ledger_pending_count": 4,
           "world_class_source_check_count": 13,
-          "world_class_source_pass_count": 6,
-          "world_class_source_blocked_count": 7,
+          "world_class_source_pass_count": 7,
+          "world_class_source_blocked_count": 6,
           "public_claim_ready": false,
-          "public_claim_blocker_count": 4,
-          "working_tree_dirty": false,
-          "changed_file_count": 0
+          "public_claim_blocker_count": 5,
+          "working_tree_dirty": true,
+          "changed_file_count": 64
         },
-        "commit": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
+        "commit": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
         "missing_artifacts": [],
         "limitations": [
           "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -2055,7 +2046,7 @@
         "interactive_script_count": 0,
         "package_hash_scope": "source-contract-without-generated-reports",
         "package_hash_file_count": 213,
-        "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+        "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
       },
       "skill_atlas": {
         "skill_count": 12,
@@ -2093,7 +2084,7 @@
           "trust_level": "local",
           "license": "MIT",
           "checksums": {
-            "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+            "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
             "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81"
           },
           "compatibility": {
@@ -2130,7 +2121,7 @@
             "install_simulated": true,
             "install_simulation": "reports/install_simulation.json"
           },
-          "generated_at": "2026-06-16"
+          "generated_at": "2026-06-13"
         },
         "failures": [],
         "warnings": []
@@ -2225,7 +2216,7 @@
             {
               "field": "package_sha256",
               "from": "0000000000000000000000000000000000000000000000000000000000000000",
-              "to": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+              "to": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
             }
           ]
         },
@@ -2242,14 +2233,14 @@
         "ok": true,
         "summary": {
           "event_count": 1,
-          "adoption_sample_count": 0,
-          "activation_count": 0,
-          "accepted_count": 0,
+          "adoption_sample_count": 1,
+          "activation_count": 1,
+          "accepted_count": 1,
           "edited_count": 0,
           "rejected_count": 0,
           "missed_count": 0,
           "failed_count": 0,
-          "adoption_rate": 0,
+          "adoption_rate": 100.0,
           "missed_trigger_count": 0,
           "wrong_trigger_count": 0,
           "bad_output_count": 0,
@@ -2258,7 +2249,7 @@
           "review_overdue_count": 0,
           "risk_band": "low",
           "event_types": {
-            "review_event": 1
+            "skill_activation": 1
           },
           "failure_types": {},
           "source_types": {
@@ -2365,7 +2356,9 @@
             "current": "model-executed 0; token-observed 0",
             "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
             "runbook": [
-              "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+              "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+              "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+              "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
               "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
               "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
               "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -2483,7 +2476,7 @@
             "status": "external_required",
             "category": "external",
             "owner": "Browser/Chrome/IDE/provider client integrator",
-            "current": "external source events 0; adoption samples 0",
+            "current": "external source events 0; adoption samples 1",
             "objective": "Import production metadata-only events from a real external client into the local drift loop.",
             "runbook": [
               "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -2535,8 +2528,8 @@
           "missing_submission_count": 4,
           "invalid_submission_count": 0,
           "source_check_count": 13,
-          "source_pass_count": 6,
-          "source_blocked_count": 7,
+          "source_pass_count": 7,
+          "source_blocked_count": 6,
           "submitted_but_pending_count": 0,
           "source_accepted_without_valid_submission_count": 0,
           "overclaim_guard_active": true,
@@ -2555,7 +2548,9 @@
             "current": "model-executed 0; token-observed 0",
             "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
             "runbook": [
-              "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+              "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+              "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+              "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
               "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
               "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
               "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -2875,7 +2870,7 @@
             "status": "pending",
             "source_status": "external_required",
             "source_accepted": false,
-            "current": "external source events 0; adoption samples 0",
+            "current": "external source events 0; adoption samples 1",
             "objective": "Import production metadata-only events from a real external client into the local drift loop.",
             "runbook": [
               "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -2912,7 +2907,7 @@
             ],
             "observed_state": {
               "external_source_events": 0,
-              "adoption_sample_count": 0,
+              "adoption_sample_count": 1,
               "raw_content_allowed": false,
               "risk_band": "low",
               "accepted": false
@@ -2933,8 +2928,8 @@
                 "label": "Adoption sample",
                 "field": "adoption_sample_count",
                 "expected": ">0",
-                "actual": 0,
-                "status": "blocked",
+                "actual": 1,
+                "status": "pass",
                 "source_accepted": false,
                 "next_action": "Telemetry must include adoption outcome evidence."
               },
@@ -2950,8 +2945,8 @@
               }
             ],
             "source_check_count": 3,
-            "source_pass_count": 1,
-            "source_blocked_count": 2,
+            "source_pass_count": 2,
+            "source_blocked_count": 1,
             "submission_state": {
               "status": "missing",
               "path": "evidence/world_class/submissions/native-client-telemetry.json",
@@ -4598,7 +4593,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 35.96,
+          "duration_ms": 46.38,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4626,7 +4621,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 34.37,
+          "duration_ms": 45.36,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4649,7 +4644,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 35.25,
+          "duration_ms": 48.62,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4677,7 +4672,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 35.14,
+          "duration_ms": 43.77,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4700,7 +4695,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 35.63,
+          "duration_ms": 43.21,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4728,7 +4723,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 34.11,
+          "duration_ms": 40.08,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4751,7 +4746,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 29.98,
+          "duration_ms": 46.12,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4778,7 +4773,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 30.13,
+          "duration_ms": 43.65,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4801,7 +4796,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 30.48,
+          "duration_ms": 40.54,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4830,7 +4825,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 30.28,
+          "duration_ms": 40.25,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -5556,22 +5551,35 @@
       "ok": true,
       "generated_at": "2026-06-16",
       "skill_dir": ".",
-      "commit": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
+      "commit": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
       "git_status": {
         "available": true,
-        "dirty": false,
-        "changed_file_count": 0,
-        "sample": [],
+        "dirty": true,
+        "changed_file_count": 64,
+        "sample": [
+          " M evidence/world_class/templates/provider-holdout.intake.json",
+          " M registry/index.json",
+          " M registry/packages/yao-meta-skill.json",
+          " M reports/adoption_drift_report.json",
+          " M reports/adoption_drift_report.md",
+          " M reports/architecture_maintainability.json",
+          " M reports/architecture_maintainability.md",
+          " M reports/benchmark_reproducibility.json",
+          " M reports/benchmark_reproducibility.md",
+          " M reports/compiled_targets.json",
+          " M reports/context_budget.json",
+          " M reports/context_budget.md"
+        ],
         "scope": "generation-time status before this report is written"
       },
       "summary": {
         "reproducibility_ready": true,
-        "release_lock_ready": true,
+        "release_lock_ready": false,
         "methodology_complete": true,
         "required_artifact_count": 25,
         "missing_artifact_count": 0,
-        "evidence_bundle_sha256": "7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1",
-        "source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+        "evidence_bundle_sha256": "95c6335a413934f197ca1595747c312701edb6028e8fc2ffed6cc4755c0a8d1f",
+        "source_contract_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
         "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
         "output_case_count": 5,
         "failure_disclosure_count": 3,
@@ -5587,29 +5595,30 @@
         "world_class_task_count": 4,
         "world_class_ledger_pending_count": 4,
         "world_class_source_check_count": 13,
-        "world_class_source_pass_count": 6,
-        "world_class_source_blocked_count": 7,
+        "world_class_source_pass_count": 7,
+        "world_class_source_blocked_count": 6,
         "public_claim_ready": false,
-        "public_claim_blocker_count": 4,
-        "working_tree_dirty": false,
-        "changed_file_count": 0
+        "public_claim_blocker_count": 5,
+        "working_tree_dirty": true,
+        "changed_file_count": 64
       },
       "public_claim": {
         "ready": false,
         "scope": "public benchmark or world-class readiness claim",
         "blockers": [
+          "release lock is not clean or commit is unavailable",
           "provider-backed model holdout evidence is incomplete",
           "human blind-review adjudication is incomplete",
           "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
-          "world-class source checks are not all accepted (6/13 pass, 7 blocked)"
+          "world-class source checks are not all accepted (7/13 pass, 6 blocked)"
         ],
         "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
       },
       "release_lock": {
-        "ready": true,
-        "commit": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
+        "ready": false,
+        "commit": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
         "status_scope": "generation-time status before this report is written",
-        "reason": "clean generation-time HEAD"
+        "reason": "working tree was dirty at generation time"
       },
       "evidence_bundle": {
         "algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -5617,7 +5626,7 @@
         "existing_count": 25,
         "missing_count": 0,
         "missing_paths": [],
-        "sha256": "7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1"
+        "sha256": "95c6335a413934f197ca1595747c312701edb6028e8fc2ffed6cc4755c0a8d1f"
       },
       "methodology": {
         "path": "reports/benchmark_methodology.md",
@@ -5691,7 +5700,7 @@
           "path": "reports/output_execution_runs.json",
           "exists": true,
           "bytes": 7967,
-          "sha256": "ab66dfd1a1f2fca481752aa164271a8c4f419cab9653f45dd63d1c73011713bb"
+          "sha256": "072e7ff6ef9c938f9b876bd950a69ede0c3d87939fc79f10c0b69b6df250c45d"
         },
         {
           "label": "blind_review",
@@ -5726,21 +5735,21 @@
           "path": "reports/security_trust_report.json",
           "exists": true,
           "bytes": 118486,
-          "sha256": "ca53fbf5fa66f574d34603b160c3c3a264b015ba2722deb930b5accb94b52af8"
+          "sha256": "390ddd84dcfb27f7d1c6a3e6216c526ff1ec1ca86c11ea22dfdcdc0403e71cda"
         },
         {
           "label": "python_compatibility",
           "path": "reports/python_compatibility.json",
           "exists": true,
           "bytes": 25199,
-          "sha256": "18c8a142c8108071bc453367c1fd3589b3368c098d5fc27f4b1d11c19f0bfb92"
+          "sha256": "dbd04851a3a6a14273a2e62823ee6d1d181d2e91b88c8c34d2a1b5ca284bc35a"
         },
         {
           "label": "registry_audit",
           "path": "reports/registry_audit.json",
           "exists": true,
           "bytes": 3183,
-          "sha256": "7f980caf507c7d094401a18194eeeb7480de3a924326b6d0c97e07b33e3fb64f"
+          "sha256": "7762378b6fe7a3228b24e6a69499efb8e7ea3c394de1c9714c4d886fc38857ff"
         },
         {
           "label": "package_verification",
@@ -5753,78 +5762,78 @@
           "label": "install_simulation",
           "path": "reports/install_simulation.json",
           "exists": true,
-          "bytes": 8604,
-          "sha256": "aa45be12d2a94664dce95884668839d58808eaad70de90cfb1e96939e9e3a3c0"
+          "bytes": 8758,
+          "sha256": "ba0b8b088b64b1b60715075da4502048c50b2b00d922c6cc7bd3456dca148b34"
         },
         {
           "label": "skill_os2_audit",
           "path": "reports/skill_os2_audit.json",
           "exists": true,
           "bytes": 14310,
-          "sha256": "a4dfc4e3af1167e3d6ced9444c41bc6cd2133bb67942fedba94c046814bf7866"
+          "sha256": "6187a8850680edd24e84161003d3d06379f5f9665ad1ed6e509b661283c62a44"
         },
         {
           "label": "world_class_evidence_plan",
           "path": "reports/world_class_evidence_plan.json",
           "exists": true,
-          "bytes": 20554,
-          "sha256": "38e95161404d2dc9a1c7bf3c1ee213a051ced5444deb01b0a01e557a4321021d"
+          "bytes": 20828,
+          "sha256": "af3c3f101ad992820bf36ddb14b02e7404ef16411567c483f86eed530ca45f62"
         },
         {
           "label": "world_class_evidence_ledger",
           "path": "reports/world_class_evidence_ledger.json",
           "exists": true,
-          "bytes": 21587,
-          "sha256": "d08019f31a7811ee747392f24a11902f173201054894c0338d80b45543c88d18"
+          "bytes": 21721,
+          "sha256": "6c135aced3443b88cc45009957386b566be80fd5c7f261361163dada861dab43"
         },
         {
           "label": "world_class_evidence_intake",
           "path": "reports/world_class_evidence_intake.json",
           "exists": true,
-          "bytes": 19178,
-          "sha256": "4a9119aba62b7cbc9f6b434c33f58a73d2fd623e1f4ed67c3ca994f23025a317"
+          "bytes": 19319,
+          "sha256": "69afd0ff3d49ba9e1ea57248e41cfe62a0abfdf06fd0f997ed3008a5656c2566"
         },
         {
           "label": "world_class_evidence_preflight",
           "path": "reports/world_class_evidence_preflight.json",
           "exists": true,
-          "bytes": 41071,
-          "sha256": "37fd4b91f92ceda3a5873431d5629b33c7909c10fbdc465eaad546e45562328f"
+          "bytes": 41202,
+          "sha256": "97924dd4be88bedd734bb0530765ce5ea6e10a92d2a17807c14b2aae5b66f960"
         },
         {
           "label": "world_class_submission_review",
           "path": "reports/world_class_submission_review.json",
           "exists": true,
-          "bytes": 13658,
-          "sha256": "6aaf868374ba134afbb4d4bf9c0339604ab41b7439379241359b83c279e9207f"
+          "bytes": 13655,
+          "sha256": "17def7ba6982d834e13ce3896dd9093019eec3ee8d2fa5b283ef8d6b17b19be0"
         },
         {
           "label": "world_class_operator_runbook",
           "path": "reports/world_class_operator_runbook.json",
           "exists": true,
-          "bytes": 24330,
-          "sha256": "40d1796964450e55bbaea98e46b0aa3433693e0b532c89b77ce5279c020570ff"
+          "bytes": 24403,
+          "sha256": "f2e53f857320f4c98faa8375e6b4758a8b6b291497578ec9adb14baeb6ee169c"
         },
         {
           "label": "world_class_operator_runbook_markdown",
           "path": "reports/world_class_operator_runbook.md",
           "exists": true,
-          "bytes": 15360,
-          "sha256": "ebfa3a4b528044bdf40f8931a246b54eb7cf37afe55bc02cad95f6e04ea4efa0"
+          "bytes": 15424,
+          "sha256": "337fb764b98ad2707f5a0d7bba88b9c5401256d7be00f8f3dc478e89e3bcb6c2"
         },
         {
           "label": "world_class_operator_runbook_html",
           "path": "reports/world_class_operator_runbook.html",
           "exists": true,
-          "bytes": 21284,
-          "sha256": "eb6c4506b0f25f01eef077c7c65bfe3f3230d3991b0db3befa8798768254373f"
+          "bytes": 21348,
+          "sha256": "ca72c65b437b2211d08b9d463c9a33a7993b4e388bb75f62757ead4dfcf81a49"
         },
         {
           "label": "world_class_claim_guard",
           "path": "reports/world_class_claim_guard.json",
           "exists": true,
           "bytes": 18406,
-          "sha256": "704aba252d55e9b9f546392ce7f51b91f3b74d3384501d7f80a74e14c5b50acd"
+          "sha256": "25206d72ff919a2a4ce398b80a602028ab5f6a43648b5d3b690b3fdd02f49280"
         }
       ],
       "missing_artifacts": [],
@@ -6775,7 +6784,7 @@
     "compiled_targets": {
       "schema_version": "1.0",
       "ok": true,
-      "generated_at": "2026-06-16",
+      "generated_at": "2026-06-13",
       "skill_dir": ".",
       "summary": {
         "target_count": 5,
@@ -11589,7 +11598,7 @@
       "schema_version": "1.0",
       "ok": true,
       "skill_dir": ".",
-      "package_dir": "dist",
+      "package_dir": "tests/tmp_review_studio/dist",
       "expected_capabilities": [
         "file_write",
         "network",
@@ -11629,7 +11638,7 @@
         {
           "target": "openai",
           "status": "pass",
-          "adapter": "dist/targets/openai/adapter.json",
+          "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json",
           "permission_model": "metadata-only",
           "native_enforcement": false,
           "metadata_fallback_explicit": true,
@@ -11726,7 +11735,7 @@
         {
           "target": "claude",
           "status": "pass",
-          "adapter": "dist/targets/claude/adapter.json",
+          "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json",
           "permission_model": "neutral-source-plus-adapter",
           "native_enforcement": false,
           "metadata_fallback_explicit": true,
@@ -11808,7 +11817,7 @@
         {
           "target": "generic",
           "status": "pass",
-          "adapter": "dist/targets/generic/adapter.json",
+          "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json",
           "permission_model": "agent-skills-compatible-metadata",
           "native_enforcement": false,
           "metadata_fallback_explicit": true,
@@ -11890,7 +11899,7 @@
         {
           "target": "vscode",
           "status": "pass",
-          "adapter": "dist/targets/vscode/adapter.json",
+          "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json",
           "permission_model": "vscode-workspace-trust-plus-metadata",
           "native_enforcement": false,
           "metadata_fallback_explicit": true,
@@ -12001,7 +12010,7 @@
         "interactive_script_count": 0,
         "package_hash_scope": "source-contract-without-generated-reports",
         "package_hash_file_count": 213,
-        "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+        "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
       },
       "failures": [],
       "warnings": [],
@@ -14967,7 +14976,7 @@
     "python_compatibility": {
       "schema_version": "1.0",
       "ok": true,
-      "generated_at": "2026-06-16",
+      "generated_at": "2026-06-13",
       "root": ".",
       "summary": {
         "target_python": "3.11",
@@ -16162,7 +16171,7 @@
     "architecture_maintainability": {
       "schema_version": "1.0",
       "ok": true,
-      "generated_at": "2026-06-16",
+      "generated_at": "2026-06-13",
       "skill_dir": ".",
       "summary": {
         "python_file_count": 191,
@@ -16190,6 +16199,13 @@
           "severity": "pass",
           "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
         },
+        {
+          "path": "tests/verify_world_class_evidence_intake.py",
+          "lines": 874,
+          "kind": "test",
+          "severity": "pass",
+          "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
+        },
         {
           "path": "scripts/yao_cli_parser.py",
           "lines": 870,
@@ -16197,16 +16213,9 @@
           "severity": "pass",
           "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
         },
-        {
-          "path": "tests/verify_world_class_evidence_intake.py",
-          "lines": 867,
-          "kind": "test",
-          "severity": "pass",
-          "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
-        },
         {
           "path": "tests/verify_review_studio.py",
-          "lines": 834,
+          "lines": 836,
           "kind": "test",
           "severity": "pass",
           "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
@@ -16276,6 +16285,13 @@
           "severity": "pass",
           "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
         },
+        {
+          "path": "tests/verify_world_class_evidence_intake.py",
+          "lines": 874,
+          "kind": "test",
+          "severity": "pass",
+          "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
+        },
         {
           "path": "scripts/yao_cli_parser.py",
           "lines": 870,
@@ -16283,16 +16299,9 @@
           "severity": "pass",
           "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
         },
-        {
-          "path": "tests/verify_world_class_evidence_intake.py",
-          "lines": 867,
-          "kind": "test",
-          "severity": "pass",
-          "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
-        },
         {
           "path": "tests/verify_review_studio.py",
-          "lines": 834,
+          "lines": 836,
           "kind": "test",
           "severity": "pass",
           "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
@@ -16355,15 +16364,15 @@
         "context_budget_tier": "production",
         "context_budget_limit": 1000,
         "skill_body_tokens": 797,
-        "other_text_tokens": 1045126,
+        "other_text_tokens": 1046015,
         "estimated_initial_load_tokens": 990,
-        "estimated_total_text_tokens": 1045923,
-        "deferred_resource_tokens": 484750,
+        "estimated_total_text_tokens": 1046812,
+        "deferred_resource_tokens": 484786,
         "deferred_resource_warn_threshold": 120000,
         "deferred_resource_dirs": [
           {
             "path": "scripts",
-            "estimated_tokens": 424772,
+            "estimated_tokens": 424808,
             "file_count": 122
           },
           {
@@ -16385,7 +16394,7 @@
         "large_deferred_resource_dirs": [
           {
             "path": "scripts",
-            "estimated_tokens": 424772,
+            "estimated_tokens": 424808,
             "file_count": 122
           }
         ],
@@ -16408,7 +16417,7 @@
               ],
               "missing": [],
               "path": "scripts",
-              "estimated_tokens": 424772,
+              "estimated_tokens": 424808,
               "file_count": 122,
               "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
             }
@@ -17259,7 +17268,7 @@
       },
       "catalog": {
         "workspace_root": ".",
-        "generated_at": "2026-06-16",
+        "generated_at": "2026-06-13",
         "skills": [
           {
             "name": "yao-meta-skill",
@@ -17470,8 +17479,8 @@
               "report": "reports/adoption_drift_report.json",
               "risk_band": "low",
               "event_count": 1,
-              "adoption_sample_count": 0,
-              "adoption_rate": 0,
+              "adoption_sample_count": 1,
+              "adoption_rate": 100.0,
               "candidate_count": 0
             }
           },
@@ -18134,7 +18143,7 @@
           "name": "incident-command-governor",
           "path": "examples/governed-incident-command/generated-skill",
           "reason": "review overdue by cadence monthly",
-          "age_days": 77,
+          "age_days": 74,
           "allowed_days": 31,
           "actionable": false,
           "scope": "example"
@@ -18302,7 +18311,7 @@
     "adoption_drift": {
       "ok": true,
       "schema_version": "2.0",
-      "generated_at": "2026-06-16",
+      "generated_at": "2026-06-16T00:06:24Z",
       "skill_dir": ".",
       "privacy_contract": {
         "storage": "local-first",
@@ -18326,14 +18335,14 @@
       },
       "summary": {
         "event_count": 1,
-        "adoption_sample_count": 0,
-        "activation_count": 0,
-        "accepted_count": 0,
+        "adoption_sample_count": 1,
+        "activation_count": 1,
+        "accepted_count": 1,
         "edited_count": 0,
         "rejected_count": 0,
         "missed_count": 0,
         "failed_count": 0,
-        "adoption_rate": 0,
+        "adoption_rate": 100.0,
         "missed_trigger_count": 0,
         "wrong_trigger_count": 0,
         "bad_output_count": 0,
@@ -18342,7 +18351,7 @@
         "review_overdue_count": 0,
         "risk_band": "low",
         "event_types": {
-          "review_event": 1
+          "skill_activation": 1
         },
         "failure_types": {},
         "source_types": {
@@ -18354,31 +18363,31 @@
         {
           "skill": "yao-meta-skill",
           "events": 1,
-          "adoption_events": 0,
-          "accepted": 0,
+          "adoption_events": 1,
+          "accepted": 1,
           "edited": 0,
           "rejected": 0,
           "missed": 0,
-          "adoption_rate": 0
+          "adoption_rate": 100.0
         }
       ],
       "next_iteration_candidates": [],
       "recent_events": [
         {
           "command": "unknown",
-          "event": "review_event",
+          "event": "skill_activation",
           "skill": "yao-meta-skill",
           "source": "manual",
           "version": "1.1.0",
-          "activation_type": "manual",
-          "outcome": "reviewed",
+          "activation_type": "explicit",
+          "outcome": "accepted",
           "failure_type": "none",
-          "timestamp": "2026-06-13T12:00:00Z"
+          "timestamp": "2026-06-13T10:00:00Z"
         }
       ],
       "failures": [],
       "artifacts": {
-        "events_jsonl": "reports/telemetry_events.jsonl",
+        "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl",
         "json": "reports/adoption_drift_report.json",
         "markdown": "reports/adoption_drift_report.md"
       }
@@ -18399,7 +18408,7 @@
       "local_blueprint_ready": true,
       "public_world_class_ready": false,
       "world_class_pending_count": 4,
-      "release_lock_ready": true,
+      "release_lock_ready": false,
       "evidence_consistency_ok": true,
       "writes_source_files": false,
       "auto_patch_enabled": false,
@@ -18416,7 +18425,7 @@
         "local_blueprint_ready": true,
         "public_world_class_ready": false,
         "world_class_pending_count": 4,
-        "release_lock_ready": true,
+        "release_lock_ready": false,
         "evidence_consistency_ok": true,
         "writes_source_files": false,
         "auto_patch_enabled": false,
@@ -18865,7 +18874,7 @@
         "local_blueprint_ready": true,
         "public_world_class_ready": false,
         "world_class_pending_count": 4,
-        "release_lock_ready": true,
+        "release_lock_ready": false,
         "evidence_consistency_ok": true
       },
       "actions": [
@@ -18914,7 +18923,7 @@
       "top_score": 88,
       "skill_count": 12,
       "actionable_portfolio_issue_count": 0,
-      "release_lock_ready": true,
+      "release_lock_ready": false,
       "evidence_consistency_ok": true,
       "public_world_class_ready": false,
       "world_class_pending_count": 4,
@@ -18934,7 +18943,7 @@
         "top_score": 88,
         "skill_count": 12,
         "actionable_portfolio_issue_count": 0,
-        "release_lock_ready": true,
+        "release_lock_ready": false,
         "evidence_consistency_ok": true,
         "public_world_class_ready": false,
         "world_class_pending_count": 4,
@@ -19186,7 +19195,7 @@
         "no_route_opportunity_count": 0
       },
       "release_state": {
-        "release_lock_ready": true,
+        "release_lock_ready": false,
         "evidence_consistency_ok": true,
         "public_world_class_ready": false,
         "world_class_pending_count": 4
@@ -19221,7 +19230,7 @@
       "schema_version": "1.0",
       "ok": true,
       "skill_dir": ".",
-      "generated_at": "2026-06-16",
+      "generated_at": "2026-06-13",
       "summary": {
         "waiver_count": 0,
         "active_count": 0,
@@ -19271,7 +19280,7 @@
             "Reviewer links output_review_adjudication or output_execution evidence."
           ],
           "suggested_evidence": "reports/output_review_adjudication.md",
-          "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md",
+          "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md",
           "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence."
         },
         {
@@ -19301,7 +19310,7 @@
       "schema_version": "1.0",
       "ok": true,
       "skill_dir": ".",
-      "source": "reports/review_annotations_input.json",
+      "source": "tests/tmp_review_studio/empty_review_annotations_input.json",
       "summary": {
         "annotation_count": 0,
         "open_count": 0,
@@ -19736,8 +19745,8 @@
       "missing_submission_count": 4,
       "invalid_submission_count": 0,
       "source_check_count": 13,
-      "source_pass_count": 6,
-      "source_blocked_count": 7,
+      "source_pass_count": 7,
+      "source_blocked_count": 6,
       "submitted_but_pending_count": 0,
       "source_accepted_without_valid_submission_count": 0,
       "overclaim_guard_active": true,
@@ -19752,8 +19761,8 @@
         "missing_submission_count": 4,
         "invalid_submission_count": 0,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "submitted_but_pending_count": 0,
         "source_accepted_without_valid_submission_count": 0,
         "overclaim_guard_active": true,
@@ -19797,7 +19806,9 @@
           "current": "model-executed 0; token-observed 0",
           "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
           "runbook": [
-            "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+            "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+            "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+            "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
             "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
             "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
             "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -20117,7 +20128,7 @@
           "status": "pending",
           "source_status": "external_required",
           "source_accepted": false,
-          "current": "external source events 0; adoption samples 0",
+          "current": "external source events 0; adoption samples 1",
           "objective": "Import production metadata-only events from a real external client into the local drift loop.",
           "runbook": [
             "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -20154,7 +20165,7 @@
           ],
           "observed_state": {
             "external_source_events": 0,
-            "adoption_sample_count": 0,
+            "adoption_sample_count": 1,
             "raw_content_allowed": false,
             "risk_band": "low",
             "accepted": false
@@ -20175,8 +20186,8 @@
               "label": "Adoption sample",
               "field": "adoption_sample_count",
               "expected": ">0",
-              "actual": 0,
-              "status": "blocked",
+              "actual": 1,
+              "status": "pass",
               "source_accepted": false,
               "next_action": "Telemetry must include adoption outcome evidence."
             },
@@ -20192,8 +20203,8 @@
             }
           ],
           "source_check_count": 3,
-          "source_pass_count": 1,
-          "source_blocked_count": 2,
+          "source_pass_count": 2,
+          "source_blocked_count": 1,
           "submission_state": {
             "status": "missing",
             "path": "evidence/world_class/submissions/native-client-telemetry.json",
@@ -20343,7 +20354,9 @@
               "observed token metadata"
             ],
             "runbook": [
-              "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+              "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+              "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+              "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
               "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
               "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
               "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -20540,7 +20553,7 @@
           "source_accepted": false,
           "observed_state": {
             "external_source_events": 0,
-            "adoption_sample_count": 0,
+            "adoption_sample_count": 1,
             "raw_content_allowed": false,
             "risk_band": "low",
             "accepted": false
@@ -20624,8 +20637,8 @@
         "collection_ready_count": 1,
         "collection_blocked_count": 3,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "pending_count": 4,
         "ready_to_claim_world_class": false,
         "credential_value_exposed": false,
@@ -20783,7 +20796,9 @@
             "artifact_prefill_counts_as_evidence": false
           },
           "runbook": [
-            "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+            "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+            "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+            "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
             "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
             "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
             "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -21143,8 +21158,8 @@
               "label": "Adoption sample",
               "field": "adoption_sample_count",
               "expected": ">0",
-              "actual": 0,
-              "status": "blocked",
+              "actual": 1,
+              "status": "pass",
               "source_accepted": false,
               "next_action": "Telemetry must include adoption outcome evidence."
             },
@@ -21499,8 +21514,8 @@
           "label": "Adoption sample",
           "field": "adoption_sample_count",
           "expected": ">0",
-          "actual": 0,
-          "status": "blocked",
+          "actual": 1,
+          "status": "pass",
           "source_accepted": false,
           "next_action": "Telemetry must include adoption outcome evidence."
         },
@@ -21583,8 +21598,8 @@
       "unmatched_submission_count": 0,
       "invalid_submission_count": 0,
       "source_check_count": 13,
-      "source_pass_count": 6,
-      "source_blocked_count": 7,
+      "source_pass_count": 7,
+      "source_blocked_count": 6,
       "review_counts_submission_as_completion": false,
       "summary": {
         "review_item_count": 4,
@@ -21596,8 +21611,8 @@
         "unmatched_submission_count": 0,
         "invalid_submission_count": 0,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "ready_to_claim_world_class": false,
         "review_counts_submission_as_completion": false,
         "decision": "awaiting-submissions"
@@ -21871,7 +21886,7 @@
           "intake_errors": [],
           "observed_state": {
             "external_source_events": 0,
-            "adoption_sample_count": 0,
+            "adoption_sample_count": 1,
             "raw_content_allowed": false,
             "risk_band": "low",
             "accepted": false
@@ -21892,8 +21907,8 @@
               "label": "Adoption sample",
               "field": "adoption_sample_count",
               "expected": ">0",
-              "actual": 0,
-              "status": "blocked",
+              "actual": 1,
+              "status": "pass",
               "source_accepted": false,
               "next_action": "Telemetry must include adoption outcome evidence."
             },
@@ -21909,8 +21924,8 @@
             }
           ],
           "source_check_count": 3,
-          "source_pass_count": 1,
-          "source_blocked_count": 2,
+          "source_pass_count": 2,
+          "source_blocked_count": 1,
           "success_checks": [
             "reports/adoption_drift_report.json summary.source_types.external > 0",
             "reports/adoption_drift_report.json summary.adoption_sample_count > 0",
@@ -21947,8 +21962,8 @@
         "valid_packet_source_incomplete_count": 0,
         "invalid_submission_count": 0,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "ready_to_claim_world_class": false,
         "runbook_counts_as_completion": false,
         "decision": "collect-evidence"
@@ -21970,7 +21985,9 @@
           "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
           "current": "model-executed 0; token-observed 0",
           "execution_runbook": [
-            "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+            "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+            "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+            "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
             "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
             "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
             "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -22332,7 +22349,7 @@
           "review_state": "awaiting-submission",
           "source_accepted": false,
           "objective": "Import production metadata-only events from a real external client into the local drift loop.",
-          "current": "external source events 0; adoption samples 0",
+          "current": "external source events 0; adoption samples 1",
           "execution_runbook": [
             "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
             "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
@@ -22380,7 +22397,7 @@
           ],
           "observed_state": {
             "external_source_events": 0,
-            "adoption_sample_count": 0,
+            "adoption_sample_count": 1,
             "raw_content_allowed": false,
             "risk_band": "low",
             "accepted": false
@@ -22401,8 +22418,8 @@
               "label": "Adoption sample",
               "field": "adoption_sample_count",
               "expected": ">0",
-              "actual": 0,
-              "status": "blocked",
+              "actual": 1,
+              "status": "pass",
               "source_accepted": false,
               "next_action": "Telemetry must include adoption outcome evidence."
             },
@@ -22417,10 +22434,9 @@
               "next_action": "Telemetry must stay metadata-only."
             }
           ],
-          "blocked_source_check_count": 2,
+          "blocked_source_check_count": 1,
           "next_source_actions": [
-            "Import at least one metadata-only event from a real client.",
-            "Telemetry must include adoption outcome evidence."
+            "Import at least one metadata-only event from a real client."
           ],
           "submission_state": {
             "status": "missing",
@@ -23248,7 +23264,7 @@
         "trust_level": "local",
         "license": "MIT",
         "checksums": {
-          "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+          "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
           "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81"
         },
         "compatibility": {
@@ -23285,11 +23301,11 @@
           "install_simulated": true,
           "install_simulation": "reports/install_simulation.json"
         },
-        "generated_at": "2026-06-16"
+        "generated_at": "2026-06-13"
       },
       "index": {
         "schema_version": "2.0",
-        "generated_at": "2026-06-16",
+        "generated_at": "2026-06-13",
         "package_count": 1,
         "packages": [
           {
@@ -23305,7 +23321,7 @@
               "vscode"
             ],
             "package_metadata": "registry/packages/yao-meta-skill.json",
-            "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+            "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
           }
         ]
       },
@@ -23987,11 +24003,11 @@
     "install_simulation": {
       "ok": true,
       "schema_version": "2.0",
-      "generated_at": "2026-06-16",
+      "generated_at": "2026-06-13",
       "skill_dir": ".",
-      "package_dir": "dist",
-      "install_root": "dist/install-simulation/simulate-yao-meta-skill",
-      "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
+      "package_dir": "tests/tmp_review_studio/dist",
+      "install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill",
+      "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
       "summary": {
         "archive_present": true,
         "archive_entry_count": 647,
@@ -24012,7 +24028,7 @@
         {
           "id": "archive-present",
           "status": "pass",
-          "detail": "Package archive exists: dist/yao-meta-skill.zip"
+          "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip"
         },
         {
           "id": "archive-safe-paths",
@@ -24258,16 +24274,16 @@
       "failures": [],
       "warnings": [],
       "artifacts": {
-        "archive": "dist/yao-meta-skill.zip",
-        "package_manifest": "dist/manifest.json",
-        "json": "reports/install_simulation.json",
-        "markdown": "reports/install_simulation.md"
+        "archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip",
+        "package_manifest": "tests/tmp_review_studio/dist/manifest.json",
+        "json": "tests/tmp_review_studio/install_simulation.json",
+        "markdown": "tests/tmp_review_studio/install_simulation.md"
       }
     },
     "upgrade_check": {
       "ok": true,
       "schema_version": "2.0",
-      "generated_at": "2026-06-16",
+      "generated_at": "2026-06-13",
       "previous": {
         "name": "yao-meta-skill",
         "version": "1.0.0",
@@ -24341,7 +24357,7 @@
           {
             "field": "package_sha256",
             "from": "0000000000000000000000000000000000000000000000000000000000000000",
-            "to": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+            "to": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
           }
         ]
       },
@@ -24356,8 +24372,8 @@
       "artifacts": {
         "previous_package": "registry/examples/yao-meta-skill-1.0.0.json",
         "current_package": "reports/registry_audit.json",
-        "json": "reports/upgrade_check.json",
-        "markdown": "reports/upgrade_check.md"
+        "json": "tests/tmp_review_studio/upgrade_check.json",
+        "markdown": "tests/tmp_review_studio/upgrade_check.md"
       }
     },
     "manifest": {
diff --git a/reports/review-viewer.json b/reports/review-viewer.json
index 8dc11dbe..9ace2823 100644
--- a/reports/review-viewer.json
+++ b/reports/review-viewer.json
@@ -412,7 +412,7 @@
       "external_pending_count": 3,
       "human_pending_count": 1,
       "source_check_count": 13,
-      "source_pass_count": 6,
+      "source_pass_count": 7,
       "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
       "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
       "entries": [
@@ -471,8 +471,7 @@
           "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
           "summary_en": "Real external-client metadata-only events have not been imported yet.",
           "blocked_checks": [
-            "External events",
-            "Adoption sample"
+            "External events"
           ]
         }
       ]
@@ -997,12 +996,12 @@
       "ok": true,
       "summary": {
         "reproducibility_ready": true,
-        "release_lock_ready": true,
+        "release_lock_ready": false,
         "methodology_complete": true,
         "required_artifact_count": 25,
         "missing_artifact_count": 0,
-        "evidence_bundle_sha256": "7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1",
-        "source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+        "evidence_bundle_sha256": "95c6335a413934f197ca1595747c312701edb6028e8fc2ffed6cc4755c0a8d1f",
+        "source_contract_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
         "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
         "output_case_count": 5,
         "failure_disclosure_count": 3,
@@ -1018,14 +1017,14 @@
         "world_class_task_count": 4,
         "world_class_ledger_pending_count": 4,
         "world_class_source_check_count": 13,
-        "world_class_source_pass_count": 6,
-        "world_class_source_blocked_count": 7,
+        "world_class_source_pass_count": 7,
+        "world_class_source_blocked_count": 6,
         "public_claim_ready": false,
-        "public_claim_blocker_count": 4,
-        "working_tree_dirty": false,
-        "changed_file_count": 0
+        "public_claim_blocker_count": 5,
+        "working_tree_dirty": true,
+        "changed_file_count": 64
       },
-      "commit": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
+      "commit": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
       "missing_artifacts": [],
       "limitations": [
         "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -1130,7 +1129,7 @@
       "interactive_script_count": 0,
       "package_hash_scope": "source-contract-without-generated-reports",
       "package_hash_file_count": 213,
-      "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+      "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
     },
     "skill_atlas": {
       "skill_count": 12,
@@ -1168,7 +1167,7 @@
         "trust_level": "local",
         "license": "MIT",
         "checksums": {
-          "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+          "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
           "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81"
         },
         "compatibility": {
@@ -1205,7 +1204,7 @@
           "install_simulated": true,
           "install_simulation": "reports/install_simulation.json"
         },
-        "generated_at": "2026-06-16"
+        "generated_at": "2026-06-13"
       },
       "failures": [],
       "warnings": []
@@ -1300,7 +1299,7 @@
           {
             "field": "package_sha256",
             "from": "0000000000000000000000000000000000000000000000000000000000000000",
-            "to": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+            "to": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
           }
         ]
       },
@@ -1317,14 +1316,14 @@
       "ok": true,
       "summary": {
         "event_count": 1,
-        "adoption_sample_count": 0,
-        "activation_count": 0,
-        "accepted_count": 0,
+        "adoption_sample_count": 1,
+        "activation_count": 1,
+        "accepted_count": 1,
         "edited_count": 0,
         "rejected_count": 0,
         "missed_count": 0,
         "failed_count": 0,
-        "adoption_rate": 0,
+        "adoption_rate": 100.0,
         "missed_trigger_count": 0,
         "wrong_trigger_count": 0,
         "bad_output_count": 0,
@@ -1333,7 +1332,7 @@
         "review_overdue_count": 0,
         "risk_band": "low",
         "event_types": {
-          "review_event": 1
+          "skill_activation": 1
         },
         "failure_types": {},
         "source_types": {
@@ -1440,7 +1439,9 @@
           "current": "model-executed 0; token-observed 0",
           "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
           "runbook": [
-            "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+            "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+            "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+            "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
             "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
             "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
             "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -1558,7 +1559,7 @@
           "status": "external_required",
           "category": "external",
           "owner": "Browser/Chrome/IDE/provider client integrator",
-          "current": "external source events 0; adoption samples 0",
+          "current": "external source events 0; adoption samples 1",
           "objective": "Import production metadata-only events from a real external client into the local drift loop.",
           "runbook": [
             "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1610,8 +1611,8 @@
         "missing_submission_count": 4,
         "invalid_submission_count": 0,
         "source_check_count": 13,
-        "source_pass_count": 6,
-        "source_blocked_count": 7,
+        "source_pass_count": 7,
+        "source_blocked_count": 6,
         "submitted_but_pending_count": 0,
         "source_accepted_without_valid_submission_count": 0,
         "overclaim_guard_active": true,
@@ -1630,7 +1631,9 @@
           "current": "model-executed 0; token-observed 0",
           "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
           "runbook": [
-            "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+            "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+            "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+            "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
             "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
             "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
             "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -1950,7 +1953,7 @@
           "status": "pending",
           "source_status": "external_required",
           "source_accepted": false,
-          "current": "external source events 0; adoption samples 0",
+          "current": "external source events 0; adoption samples 1",
           "objective": "Import production metadata-only events from a real external client into the local drift loop.",
           "runbook": [
             "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1987,7 +1990,7 @@
           ],
           "observed_state": {
             "external_source_events": 0,
-            "adoption_sample_count": 0,
+            "adoption_sample_count": 1,
             "raw_content_allowed": false,
             "risk_band": "low",
             "accepted": false
@@ -2008,8 +2011,8 @@
               "label": "Adoption sample",
               "field": "adoption_sample_count",
               "expected": ">0",
-              "actual": 0,
-              "status": "blocked",
+              "actual": 1,
+              "status": "pass",
               "source_accepted": false,
               "next_action": "Telemetry must include adoption outcome evidence."
             },
@@ -2025,8 +2028,8 @@
             }
           ],
           "source_check_count": 3,
-          "source_pass_count": 1,
-          "source_blocked_count": 2,
+          "source_pass_count": 2,
+          "source_blocked_count": 1,
           "submission_state": {
             "status": "missing",
             "path": "evidence/world_class/submissions/native-client-telemetry.json",
diff --git a/reports/review_annotations.json b/reports/review_annotations.json
index 76fadc1f..66f2b1d9 100644
--- a/reports/review_annotations.json
+++ b/reports/review_annotations.json
@@ -2,7 +2,7 @@
   "schema_version": "1.0",
   "ok": true,
   "skill_dir": ".",
-  "source": "reports/review_annotations_input.json",
+  "source": "tests/tmp_review_studio/empty_review_annotations_input.json",
   "summary": {
     "annotation_count": 0,
     "open_count": 0,
diff --git a/reports/review_waivers.json b/reports/review_waivers.json
index aa2558e7..07eeccbc 100644
--- a/reports/review_waivers.json
+++ b/reports/review_waivers.json
@@ -2,7 +2,7 @@
   "schema_version": "1.0",
   "ok": true,
   "skill_dir": ".",
-  "generated_at": "2026-06-16",
+  "generated_at": "2026-06-13",
   "summary": {
     "waiver_count": 0,
     "active_count": 0,
@@ -52,7 +52,7 @@
         "Reviewer links output_review_adjudication or output_execution evidence."
       ],
       "suggested_evidence": "reports/output_review_adjudication.md",
-      "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md",
+      "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md",
       "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence."
     },
     {
diff --git a/reports/review_waivers.md b/reports/review_waivers.md
index 6c8d594c..dbc942d1 100644
--- a/reports/review_waivers.md
+++ b/reports/review_waivers.md
@@ -35,7 +35,7 @@
 - waiver allowed: `true`
 - risk: review pending 5; model-executed 0; output failures 0
 - evidence: `reports/output_review_adjudication.md`
-- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md`
+- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md`
 - world-class boundary: Does not count as provider, human, or public world-class completion evidence.
 
 #### Required Review
diff --git a/reports/runtime_permission_probes.json b/reports/runtime_permission_probes.json
index 9c2ffd6e..59c9a1a4 100644
--- a/reports/runtime_permission_probes.json
+++ b/reports/runtime_permission_probes.json
@@ -2,7 +2,7 @@
   "schema_version": "1.0",
   "ok": true,
   "skill_dir": ".",
-  "package_dir": "dist",
+  "package_dir": "tests/tmp_review_studio/dist",
   "expected_capabilities": [
     "file_write",
     "network",
@@ -42,7 +42,7 @@
     {
       "target": "openai",
       "status": "pass",
-      "adapter": "dist/targets/openai/adapter.json",
+      "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json",
       "permission_model": "metadata-only",
       "native_enforcement": false,
       "metadata_fallback_explicit": true,
@@ -139,7 +139,7 @@
     {
       "target": "claude",
       "status": "pass",
-      "adapter": "dist/targets/claude/adapter.json",
+      "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json",
       "permission_model": "neutral-source-plus-adapter",
       "native_enforcement": false,
       "metadata_fallback_explicit": true,
@@ -221,7 +221,7 @@
     {
       "target": "generic",
       "status": "pass",
-      "adapter": "dist/targets/generic/adapter.json",
+      "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json",
       "permission_model": "agent-skills-compatible-metadata",
       "native_enforcement": false,
       "metadata_fallback_explicit": true,
@@ -303,7 +303,7 @@
     {
       "target": "vscode",
       "status": "pass",
-      "adapter": "dist/targets/vscode/adapter.json",
+      "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json",
       "permission_model": "vscode-workspace-trust-plus-metadata",
       "native_enforcement": false,
       "metadata_fallback_explicit": true,
diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json
index c05e9830..ce7f483e 100644
--- a/reports/security_trust_report.json
+++ b/reports/security_trust_report.json
@@ -23,7 +23,7 @@
     "interactive_script_count": 0,
     "package_hash_scope": "source-contract-without-generated-reports",
     "package_hash_file_count": 213,
-    "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+    "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
   },
   "failures": [],
   "warnings": [],
diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md
index 0e3c4682..be4ab92f 100644
--- a/reports/security_trust_report.md
+++ b/reports/security_trust_report.md
@@ -16,7 +16,7 @@
 - Interactive scripts: `0`
 - Package hash scope: `source-contract-without-generated-reports`
 - Package hash files: `213`
-- Package SHA256: `db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336`
+- Package SHA256: `a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f`
 
 ## Failures
 
diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html
index d04bb40e..efd1f1f6 100644
--- a/reports/skill-interpretation.html
+++ b/reports/skill-interpretation.html
@@ -919,7 +919,7 @@
             </table>
           </div>
         </div>
-        <article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>6 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li><li><span data-lang="zh-CN">采用样本</span><span data-lang="en">Adoption sample</span></li></ul></article></div></article>
+        <article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>7 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li></ul></article></div></article>
       </div>
     </section>
 
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json
index 564a097a..4f650692 100644
--- a/reports/skill-interpretation.json
+++ b/reports/skill-interpretation.json
@@ -412,7 +412,7 @@
     "external_pending_count": 3,
     "human_pending_count": 1,
     "source_check_count": 13,
-    "source_pass_count": 6,
+    "source_pass_count": 7,
     "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
     "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
     "entries": [
@@ -471,8 +471,7 @@
         "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
         "summary_en": "Real external-client metadata-only events have not been imported yet.",
         "blocked_checks": [
-          "External events",
-          "Adoption sample"
+          "External events"
         ]
       }
     ]
@@ -1001,12 +1000,12 @@
     "ok": true,
     "summary": {
       "reproducibility_ready": true,
-      "release_lock_ready": true,
+      "release_lock_ready": false,
       "methodology_complete": true,
       "required_artifact_count": 25,
       "missing_artifact_count": 0,
-      "evidence_bundle_sha256": "7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1",
-      "source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+      "evidence_bundle_sha256": "95c6335a413934f197ca1595747c312701edb6028e8fc2ffed6cc4755c0a8d1f",
+      "source_contract_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
       "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
       "output_case_count": 5,
       "failure_disclosure_count": 3,
@@ -1022,14 +1021,14 @@
       "world_class_task_count": 4,
       "world_class_ledger_pending_count": 4,
       "world_class_source_check_count": 13,
-      "world_class_source_pass_count": 6,
-      "world_class_source_blocked_count": 7,
+      "world_class_source_pass_count": 7,
+      "world_class_source_blocked_count": 6,
       "public_claim_ready": false,
-      "public_claim_blocker_count": 4,
-      "working_tree_dirty": false,
-      "changed_file_count": 0
+      "public_claim_blocker_count": 5,
+      "working_tree_dirty": true,
+      "changed_file_count": 64
     },
-    "commit": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
+    "commit": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
     "missing_artifacts": [],
     "limitations": [
       "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -1134,7 +1133,7 @@
     "interactive_script_count": 0,
     "package_hash_scope": "source-contract-without-generated-reports",
     "package_hash_file_count": 213,
-    "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+    "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
   },
   "skill_atlas": {
     "skill_count": 12,
@@ -1172,7 +1171,7 @@
       "trust_level": "local",
       "license": "MIT",
       "checksums": {
-        "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+        "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
         "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81"
       },
       "compatibility": {
@@ -1209,7 +1208,7 @@
         "install_simulated": true,
         "install_simulation": "reports/install_simulation.json"
       },
-      "generated_at": "2026-06-16"
+      "generated_at": "2026-06-13"
     },
     "failures": [],
     "warnings": []
@@ -1304,7 +1303,7 @@
         {
           "field": "package_sha256",
           "from": "0000000000000000000000000000000000000000000000000000000000000000",
-          "to": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+          "to": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
         }
       ]
     },
@@ -1321,14 +1320,14 @@
     "ok": true,
     "summary": {
       "event_count": 1,
-      "adoption_sample_count": 0,
-      "activation_count": 0,
-      "accepted_count": 0,
+      "adoption_sample_count": 1,
+      "activation_count": 1,
+      "accepted_count": 1,
       "edited_count": 0,
       "rejected_count": 0,
       "missed_count": 0,
       "failed_count": 0,
-      "adoption_rate": 0,
+      "adoption_rate": 100.0,
       "missed_trigger_count": 0,
       "wrong_trigger_count": 0,
       "bad_output_count": 0,
@@ -1337,7 +1336,7 @@
       "review_overdue_count": 0,
       "risk_band": "low",
       "event_types": {
-        "review_event": 1
+        "skill_activation": 1
       },
       "failure_types": {},
       "source_types": {
@@ -1444,7 +1443,9 @@
         "current": "model-executed 0; token-observed 0",
         "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
         "runbook": [
-          "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+          "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+          "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+          "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
           "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
           "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
           "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -1562,7 +1563,7 @@
         "status": "external_required",
         "category": "external",
         "owner": "Browser/Chrome/IDE/provider client integrator",
-        "current": "external source events 0; adoption samples 0",
+        "current": "external source events 0; adoption samples 1",
         "objective": "Import production metadata-only events from a real external client into the local drift loop.",
         "runbook": [
           "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1614,8 +1615,8 @@
       "missing_submission_count": 4,
       "invalid_submission_count": 0,
       "source_check_count": 13,
-      "source_pass_count": 6,
-      "source_blocked_count": 7,
+      "source_pass_count": 7,
+      "source_blocked_count": 6,
       "submitted_but_pending_count": 0,
       "source_accepted_without_valid_submission_count": 0,
       "overclaim_guard_active": true,
@@ -1634,7 +1635,9 @@
         "current": "model-executed 0; token-observed 0",
         "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
         "runbook": [
-          "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+          "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+          "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+          "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
           "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
           "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
           "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -1954,7 +1957,7 @@
         "status": "pending",
         "source_status": "external_required",
         "source_accepted": false,
-        "current": "external source events 0; adoption samples 0",
+        "current": "external source events 0; adoption samples 1",
         "objective": "Import production metadata-only events from a real external client into the local drift loop.",
         "runbook": [
           "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1991,7 +1994,7 @@
         ],
         "observed_state": {
           "external_source_events": 0,
-          "adoption_sample_count": 0,
+          "adoption_sample_count": 1,
           "raw_content_allowed": false,
           "risk_band": "low",
           "accepted": false
@@ -2012,8 +2015,8 @@
             "label": "Adoption sample",
             "field": "adoption_sample_count",
             "expected": ">0",
-            "actual": 0,
-            "status": "blocked",
+            "actual": 1,
+            "status": "pass",
             "source_accepted": false,
             "next_action": "Telemetry must include adoption outcome evidence."
           },
@@ -2029,8 +2032,8 @@
           }
         ],
         "source_check_count": 3,
-        "source_pass_count": 1,
-        "source_blocked_count": 2,
+        "source_pass_count": 2,
+        "source_blocked_count": 1,
         "submission_state": {
           "status": "missing",
           "path": "evidence/world_class/submissions/native-client-telemetry.json",
diff --git a/reports/skill-overview.html b/reports/skill-overview.html
index f999d092..d41e78e8 100644
--- a/reports/skill-overview.html
+++ b/reports/skill-overview.html
@@ -919,7 +919,7 @@
             </table>
           </div>
         </div>
-        <article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>6 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li><li><span data-lang="zh-CN">采用样本</span><span data-lang="en">Adoption sample</span></li></ul></article></div></article>
+        <article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>7 / 13</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li></ul></article></div></article>
       </div>
     </section>
 
diff --git a/reports/skill-overview.json b/reports/skill-overview.json
index ce04180a..2dcc4e05 100644
--- a/reports/skill-overview.json
+++ b/reports/skill-overview.json
@@ -411,7 +411,7 @@
     "external_pending_count": 3,
     "human_pending_count": 1,
     "source_check_count": 13,
-    "source_pass_count": 6,
+    "source_pass_count": 7,
     "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
     "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
     "entries": [
@@ -470,8 +470,7 @@
         "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
         "summary_en": "Real external-client metadata-only events have not been imported yet.",
         "blocked_checks": [
-          "External events",
-          "Adoption sample"
+          "External events"
         ]
       }
     ]
@@ -996,12 +995,12 @@
     "ok": true,
     "summary": {
       "reproducibility_ready": true,
-      "release_lock_ready": true,
+      "release_lock_ready": false,
       "methodology_complete": true,
       "required_artifact_count": 25,
       "missing_artifact_count": 0,
-      "evidence_bundle_sha256": "7ef645993fc40e21528099046d09056d87af293c171850a84acbcab4d7f8f0a1",
-      "source_contract_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+      "evidence_bundle_sha256": "95c6335a413934f197ca1595747c312701edb6028e8fc2ffed6cc4755c0a8d1f",
+      "source_contract_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
       "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81",
       "output_case_count": 5,
       "failure_disclosure_count": 3,
@@ -1017,14 +1016,14 @@
       "world_class_task_count": 4,
       "world_class_ledger_pending_count": 4,
       "world_class_source_check_count": 13,
-      "world_class_source_pass_count": 6,
-      "world_class_source_blocked_count": 7,
+      "world_class_source_pass_count": 7,
+      "world_class_source_blocked_count": 6,
       "public_claim_ready": false,
-      "public_claim_blocker_count": 4,
-      "working_tree_dirty": false,
-      "changed_file_count": 0
+      "public_claim_blocker_count": 5,
+      "working_tree_dirty": true,
+      "changed_file_count": 64
     },
-    "commit": "4b2767900bbbbb962d2b11a92610951c3a0a0f0e",
+    "commit": "54851019f53f3ee3f508dedfc0daaf192d6bc6ad",
     "missing_artifacts": [],
     "limitations": [
       "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -1129,7 +1128,7 @@
     "interactive_script_count": 0,
     "package_hash_scope": "source-contract-without-generated-reports",
     "package_hash_file_count": 213,
-    "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+    "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
   },
   "skill_atlas": {
     "skill_count": 12,
@@ -1167,7 +1166,7 @@
       "trust_level": "local",
       "license": "MIT",
       "checksums": {
-        "package_sha256": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336",
+        "package_sha256": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f",
         "archive_sha256": "996e36863203c30d3c518e0d635be054177dc5b774c9cd3d8311f77d69013a81"
       },
       "compatibility": {
@@ -1204,7 +1203,7 @@
         "install_simulated": true,
         "install_simulation": "reports/install_simulation.json"
       },
-      "generated_at": "2026-06-16"
+      "generated_at": "2026-06-13"
     },
     "failures": [],
     "warnings": []
@@ -1299,7 +1298,7 @@
         {
           "field": "package_sha256",
           "from": "0000000000000000000000000000000000000000000000000000000000000000",
-          "to": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+          "to": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
         }
       ]
     },
@@ -1316,14 +1315,14 @@
     "ok": true,
     "summary": {
       "event_count": 1,
-      "adoption_sample_count": 0,
-      "activation_count": 0,
-      "accepted_count": 0,
+      "adoption_sample_count": 1,
+      "activation_count": 1,
+      "accepted_count": 1,
       "edited_count": 0,
       "rejected_count": 0,
       "missed_count": 0,
       "failed_count": 0,
-      "adoption_rate": 0,
+      "adoption_rate": 100.0,
       "missed_trigger_count": 0,
       "wrong_trigger_count": 0,
       "bad_output_count": 0,
@@ -1332,7 +1331,7 @@
       "review_overdue_count": 0,
       "risk_band": "low",
       "event_types": {
-        "review_event": 1
+        "skill_activation": 1
       },
       "failure_types": {},
       "source_types": {
@@ -1439,7 +1438,9 @@
         "current": "model-executed 0; token-observed 0",
         "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
         "runbook": [
-          "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+          "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+          "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+          "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
           "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
           "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
           "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -1557,7 +1558,7 @@
         "status": "external_required",
         "category": "external",
         "owner": "Browser/Chrome/IDE/provider client integrator",
-        "current": "external source events 0; adoption samples 0",
+        "current": "external source events 0; adoption samples 1",
         "objective": "Import production metadata-only events from a real external client into the local drift loop.",
         "runbook": [
           "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1609,8 +1610,8 @@
       "missing_submission_count": 4,
       "invalid_submission_count": 0,
       "source_check_count": 13,
-      "source_pass_count": 6,
-      "source_blocked_count": 7,
+      "source_pass_count": 7,
+      "source_blocked_count": 6,
       "submitted_but_pending_count": 0,
       "source_accepted_without_valid_submission_count": 0,
       "overclaim_guard_active": true,
@@ -1629,7 +1630,9 @@
         "current": "model-executed 0; token-observed 0",
         "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
         "runbook": [
-          "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+          "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+          "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+          "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
           "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
           "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
           "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -1949,7 +1952,7 @@
         "status": "pending",
         "source_status": "external_required",
         "source_accepted": false,
-        "current": "external source events 0; adoption samples 0",
+        "current": "external source events 0; adoption samples 1",
         "objective": "Import production metadata-only events from a real external client into the local drift loop.",
         "runbook": [
           "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -1986,7 +1989,7 @@
         ],
         "observed_state": {
           "external_source_events": 0,
-          "adoption_sample_count": 0,
+          "adoption_sample_count": 1,
           "raw_content_allowed": false,
           "risk_band": "low",
           "accepted": false
@@ -2007,8 +2010,8 @@
             "label": "Adoption sample",
             "field": "adoption_sample_count",
             "expected": ">0",
-            "actual": 0,
-            "status": "blocked",
+            "actual": 1,
+            "status": "pass",
             "source_accepted": false,
             "next_action": "Telemetry must include adoption outcome evidence."
           },
@@ -2024,8 +2027,8 @@
           }
         ],
         "source_check_count": 3,
-        "source_pass_count": 1,
-        "source_blocked_count": 2,
+        "source_pass_count": 2,
+        "source_blocked_count": 1,
         "submission_state": {
           "status": "missing",
           "path": "evidence/world_class/submissions/native-client-telemetry.json",
diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json
index 85769028..ae6eddde 100644
--- a/reports/skill_atlas.json
+++ b/reports/skill_atlas.json
@@ -44,7 +44,7 @@
   },
   "catalog": {
     "workspace_root": ".",
-    "generated_at": "2026-06-16",
+    "generated_at": "2026-06-13",
     "skills": [
       {
         "name": "yao-meta-skill",
@@ -255,8 +255,8 @@
           "report": "reports/adoption_drift_report.json",
           "risk_band": "low",
           "event_count": 1,
-          "adoption_sample_count": 0,
-          "adoption_rate": 0,
+          "adoption_sample_count": 1,
+          "adoption_rate": 100.0,
           "candidate_count": 0
         }
       },
@@ -919,7 +919,7 @@
       "name": "incident-command-governor",
       "path": "examples/governed-incident-command/generated-skill",
       "reason": "review overdue by cadence monthly",
-      "age_days": 77,
+      "age_days": 74,
       "allowed_days": 31,
       "actionable": false,
       "scope": "example"
diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json
index 882c3f8d..8559a597 100644
--- a/reports/skill_os2_audit.json
+++ b/reports/skill_os2_audit.json
@@ -351,7 +351,7 @@
       "key": "native-client-telemetry",
       "label": "Native Client Telemetry",
       "status": "external_required",
-      "current": "external source events 0; adoption samples 0",
+      "current": "external source events 0; adoption samples 1",
       "target": "A real Browser/Chrome/provider client sends production metadata events",
       "evidence": [
         {
@@ -433,7 +433,7 @@
       "key": "native-client-telemetry",
       "label": "Native Client Telemetry",
       "status": "external_required",
-      "current": "external source events 0; adoption samples 0",
+      "current": "external source events 0; adoption samples 1",
       "target": "A real Browser/Chrome/provider client sends production metadata events",
       "evidence": [
         {
diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md
index 4bd96bde..1bf27b9b 100644
--- a/reports/skill_os2_audit.md
+++ b/reports/skill_os2_audit.md
@@ -30,7 +30,7 @@ Generated at: `2026-06-16`
 | Registry Distribution | pass | zip entries 647; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
 | Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. |
 | Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. |
-| Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
+| Native Client Telemetry | external-required | external source events 0; adoption samples 1 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
 
 ## Open Highest-Leverage Gaps
 
diff --git a/reports/skillops/daily/2026-06-16.json b/reports/skillops/daily/2026-06-16.json
index a35cbc88..386b0613 100644
--- a/reports/skillops/daily/2026-06-16.json
+++ b/reports/skillops/daily/2026-06-16.json
@@ -14,7 +14,7 @@
   "local_blueprint_ready": true,
   "public_world_class_ready": false,
   "world_class_pending_count": 4,
-  "release_lock_ready": true,
+  "release_lock_ready": false,
   "evidence_consistency_ok": true,
   "writes_source_files": false,
   "auto_patch_enabled": false,
@@ -31,7 +31,7 @@
     "local_blueprint_ready": true,
     "public_world_class_ready": false,
     "world_class_pending_count": 4,
-    "release_lock_ready": true,
+    "release_lock_ready": false,
     "evidence_consistency_ok": true,
     "writes_source_files": false,
     "auto_patch_enabled": false,
@@ -480,7 +480,7 @@
     "local_blueprint_ready": true,
     "public_world_class_ready": false,
     "world_class_pending_count": 4,
-    "release_lock_ready": true,
+    "release_lock_ready": false,
     "evidence_consistency_ok": true
   },
   "actions": [
diff --git a/reports/skillops/daily/2026-06-16.md b/reports/skillops/daily/2026-06-16.md
index 105c41c3..d0fbea0f 100644
--- a/reports/skillops/daily/2026-06-16.md
+++ b/reports/skillops/daily/2026-06-16.md
@@ -14,7 +14,7 @@ Generated at: `2026-06-16`
 - local blueprint ready: `true`
 - public world-class ready: `false`
 - world-class pending: `4`
-- release lock ready: `true`
+- release lock ready: `false`
 - evidence consistency ok: `true`
 
 This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence.
diff --git a/reports/skillops/weekly/2026-W25.json b/reports/skillops/weekly/2026-W25.json
index 998d23ea..65c79eb3 100644
--- a/reports/skillops/weekly/2026-W25.json
+++ b/reports/skillops/weekly/2026-W25.json
@@ -15,7 +15,7 @@
   "top_score": 88,
   "skill_count": 12,
   "actionable_portfolio_issue_count": 0,
-  "release_lock_ready": true,
+  "release_lock_ready": false,
   "evidence_consistency_ok": true,
   "public_world_class_ready": false,
   "world_class_pending_count": 4,
@@ -35,7 +35,7 @@
     "top_score": 88,
     "skill_count": 12,
     "actionable_portfolio_issue_count": 0,
-    "release_lock_ready": true,
+    "release_lock_ready": false,
     "evidence_consistency_ok": true,
     "public_world_class_ready": false,
     "world_class_pending_count": 4,
@@ -287,7 +287,7 @@
     "no_route_opportunity_count": 0
   },
   "release_state": {
-    "release_lock_ready": true,
+    "release_lock_ready": false,
     "evidence_consistency_ok": true,
     "public_world_class_ready": false,
     "world_class_pending_count": 4
diff --git a/reports/skillops/weekly/2026-W25.md b/reports/skillops/weekly/2026-W25.md
index 4d75fc31..1fd6a716 100644
--- a/reports/skillops/weekly/2026-W25.md
+++ b/reports/skillops/weekly/2026-W25.md
@@ -13,7 +13,7 @@ Week: `2026-W25`
 - top_score: `88`
 - skill_count: `12`
 - actionable_portfolio_issue_count: `0`
-- release_lock_ready: `True`
+- release_lock_ready: `False`
 - evidence_consistency_ok: `True`
 - public_world_class_ready: `False`
 - world_class_pending_count: `4`
diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json
index b07bb792..ee01af92 100644
--- a/reports/upgrade_check.json
+++ b/reports/upgrade_check.json
@@ -1,7 +1,7 @@
 {
   "ok": true,
   "schema_version": "2.0",
-  "generated_at": "2026-06-16",
+  "generated_at": "2026-06-13",
   "previous": {
     "name": "yao-meta-skill",
     "version": "1.0.0",
@@ -75,7 +75,7 @@
       {
         "field": "package_sha256",
         "from": "0000000000000000000000000000000000000000000000000000000000000000",
-        "to": "db36e8f9d7d6745de28566d93383ac8d491806ee1e7a7175e6611db8e2958336"
+        "to": "a5f307ba8e89acb55d03b1bcee3e0ea50471af388511f2e53c73aff6d96ffb7f"
       }
     ]
   },
@@ -90,7 +90,7 @@
   "artifacts": {
     "previous_package": "registry/examples/yao-meta-skill-1.0.0.json",
     "current_package": "reports/registry_audit.json",
-    "json": "reports/upgrade_check.json",
-    "markdown": "reports/upgrade_check.md"
+    "json": "tests/tmp_review_studio/upgrade_check.json",
+    "markdown": "tests/tmp_review_studio/upgrade_check.md"
   }
 }
diff --git a/reports/world_class_evidence_intake.json b/reports/world_class_evidence_intake.json
index d42e2d05..f97f646f 100644
--- a/reports/world_class_evidence_intake.json
+++ b/reports/world_class_evidence_intake.json
@@ -113,7 +113,9 @@
           "observed token metadata"
         ],
         "runbook": [
-          "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+          "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+          "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+          "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
           "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
           "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
           "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -310,7 +312,7 @@
       "source_accepted": false,
       "observed_state": {
         "external_source_events": 0,
-        "adoption_sample_count": 0,
+        "adoption_sample_count": 1,
         "raw_content_allowed": false,
         "risk_band": "low",
         "accepted": false
diff --git a/reports/world_class_evidence_intake.md b/reports/world_class_evidence_intake.md
index bdc44eb2..c5a01fae 100644
--- a/reports/world_class_evidence_intake.md
+++ b/reports/world_class_evidence_intake.md
@@ -83,7 +83,9 @@ This report validates the intake contract for human and external evidence. A val
 
 #### Source Runbook
 
-- `YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60`
+- Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.
+- `export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}`
+- `python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60`
 - `python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>`
 - Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
 - `python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions`
diff --git a/reports/world_class_evidence_ledger.json b/reports/world_class_evidence_ledger.json
index fc725830..3d24c166 100644
--- a/reports/world_class_evidence_ledger.json
+++ b/reports/world_class_evidence_ledger.json
@@ -15,8 +15,8 @@
   "missing_submission_count": 4,
   "invalid_submission_count": 0,
   "source_check_count": 13,
-  "source_pass_count": 6,
-  "source_blocked_count": 7,
+  "source_pass_count": 7,
+  "source_blocked_count": 6,
   "submitted_but_pending_count": 0,
   "source_accepted_without_valid_submission_count": 0,
   "overclaim_guard_active": true,
@@ -31,8 +31,8 @@
     "missing_submission_count": 4,
     "invalid_submission_count": 0,
     "source_check_count": 13,
-    "source_pass_count": 6,
-    "source_blocked_count": 7,
+    "source_pass_count": 7,
+    "source_blocked_count": 6,
     "submitted_but_pending_count": 0,
     "source_accepted_without_valid_submission_count": 0,
     "overclaim_guard_active": true,
@@ -76,7 +76,9 @@
       "current": "model-executed 0; token-observed 0",
       "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
       "runbook": [
-        "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+        "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+        "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+        "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
         "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
         "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
         "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -396,7 +398,7 @@
       "status": "pending",
       "source_status": "external_required",
       "source_accepted": false,
-      "current": "external source events 0; adoption samples 0",
+      "current": "external source events 0; adoption samples 1",
       "objective": "Import production metadata-only events from a real external client into the local drift loop.",
       "runbook": [
         "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -433,7 +435,7 @@
       ],
       "observed_state": {
         "external_source_events": 0,
-        "adoption_sample_count": 0,
+        "adoption_sample_count": 1,
         "raw_content_allowed": false,
         "risk_band": "low",
         "accepted": false
@@ -454,8 +456,8 @@
           "label": "Adoption sample",
           "field": "adoption_sample_count",
           "expected": ">0",
-          "actual": 0,
-          "status": "blocked",
+          "actual": 1,
+          "status": "pass",
           "source_accepted": false,
           "next_action": "Telemetry must include adoption outcome evidence."
         },
@@ -471,8 +473,8 @@
         }
       ],
       "source_check_count": 3,
-      "source_pass_count": 1,
-      "source_blocked_count": 2,
+      "source_pass_count": 2,
+      "source_blocked_count": 1,
       "submission_state": {
         "status": "missing",
         "path": "evidence/world_class/submissions/native-client-telemetry.json",
diff --git a/reports/world_class_evidence_ledger.md b/reports/world_class_evidence_ledger.md
index 7fd7dc45..420fbb52 100644
--- a/reports/world_class_evidence_ledger.md
+++ b/reports/world_class_evidence_ledger.md
@@ -8,8 +8,8 @@ Generated at: `2026-06-16`
 - ready to claim world-class: `false`
 - entries: `4`
 - source accepted: `0`
-- source checks: `6` pass / `13` total
-- source blocked: `7`
+- source checks: `7` pass / `13` total
+- source blocked: `6`
 - accepted: `0`
 - pending: `4`
 - human pending: `1`
@@ -29,7 +29,7 @@ This ledger records the current evidence state. It requires both passing source
 | `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
 | `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices in the decision template, then regenerate adjudication. |
 | `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
-| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | Install a real client against the native host and import production metadata-only events. |
+| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 1 | Install a real client against the native host and import production metadata-only events. |
 
 ## Provider Holdout
 
@@ -47,7 +47,9 @@ This ledger records the current evidence state. It requires both passing source
 
 ### Source Runbook
 
-- `YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60`
+- Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.
+- `export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}`
+- `python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60`
 - `python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>`
 - Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
 - `python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions`
@@ -169,8 +171,8 @@ This ledger records the current evidence state. It requires both passing source
 
 - objective: Import production metadata-only events from a real external client into the local drift loop.
 - source status: `external_required`
-- observed state: `{"external_source_events": 0, "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false}`
-- source checks: `1` pass / `3` total
+- observed state: `{"external_source_events": 0, "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false}`
+- source checks: `2` pass / `3` total
 - submission state: `{"status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", "artifact_ref_count": 0, "attested_real_evidence": false, "privacy_contract_satisfied": false, "ledger_counts_as_completion": false}`
 
 ### Provenance Requirements
@@ -194,7 +196,7 @@ This ledger records the current evidence state. It requires both passing source
 | Check | Current | Expected | Status |
 | --- | --- | --- | --- |
 | External events | `0` | `>0` | `blocked` |
-| Adoption sample | `0` | `>0` | `blocked` |
+| Adoption sample | `1` | `>0` | `pass` |
 | Raw content blocked | `False` | `false` | `pass` |
 
 ### Completion Assertions
diff --git a/reports/world_class_evidence_plan.json b/reports/world_class_evidence_plan.json
index dbe36747..845c0ad8 100644
--- a/reports/world_class_evidence_plan.json
+++ b/reports/world_class_evidence_plan.json
@@ -26,7 +26,9 @@
       "current": "model-executed 0; token-observed 0",
       "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
       "runbook": [
-        "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+        "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+        "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+        "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
         "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
         "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
         "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -144,7 +146,7 @@
       "status": "external_required",
       "category": "external",
       "owner": "Browser/Chrome/IDE/provider client integrator",
-      "current": "external source events 0; adoption samples 0",
+      "current": "external source events 0; adoption samples 1",
       "objective": "Import production metadata-only events from a real external client into the local drift loop.",
       "runbook": [
         "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -187,7 +189,9 @@
       "current": "model-executed 0; token-observed 0",
       "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
       "runbook": [
-        "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+        "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+        "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+        "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
         "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
         "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
         "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -305,7 +309,7 @@
       "status": "external_required",
       "category": "external",
       "owner": "Browser/Chrome/IDE/provider client integrator",
-      "current": "external source events 0; adoption samples 0",
+      "current": "external source events 0; adoption samples 1",
       "objective": "Import production metadata-only events from a real external client into the local drift loop.",
       "runbook": [
         "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
diff --git a/reports/world_class_evidence_plan.md b/reports/world_class_evidence_plan.md
index f2da2daa..8c5c9537 100644
--- a/reports/world_class_evidence_plan.md
+++ b/reports/world_class_evidence_plan.md
@@ -22,7 +22,7 @@ This report is an execution plan for the remaining world-class evidence gaps. It
 | `provider-holdout` | `external_required` | `external` | operator with provider credentials | model-executed 0; token-observed 0 |
 | `human-adjudication` | `human_required` | `human` | human reviewer | 0/5 decisions; pending 5 |
 | `native-permission-enforcement` | `external_required` | `external` | target client or installer integrator | native-enforced targets 0; installer-enforced targets 4 |
-| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 |
+| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 |
 
 ## Provider Holdout
 
@@ -31,7 +31,9 @@ This report is an execution plan for the remaining world-class evidence gaps. It
 
 ### Runbook
 
-- `YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60`
+- Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.
+- `export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}`
+- `python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60`
 - `python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>`
 - Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
 - `python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions`
diff --git a/reports/world_class_evidence_preflight.html b/reports/world_class_evidence_preflight.html
index f40d59e8..88f28e2d 100644
--- a/reports/world_class_evidence_preflight.html
+++ b/reports/world_class_evidence_preflight.html
@@ -65,7 +65,7 @@
       <span class="eyebrow">Evidence Collection</span>
       <h1>World-Class Evidence Preflight</h1>
       <p class="lede">This operator view shows which external and human evidence is still blocked, which commands prepare editable submission drafts, and why preflight never counts as accepted evidence.</p>
-      <div class="stats"><article><span>Decision</span><strong>collection-preflight-blocked</strong></article><article><span>Pending</span><strong>4</strong></article><article><span>Ready</span><strong>1</strong></article><article><span>Blocked</span><strong>3</strong></article><article><span>Source</span><strong>6/13</strong></article></div>
+      <div class="stats"><article><span>Decision</span><strong>collection-preflight-blocked</strong></article><article><span>Pending</span><strong>4</strong></article><article><span>Ready</span><strong>1</strong></article><article><span>Blocked</span><strong>3</strong></article><article><span>Source</span><strong>7/13</strong></article></div>
     </section>
     <section class="section two-col" id="handoff">
       <article class="panel">
@@ -234,7 +234,7 @@
         </section>
         <section class="runbook">
           <h4>Runbook</h4>
-          <ul><li>YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=&lt;redacted&gt; python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul>
+          <ul><li>Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.</li><li>export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}</li><li>python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul>
         </section>
       </article>
 
@@ -611,15 +611,15 @@
           </dl>
         </article>
 
-        <article class="check-row blocked">
+        <article class="check-row pass">
           <div>
             <span>adoption_sample_count</span>
             <strong>Adoption sample</strong>
           </div>
           <dl>
-            <dt>Current</dt><dd><code>0</code></dd>
+            <dt>Current</dt><dd><code>1</code></dd>
             <dt>Expected</dt><dd><code>&gt;0</code></dd>
-            <dt>Status</dt><dd>blocked</dd>
+            <dt>Status</dt><dd>pass</dd>
             <dt>Action</dt><dd>Telemetry must include adoption outcome evidence.</dd>
           </dl>
         </article>
diff --git a/reports/world_class_evidence_preflight.json b/reports/world_class_evidence_preflight.json
index ecdf483a..615577db 100644
--- a/reports/world_class_evidence_preflight.json
+++ b/reports/world_class_evidence_preflight.json
@@ -14,8 +14,8 @@
     "collection_ready_count": 1,
     "collection_blocked_count": 3,
     "source_check_count": 13,
-    "source_pass_count": 6,
-    "source_blocked_count": 7,
+    "source_pass_count": 7,
+    "source_blocked_count": 6,
     "pending_count": 4,
     "ready_to_claim_world_class": false,
     "credential_value_exposed": false,
@@ -173,7 +173,9 @@
         "artifact_prefill_counts_as_evidence": false
       },
       "runbook": [
-        "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+        "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+        "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+        "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
         "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
         "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
         "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -533,8 +535,8 @@
           "label": "Adoption sample",
           "field": "adoption_sample_count",
           "expected": ">0",
-          "actual": 0,
-          "status": "blocked",
+          "actual": 1,
+          "status": "pass",
           "source_accepted": false,
           "next_action": "Telemetry must include adoption outcome evidence."
         },
@@ -889,8 +891,8 @@
       "label": "Adoption sample",
       "field": "adoption_sample_count",
       "expected": ">0",
-      "actual": 0,
-      "status": "blocked",
+      "actual": 1,
+      "status": "pass",
       "source_accepted": false,
       "next_action": "Telemetry must include adoption outcome evidence."
     },
diff --git a/reports/world_class_evidence_preflight.md b/reports/world_class_evidence_preflight.md
index 696f261d..b2349713 100644
--- a/reports/world_class_evidence_preflight.md
+++ b/reports/world_class_evidence_preflight.md
@@ -10,7 +10,7 @@ Generated at: `2026-06-16`
 - credential value exposed: `false`
 - collection ready: `1`
 - collection blocked: `3`
-- source checks: `6` pass / `13` total
+- source checks: `7` pass / `13` total
 
 This preflight report checks whether an operator can start collecting the remaining external or human evidence. It never accepts evidence, prints secret values, or changes the world-class ledger.
 
@@ -150,7 +150,7 @@ Generate the submission kit after the real provider, human, native-permission, o
 | Check | Current | Expected | Status | Next action |
 | --- | --- | --- | --- | --- |
 | External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. |
-| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. |
+| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. |
 | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. |
 
 ## Boundary
diff --git a/reports/world_class_operator_runbook.html b/reports/world_class_operator_runbook.html
index 81f44874..9fa92ced 100644
--- a/reports/world_class_operator_runbook.html
+++ b/reports/world_class_operator_runbook.html
@@ -57,7 +57,7 @@
       <span class="eyebrow">Evidence Operations</span>
       <h1>World-Class Operator Runbook</h1>
       <p class="lede">A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.</p>
-      <div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>6/13</strong></article><article><span>Blocked</span><strong>7</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
+      <div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>7/13</strong></article><article><span>Blocked</span><strong>6</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
     </section>
     <section class="section panel" id="fast-path"><h2>Fast Path</h2><ol><li>Run the real external or human work for one evidence item.</li><li>Generate and fill the matching submission draft.</li><li>Validate intake and inspect the submission review queue.</li><li>Refresh the ledger and run the claim guard before making any completion claim.</li></ol></section>
     <section class="section" id="items"><h2>Evidence Items</h2><div class="item-grid"><article class="item-card awaiting-submission">
@@ -69,7 +69,7 @@
           <dt>Blocked</dt><dd><code>2</code></dd>
           <dt>Submission</dt><dd><code>evidence/world_class/submissions/provider-holdout.json</code></dd>
         </dl>
-        <section class="source-panel"><h4>Source Runbook</h4><ul><li>YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=&lt;redacted&gt; python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section>
+        <section class="source-panel"><h4>Source Runbook</h4><ul><li>Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.</li><li>export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}</li><li>python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section>
         <section><h4>Commands</h4><ul class="commands"><li><span>prepare submission</span><code>python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions</code></li><li><span>validate intake</span><code>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</code></li><li><span>review queue</span><code>python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions</code></li><li><span>refresh ledger</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions</code></li><li><span>guard claim</span><code>python3 scripts/yao.py world-class-claim-guard .</code></li></ul></section>
         <div class="mini-grid">
           <section><h4>Must Collect</h4><ul><li>provider-backed model run</li><li>observed timing</li><li>observed token metadata</li></ul></section>
@@ -120,7 +120,7 @@
         <dl>
           <dt>Owner</dt><dd>Browser/Chrome/IDE/provider client integrator</dd>
           <dt>Ledger</dt><dd><code>pending</code></dd>
-          <dt>Blocked</dt><dd><code>2</code></dd>
+          <dt>Blocked</dt><dd><code>1</code></dd>
           <dt>Submission</dt><dd><code>evidence/world_class/submissions/native-client-telemetry.json</code></dd>
         </dl>
         <section class="source-panel"><h4>Source Runbook</h4><ul><li>python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://&lt;extension-id&gt;/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li><li>python3 scripts/yao.py skill-atlas --workspace-root .</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section>
@@ -130,8 +130,8 @@
           <section><h4>Success Checks</h4><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></section>
           <section><h4>Privacy</h4><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></section>
         </div>
-        <section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li><li>Telemetry must include adoption outcome evidence.</li></ul></section>
-        <section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check blocked'><span>Adoption sample</span><code>adoption_sample_count: 0 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
+        <section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li></ul></section>
+        <section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check pass'><span>Adoption sample</span><code>adoption_sample_count: 1 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
       </article></div></section>
     <section class="section panel" id="boundary"><h2>Boundary</h2><ul><li>Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.</li><li>Valid intake means ready for submission review; ledger review still requires passing source evidence.</li><li>The world-class ledger and claim guard remain the source of truth.</li></ul></section>
   </main>
diff --git a/reports/world_class_operator_runbook.json b/reports/world_class_operator_runbook.json
index c889b801..bc72296d 100644
--- a/reports/world_class_operator_runbook.json
+++ b/reports/world_class_operator_runbook.json
@@ -12,8 +12,8 @@
     "valid_packet_source_incomplete_count": 0,
     "invalid_submission_count": 0,
     "source_check_count": 13,
-    "source_pass_count": 6,
-    "source_blocked_count": 7,
+    "source_pass_count": 7,
+    "source_blocked_count": 6,
     "ready_to_claim_world_class": false,
     "runbook_counts_as_completion": false,
     "decision": "collect-evidence"
@@ -35,7 +35,9 @@
       "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
       "current": "model-executed 0; token-observed 0",
       "execution_runbook": [
-        "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+        "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+        "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+        "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
         "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
         "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
         "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
@@ -397,7 +399,7 @@
       "review_state": "awaiting-submission",
       "source_accepted": false,
       "objective": "Import production metadata-only events from a real external client into the local drift loop.",
-      "current": "external source events 0; adoption samples 0",
+      "current": "external source events 0; adoption samples 1",
       "execution_runbook": [
         "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
         "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
@@ -445,7 +447,7 @@
       ],
       "observed_state": {
         "external_source_events": 0,
-        "adoption_sample_count": 0,
+        "adoption_sample_count": 1,
         "raw_content_allowed": false,
         "risk_band": "low",
         "accepted": false
@@ -466,8 +468,8 @@
           "label": "Adoption sample",
           "field": "adoption_sample_count",
           "expected": ">0",
-          "actual": 0,
-          "status": "blocked",
+          "actual": 1,
+          "status": "pass",
           "source_accepted": false,
           "next_action": "Telemetry must include adoption outcome evidence."
         },
@@ -482,10 +484,9 @@
           "next_action": "Telemetry must stay metadata-only."
         }
       ],
-      "blocked_source_check_count": 2,
+      "blocked_source_check_count": 1,
       "next_source_actions": [
-        "Import at least one metadata-only event from a real client.",
-        "Telemetry must include adoption outcome evidence."
+        "Import at least one metadata-only event from a real client."
       ],
       "submission_state": {
         "status": "missing",
diff --git a/reports/world_class_operator_runbook.md b/reports/world_class_operator_runbook.md
index 7d396272..9db0580c 100644
--- a/reports/world_class_operator_runbook.md
+++ b/reports/world_class_operator_runbook.md
@@ -28,7 +28,7 @@ This runbook coordinates evidence collection only. It does not accept submission
 | `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials. | operator with provider credentials |
 | `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Record a reviewer choice for every pair. | human reviewer |
 | `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator |
-| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
+| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
 
 ## Provider Holdout
 
@@ -40,7 +40,9 @@ This runbook coordinates evidence collection only. It does not accept submission
 
 ### Source Runbook
 
-- YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
+- Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.
+- export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}
+- python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
 - python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
 - Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
 - python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
@@ -242,7 +244,7 @@ This runbook coordinates evidence collection only. It does not accept submission
 
 - objective: Import production metadata-only events from a real external client into the local drift loop.
 - blocking reason: No evidence packet has been submitted for review.
-- blocked source checks: `2`
+- blocked source checks: `1`
 - submission: `evidence/world_class/submissions/native-client-telemetry.json`
 - template: `evidence/world_class/templates/native-client-telemetry.intake.json`
 
@@ -295,14 +297,13 @@ This runbook coordinates evidence collection only. It does not accept submission
 ### Next Source Actions
 
 - Import at least one metadata-only event from a real client.
-- Telemetry must include adoption outcome evidence.
 
 ### Source Evidence Snapshot
 
 | Check | Current | Expected | Status | Next action |
 | --- | --- | --- | --- | --- |
 | External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. |
-| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. |
+| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. |
 | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. |
 
 ## Boundary
diff --git a/reports/world_class_submission_review.json b/reports/world_class_submission_review.json
index 43a75d25..8eaeeee6 100644
--- a/reports/world_class_submission_review.json
+++ b/reports/world_class_submission_review.json
@@ -14,8 +14,8 @@
   "unmatched_submission_count": 0,
   "invalid_submission_count": 0,
   "source_check_count": 13,
-  "source_pass_count": 6,
-  "source_blocked_count": 7,
+  "source_pass_count": 7,
+  "source_blocked_count": 6,
   "review_counts_submission_as_completion": false,
   "summary": {
     "review_item_count": 4,
@@ -27,8 +27,8 @@
     "unmatched_submission_count": 0,
     "invalid_submission_count": 0,
     "source_check_count": 13,
-    "source_pass_count": 6,
-    "source_blocked_count": 7,
+    "source_pass_count": 7,
+    "source_blocked_count": 6,
     "ready_to_claim_world_class": false,
     "review_counts_submission_as_completion": false,
     "decision": "awaiting-submissions"
@@ -302,7 +302,7 @@
       "intake_errors": [],
       "observed_state": {
         "external_source_events": 0,
-        "adoption_sample_count": 0,
+        "adoption_sample_count": 1,
         "raw_content_allowed": false,
         "risk_band": "low",
         "accepted": false
@@ -323,8 +323,8 @@
           "label": "Adoption sample",
           "field": "adoption_sample_count",
           "expected": ">0",
-          "actual": 0,
-          "status": "blocked",
+          "actual": 1,
+          "status": "pass",
           "source_accepted": false,
           "next_action": "Telemetry must include adoption outcome evidence."
         },
@@ -340,8 +340,8 @@
         }
       ],
       "source_check_count": 3,
-      "source_pass_count": 1,
-      "source_blocked_count": 2,
+      "source_pass_count": 2,
+      "source_blocked_count": 1,
       "success_checks": [
         "reports/adoption_drift_report.json summary.source_types.external > 0",
         "reports/adoption_drift_report.json summary.adoption_sample_count > 0",
diff --git a/reports/world_class_submission_review.md b/reports/world_class_submission_review.md
index 7d625fcc..322fc7ff 100644
--- a/reports/world_class_submission_review.md
+++ b/reports/world_class_submission_review.md
@@ -139,7 +139,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
 #### Source Checks
 
 - External events: 0 / >0 => blocked
-- Adoption sample: 0 / >0 => blocked
+- Adoption sample: 1 / >0 => pass
 - Raw content blocked: False / false => pass
 
 #### Completion Assertions
diff --git a/scripts/render_world_class_evidence_plan.py b/scripts/render_world_class_evidence_plan.py
index eb0b7c47..d0ec028a 100644
--- a/scripts/render_world_class_evidence_plan.py
+++ b/scripts/render_world_class_evidence_plan.py
@@ -17,7 +17,9 @@ TASK_TEMPLATES: dict[str, dict[str, Any]] = {
         "owner": "operator with provider credentials",
         "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
         "runbook": [
-            "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
+            "Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
+            "export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
+            "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
             "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
         ],
         "success_checks": [
diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json
index aa7cbeaa..14b36f13 100644
--- a/skill_atlas/catalog.json
+++ b/skill_atlas/catalog.json
@@ -1,6 +1,6 @@
 {
   "workspace_root": ".",
-  "generated_at": "2026-06-16",
+  "generated_at": "2026-06-13",
   "skills": [
     {
       "name": "yao-meta-skill",
@@ -211,8 +211,8 @@
         "report": "reports/adoption_drift_report.json",
         "risk_band": "low",
         "event_count": 1,
-        "adoption_sample_count": 0,
-        "adoption_rate": 0,
+        "adoption_sample_count": 1,
+        "adoption_rate": 100.0,
         "candidate_count": 0
       }
     },
diff --git a/skill_atlas/stale_skills.json b/skill_atlas/stale_skills.json
index b57d361d..6602e829 100644
--- a/skill_atlas/stale_skills.json
+++ b/skill_atlas/stale_skills.json
@@ -24,7 +24,7 @@
     "name": "incident-command-governor",
     "path": "examples/governed-incident-command/generated-skill",
     "reason": "review overdue by cadence monthly",
-    "age_days": 77,
+    "age_days": 74,
     "allowed_days": 31,
     "actionable": false,
     "scope": "example"
diff --git a/tests/verify_review_studio.py b/tests/verify_review_studio.py
index 357aa1bc..f43c9b9a 100644
--- a/tests/verify_review_studio.py
+++ b/tests/verify_review_studio.py
@@ -545,6 +545,7 @@ def main() -> None:
     assert any("world-class-intake" in item["command"] for item in provider_action_step["commands"]), provider_action_step
     assert any("world-class-ledger" in item["command"] for item in provider_action_step["commands"]), provider_action_step
     assert any("output-exec --provider-runner openai" in item for item in provider_action_step["runbook"]), provider_action_step
+    assert not any("<redacted>" in item or "OPENAI_API_KEY=" in item for item in provider_action_step["runbook"]), provider_action_step
     assert "provider-backed model run" in provider_action_step["provenance_requirements"], provider_action_step
     assert "reports/output_execution_runs.json summary.model_executed_count > 0" in provider_action_step["success_checks"], provider_action_step
     assert "reports/output_execution_runs.json" in provider_action_step["evidence_artifacts"], provider_action_step
@@ -727,6 +728,7 @@ def main() -> None:
     assert "计划、metadata fallback、待评审和本地命令不会被当成完成证据" in html, html
     assert "执行步骤" in html, html
     assert "output-exec --provider-runner openai" in html, html
+    assert "&lt;redacted&gt;" not in html and "<redacted>" not in html, html
     assert "world-runbook-panel" in html, html
     assert "源证据检查" in html, html
     assert "world-source-checks" in html, html
diff --git a/tests/verify_world_class_evidence_intake.py b/tests/verify_world_class_evidence_intake.py
index 4ef7a785..269b82bb 100644
--- a/tests/verify_world_class_evidence_intake.py
+++ b/tests/verify_world_class_evidence_intake.py
@@ -604,6 +604,8 @@ def main() -> None:
     assert "`python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions`" in markdown, markdown
     assert "Source Runbook" in markdown, markdown
     assert "output-exec --provider-runner openai" in markdown, markdown
+    assert "<redacted>" not in markdown, markdown
+    assert "OPENAI_API_KEY=<redacted>" not in markdown, markdown
     assert "Templates and planned work do not count as accepted evidence." in markdown, markdown
     assert "Real submissions must include the evidence-key critical artifact paths with verified SHA-256 digests." in markdown, markdown
     assert "Real submissions must replace template submitter, date, and provenance placeholders with concrete evidence metadata." in markdown, markdown
@@ -669,6 +671,9 @@ def main() -> None:
     assert kit_draft["template_only"] is True, kit_draft
     assert kit_draft["attestation"]["real_external_or_human_evidence"] is False, kit_draft
     assert "sha256" not in kit_draft["artifact_refs"][0], kit_draft
+    assert kit_draft["provenance"]["run_command"] == "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60", kit_draft
+    assert kit_draft["provenance"]["credential_env"] == "OPENAI_API_KEY", kit_draft
+    assert "<redacted>" not in json.dumps(kit_draft), kit_draft
     kit_manifest = json.loads((kit_dir / "submission_manifest.json").read_text(encoding="utf-8"))
     assert kit_manifest["summary"]["ledger_counts_submission_as_completion"] is False, kit_manifest["summary"]
     assert kit_manifest["summary"]["artifact_prefill_enabled"] is False, kit_manifest["summary"]
@@ -680,6 +685,7 @@ def main() -> None:
     assert "Drafts are not accepted evidence." in kit_readme, kit_readme
     assert "Execution Runbook" in kit_readme, kit_readme
     assert "output-exec --provider-runner openai" in kit_readme, kit_readme
+    assert "<redacted>" not in kit_readme, kit_readme
     assert "validate intake" in kit_readme, kit_readme
     assert "Artifact Checklist" in kit_readme, kit_readme
     assert "Evidence Matrix" in kit_readme, kit_readme
@@ -715,6 +721,7 @@ def main() -> None:
     assert "World-Class Evidence Submission Kit" in kit_html, kit_html
     assert "Execution Runbook" in kit_html, kit_html
     assert "output-exec --provider-runner openai" in kit_html, kit_html
+    assert "&lt;redacted&gt;" not in kit_html and "<redacted>" not in kit_html, kit_html
     assert "Do not include credentials, raw prompts, raw outputs, transcripts, notes, or private user content." in kit_html, kit_html
     assert "Rows marked submission-ref are the paths expected in artifact_refs" in kit_html, kit_html
 
diff --git a/tests/verify_world_class_evidence_ledger.py b/tests/verify_world_class_evidence_ledger.py
index fa00b3ac..3f7357be 100644
--- a/tests/verify_world_class_evidence_ledger.py
+++ b/tests/verify_world_class_evidence_ledger.py
@@ -122,6 +122,7 @@ def main() -> None:
     }, entries
     assert entries["provider-holdout"]["observed_state"]["model_executed_count"] == 0, entries["provider-holdout"]
     assert any("output-exec --provider-runner openai" in step for step in entries["provider-holdout"]["runbook"]), entries["provider-holdout"]
+    assert not any("<redacted>" in step or "OPENAI_API_KEY=" in step for step in entries["provider-holdout"]["runbook"]), entries["provider-holdout"]
     provider_source = {item["field"]: item for item in entries["provider-holdout"]["source_checklist"]}
     assert provider_source["model_executed_count"]["status"] == "blocked", provider_source
     assert provider_source["timing_observed_count"]["status"] == "pass", provider_source
@@ -147,6 +148,8 @@ def main() -> None:
     assert "source checks:" in markdown, markdown
     assert "Source Runbook" in markdown, markdown
     assert "output-exec --provider-runner openai" in markdown, markdown
+    assert "<redacted>" not in markdown, markdown
+    assert "OPENAI_API_KEY=<redacted>" not in markdown, markdown
     assert "Source Evidence Checks" in markdown, markdown
     assert "| Provider model run | `0` | `>0` | `blocked` |" in markdown, markdown
     assert "`provider-holdout`" in markdown, markdown
diff --git a/tests/verify_world_class_evidence_plan.py b/tests/verify_world_class_evidence_plan.py
index 0a72b6d0..3f8393ec 100644
--- a/tests/verify_world_class_evidence_plan.py
+++ b/tests/verify_world_class_evidence_plan.py
@@ -54,7 +54,11 @@ def main() -> None:
         "native-client-telemetry",
     }, tasks
     assert set(requirements) == set(tasks), requirements
-    assert any("--provider-runner openai" in command for command in tasks["provider-holdout"]["runbook"]), tasks["provider-holdout"]
+    provider_runbook = tasks["provider-holdout"]["runbook"]
+    assert any("--provider-runner openai" in command for command in provider_runbook), tasks["provider-holdout"]
+    assert any(command.startswith("Set OPENAI_API_KEY") for command in provider_runbook), tasks["provider-holdout"]
+    assert any(command.startswith("export YAO_OUTPUT_EVAL_MODEL=") for command in provider_runbook), tasks["provider-holdout"]
+    assert not any("<redacted>" in command or "OPENAI_API_KEY=" in command for command in provider_runbook), tasks["provider-holdout"]
     assert any("world-class-intake . --submissions-dir evidence/world_class/submissions" in command for command in tasks["provider-holdout"]["runbook"]), tasks["provider-holdout"]
     assert any("evidence/world_class/templates/provider-holdout.intake.json" in command for command in tasks["provider-holdout"]["runbook"]), tasks["provider-holdout"]
     assert "reports/output_review_decisions.json" in tasks["human-adjudication"]["evidence_artifacts"], tasks["human-adjudication"]
@@ -76,6 +80,8 @@ def main() -> None:
     assert "`provider-holdout`" in markdown, markdown
     assert "ready to claim world-class: `false`" in markdown, markdown
     assert "ledger completion required: `true`" in markdown, markdown
+    assert "<redacted>" not in markdown, markdown
+    assert "OPENAI_API_KEY=<redacted>" not in markdown, markdown
     print(json.dumps({"ok": True}, ensure_ascii=False, indent=2))
 
 
diff --git a/tests/verify_world_class_operator_runbook.py b/tests/verify_world_class_operator_runbook.py
index c4edbae9..c04738d7 100644
--- a/tests/verify_world_class_operator_runbook.py
+++ b/tests/verify_world_class_operator_runbook.py
@@ -122,6 +122,7 @@ def main() -> None:
     assert provider["source_accepted"] is False, provider
     assert provider["blocked_source_check_count"] == 2, provider
     assert any("output-exec --provider-runner openai" in step for step in provider["execution_runbook"]), provider
+    assert not any("<redacted>" in step or "OPENAI_API_KEY=" in step for step in provider["execution_runbook"]), provider
     assert "Run provider-backed output-exec with real credentials." in provider["next_source_actions"], provider
     assert "Provider execution should return non-estimated token usage." in provider["next_source_actions"], provider
     assert provider["commands"]["prepare_submission"].startswith("python3 scripts/yao.py world-class-submission-kit"), provider
@@ -143,6 +144,8 @@ def main() -> None:
     assert "| `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials." in markdown, markdown
     assert "Source Runbook" in markdown, markdown
     assert "output-exec --provider-runner openai" in markdown, markdown
+    assert "<redacted>" not in markdown, markdown
+    assert "OPENAI_API_KEY=<redacted>" not in markdown, markdown
     assert "### Next Source Actions" in markdown, markdown
     assert "- Provider execution should return non-estimated token usage." in markdown, markdown
     assert "Source Evidence Snapshot" in markdown, markdown
@@ -159,6 +162,8 @@ def main() -> None:
     assert "Next Source Actions" in html, html
     assert "Source Runbook" in html, html
     assert "output-exec --provider-runner openai" in html, html
+    assert "&lt;redacted&gt;" not in html and "<redacted>" not in html, html
+    assert "OPENAI_API_KEY=&lt;redacted&gt;" not in html, html
     assert "Source Evidence Snapshot" in html, html
     assert "model_executed_count" in html, html
     assert "model_executed_count: 0 / &gt;0" in html, html