diff --git a/AGENTS.md b/AGENTS.md
index 7190529e..9ddab014 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -76,6 +76,7 @@ Clean test-only scratch directories after verification with `find tests -maxdept
 - `scripts/render_world_class_evidence_plan.py`: executable evidence task plan for the remaining world-class readiness gaps. Keep provider, human, native-permission, and real-client telemetry evidence requirements concrete without marking planned work as complete.
 - `scripts/render_world_class_evidence_ledger.py`: machine-checkable acceptance ledger for the remaining world-class evidence gaps. Keep anti-overclaim guards explicit so planned work, metadata fallbacks, pending review, and local command runners never count as final evidence.
 - `scripts/render_world_class_evidence_intake.py`: intake validator for external and human world-class evidence packets. Real submissions must reference concrete local aggregate artifacts with matching SHA-256 digests; templates may stay hash-free and must not count as evidence.
+- `scripts/world_class_evidence_contract.py`: shared intake contract and artifact-integrity validator. Keep ledger, intake, and submission review aligned so source evidence cannot be accepted without a valid real submission and matching artifact SHA-256 checks.
 - `scripts/render_world_class_submission_review.py`: read-only queue for external and human evidence packets after intake validation. Keep it from accepting evidence; it may only compare packet validity, source evidence checks, and ledger state.
 - `scripts/render_world_class_operator_runbook.py`: operator-facing world-class evidence runbook. Keep it as coordination guidance only; it must not accept evidence or flip world-class readiness.
 - `scripts/render_benchmark_reproducibility.py`: release-facing benchmark reproducibility manifest. Keep methodology sections, required artifacts, failure disclosure, reproduction commands, and world-class limitations machine-checkable.
diff --git a/registry/index.json b/registry/index.json
index 1202c03d..58dc5ab3 100644
--- a/registry/index.json
+++ b/registry/index.json
@@ -1,6 +1,6 @@
 {
   "schema_version": "2.0",
-  "generated_at": "2026-06-14",
+  "generated_at": "2026-06-13",
   "package_count": 1,
   "packages": [
     {
@@ -16,7 +16,7 @@
         "vscode"
       ],
       "package_metadata": "registry/packages/yao-meta-skill.json",
-      "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+      "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
     }
   ]
 }
diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json
index 14747475..0ae24966 100644
--- a/registry/packages/yao-meta-skill.json
+++ b/registry/packages/yao-meta-skill.json
@@ -16,8 +16,8 @@
   "trust_level": "local",
   "license": "MIT",
   "checksums": {
-    "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c",
-    "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e"
+    "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb",
+    "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe"
   },
   "compatibility": {
     "openai": "pass",
@@ -48,10 +48,10 @@
   },
   "distribution": {
     "archive_verified": true,
-    "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e",
+    "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe",
     "package_verification": "reports/package_verification.json",
     "install_simulated": true,
     "install_simulation": "reports/install_simulation.json"
   },
-  "generated_at": "2026-06-14"
+  "generated_at": "2026-06-13"
 }
diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json
index f1398131..75697bfe 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": "2026-06-14T00:32:04Z",
+  "generated_at": "2026-06-14T00:52:22Z",
   "skill_dir": ".",
   "privacy_contract": {
     "storage": "local-first",
diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json
index b188c644..dfcdabf5 100644
--- a/reports/architecture_maintainability.json
+++ b/reports/architecture_maintainability.json
@@ -4,10 +4,10 @@
   "generated_at": "2026-06-13",
   "skill_dir": ".",
   "summary": {
-    "python_file_count": 153,
-    "script_file_count": 94,
+    "python_file_count": 154,
+    "script_file_count": 95,
     "test_file_count": 59,
-    "internal_module_count": 19,
+    "internal_module_count": 20,
     "cli_script_count": 76,
     "command_handler_count": 34,
     "warn_line_threshold": 900,
diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md
index 168317fb..8396d083 100644
--- a/reports/architecture_maintainability.md
+++ b/reports/architecture_maintainability.md
@@ -5,10 +5,10 @@ Generated at: `2026-06-13`
 ## Summary
 
 - decision: `pass`
-- python files: `153`
-- scripts: `94`
+- python files: `154`
+- scripts: `95`
 - tests: `59`
-- internal modules: `19`
+- internal modules: `20`
 - CLI scripts: `76`
 - Yao CLI command handlers: `34`
 - largest file lines: `899`
diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json
index 09f23f59..96ea6484 100644
--- a/reports/benchmark_reproducibility.json
+++ b/reports/benchmark_reproducibility.json
@@ -3,24 +3,24 @@
   "ok": true,
   "generated_at": "2026-06-14",
   "skill_dir": ".",
-  "commit": "bd7f1d8cccbebac1222c0ee7bbc01c1e3b991126",
+  "commit": "48f2826b8c9ebad3a9cc90e6166f4fd253f98308",
   "git_status": {
     "available": true,
     "dirty": true,
-    "changed_file_count": 27,
+    "changed_file_count": 50,
     "sample": [
       " M AGENTS.md",
-      " M evidence/world_class/README.md",
-      " M evidence/world_class/intake.schema.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/context_budget.json",
-      " M reports/output_execution_runs.json",
-      " M reports/output_execution_runs.md",
-      " M reports/package_verification.json"
+      " M reports/install_simulation.json",
+      " M reports/install_simulation.md"
     ]
   },
   "summary": {
@@ -42,7 +42,7 @@
     "world_class_task_count": 4,
     "world_class_ledger_pending_count": 4,
     "working_tree_dirty": true,
-    "changed_file_count": 27
+    "changed_file_count": 50
   },
   "methodology": {
     "path": "reports/benchmark_methodology.md",
@@ -116,7 +116,7 @@
       "path": "reports/output_execution_runs.json",
       "exists": true,
       "bytes": 7967,
-      "sha256": "9b77977fc455f5cc473317efb0a71ae07a13bb1ddc5874ba5acb296659c5bac0"
+      "sha256": "0ff38df2c18b25b79b9bf36e3055908a57d920ff45fa697f8281ce3a960f61b5"
     },
     {
       "label": "blind_review",
@@ -150,57 +150,57 @@
       "label": "trust_report",
       "path": "reports/security_trust_report.json",
       "exists": true,
-      "bytes": 97005,
-      "sha256": "dc188ff6756e94c207ebdd2e182dcb2432cf44d8f8f824c10ff31f6ba0a4078f"
+      "bytes": 97621,
+      "sha256": "3c95ea60b1c941d1adae1827ca0ec312140d72db4d45e512ace8636f75378ba2"
     },
     {
       "label": "python_compatibility",
       "path": "reports/python_compatibility.json",
       "exists": true,
-      "bytes": 20367,
-      "sha256": "3698aad5388cad659840d1d31dbc9c694e0067b1de1e84423336a34e22df9625"
+      "bytes": 20499,
+      "sha256": "4edb5722c888f2fe5fc6c3141535ab5d550b6b1c05e9b4230b77e6712a982fb4"
     },
     {
       "label": "registry_audit",
       "path": "reports/registry_audit.json",
       "exists": true,
       "bytes": 3183,
-      "sha256": "b9acd15b662da8835b0c2ba0ad554a409f3265c2c779753d68f8a8dc5fdd5820"
+      "sha256": "ad7900024ed6cadd5ea717ba22e38f38402e1a883bff119da24f7ecfd92c7dd8"
     },
     {
       "label": "package_verification",
       "path": "reports/package_verification.json",
       "exists": true,
       "bytes": 19325,
-      "sha256": "0e87470fb95411379ee79420db3c7069433d086378a69b78da1f4ad2bf45edd8"
+      "sha256": "dd12856ce8306600e089b44018ae4f7fae66366fba60f9408da885fbf5ab8035"
     },
     {
       "label": "install_simulation",
       "path": "reports/install_simulation.json",
       "exists": true,
-      "bytes": 8604,
-      "sha256": "97055f63c699b2812bab1a0f05460f1065a6211164b4c22c9bebc8aab6ef012f"
+      "bytes": 8758,
+      "sha256": "aabe72c3f5bde128ff74a24aef3e35f0ad449a431b9a932e92ec4ae5f3f308e4"
     },
     {
       "label": "skill_os2_audit",
       "path": "reports/skill_os2_audit.json",
       "exists": true,
       "bytes": 14309,
-      "sha256": "9c7b86742ed4dd5c930fbc3572d943937a4817bbd465d89da12f0929911607d0"
+      "sha256": "0c74deea906e75f6a116e2e3d043e134ce820bd12782af18428b3c04a02e6bd0"
     },
     {
       "label": "world_class_evidence_plan",
       "path": "reports/world_class_evidence_plan.json",
       "exists": true,
-      "bytes": 10083,
-      "sha256": "194d5a681920c3aca5e454d8839cdec551a076d54e360424831c5f312d1367b1"
+      "bytes": 19532,
+      "sha256": "a9bd392cd45f3accabe9b5befb9090456f383b1edbc323cab7d20930179dc229"
     },
     {
       "label": "world_class_evidence_ledger",
       "path": "reports/world_class_evidence_ledger.json",
       "exists": true,
-      "bytes": 11308,
-      "sha256": "dc4cf8cf18899bdf10d32fe72bb8f306ee297106e6cc25fd041d56e36631af63"
+      "bytes": 11613,
+      "sha256": "0bff14542475657a1261c1afcd87ffabc5d5c5e75bcd20afcfeacc44b16b7c14"
     },
     {
       "label": "world_class_evidence_intake",
@@ -214,14 +214,14 @@
       "path": "reports/world_class_submission_review.json",
       "exists": true,
       "bytes": 7263,
-      "sha256": "185a8cab25e7155ebd80cb66049c0965e4dc2d7cc38991f17464946f87fd26f2"
+      "sha256": "4f03edb2ef28d9dfd27a393f8058d6e27d2b10fa8cbfe35f473e003556b9ffe0"
     },
     {
       "label": "world_class_operator_runbook",
       "path": "reports/world_class_operator_runbook.json",
       "exists": true,
       "bytes": 15002,
-      "sha256": "3d643dc8170b50a37f91ffb190f69ad1e0d32f64914ebe2d731226728ac28cdc"
+      "sha256": "614742ea666c64cdb68e10fc77022c31e68abe82ed88325aea21acb2f277063e"
     },
     {
       "label": "world_class_operator_runbook_markdown",
diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md
index 89573749..9b13c349 100644
--- a/reports/benchmark_reproducibility.md
+++ b/reports/benchmark_reproducibility.md
@@ -1,7 +1,7 @@
 # Benchmark Reproducibility
 
 Generated at: `2026-06-14`
-Commit: `bd7f1d8cccbebac1222c0ee7bbc01c1e3b991126`
+Commit: `48f2826b8c9ebad3a9cc90e6166f4fd253f98308`
 Working tree dirty at generation: `true`
 
 ## Summary
@@ -16,7 +16,7 @@ Working tree dirty at generation: `true`
 - provider evidence complete: `false`
 - human review complete: `false`
 - world-class ready: `false`
-- changed files at generation: `27`
+- changed files at generation: `50`
 
 This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete.
 
@@ -40,22 +40,22 @@ 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 | `9b77977fc455` |
+| output_execution | `reports/output_execution_runs.json` | present | `0ff38df2c18b` |
 | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
 | review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` |
 | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
 | runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` |
-| trust_report | `reports/security_trust_report.json` | present | `dc188ff6756e` |
-| python_compatibility | `reports/python_compatibility.json` | present | `3698aad5388c` |
-| registry_audit | `reports/registry_audit.json` | present | `b9acd15b662d` |
-| package_verification | `reports/package_verification.json` | present | `0e87470fb954` |
-| install_simulation | `reports/install_simulation.json` | present | `97055f63c699` |
-| skill_os2_audit | `reports/skill_os2_audit.json` | present | `9c7b86742ed4` |
-| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `194d5a681920` |
-| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `dc4cf8cf1889` |
+| trust_report | `reports/security_trust_report.json` | present | `3c95ea60b1c9` |
+| python_compatibility | `reports/python_compatibility.json` | present | `4edb5722c888` |
+| registry_audit | `reports/registry_audit.json` | present | `ad7900024ed6` |
+| package_verification | `reports/package_verification.json` | present | `dd12856ce830` |
+| install_simulation | `reports/install_simulation.json` | present | `aabe72c3f5bd` |
+| skill_os2_audit | `reports/skill_os2_audit.json` | present | `0c74deea906e` |
+| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `a9bd392cd45f` |
+| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `0bff14542475` |
 | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `2cb7e6beb565` |
-| world_class_submission_review | `reports/world_class_submission_review.json` | present | `185a8cab25e7` |
-| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `3d643dc8170b` |
+| world_class_submission_review | `reports/world_class_submission_review.json` | present | `4f03edb2ef28` |
+| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `614742ea666c` |
 | world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `f67ca3d0aa9c` |
 | world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `963026f551dc` |
 | world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `250d616b028c` |
diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json
index dfb56a41..bf18763e 100644
--- a/reports/compiled_targets.json
+++ b/reports/compiled_targets.json
@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-14",
+  "generated_at": "2026-06-13",
   "skill_dir": ".",
   "summary": {
     "target_count": 5,
diff --git a/reports/context_budget.json b/reports/context_budget.json
index d1672d78..8ac8fd13 100644
--- a/reports/context_budget.json
+++ b/reports/context_budget.json
@@ -6,10 +6,10 @@
     "context_budget_tier": "production",
     "context_budget_limit": 1000,
     "skill_body_tokens": 751,
-    "other_text_tokens": 1178333,
+    "other_text_tokens": 1183524,
     "estimated_initial_load_tokens": 944,
-    "estimated_total_text_tokens": 1179084,
-    "relevant_file_count": 498,
+    "estimated_total_text_tokens": 1184275,
+    "relevant_file_count": 500,
     "unused_resource_dirs": [],
     "quality_signal_points": 130,
     "quality_density": 137.7
diff --git a/reports/install_simulation.json b/reports/install_simulation.json
index 291d2ad4..38051603 100644
--- a/reports/install_simulation.json
+++ b/reports/install_simulation.json
@@ -1,14 +1,14 @@
 {
   "ok": true,
   "schema_version": "2.0",
-  "generated_at": "2026-06-14",
+  "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": 573,
+    "archive_entry_count": 574,
     "archive_extracted": true,
     "entrypoint_loaded": true,
     "manifest_loaded": true,
@@ -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 863bb839..04d82c8d 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": 24.72,
+      "duration_ms": 30.68,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -62,7 +62,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 23.92,
+      "duration_ms": 28.53,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -85,7 +85,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 24.18,
+      "duration_ms": 29.59,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -113,7 +113,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 25.49,
+      "duration_ms": 31.84,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -136,7 +136,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 24.68,
+      "duration_ms": 30.95,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -164,7 +164,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 24.46,
+      "duration_ms": 27.6,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -187,7 +187,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 24.04,
+      "duration_ms": 26.76,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -214,7 +214,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 24.01,
+      "duration_ms": 26.87,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -237,7 +237,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 23.99,
+      "duration_ms": 26.9,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -266,7 +266,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 24.34,
+      "duration_ms": 27.3,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md
index 6c6aeaf3..083d91b8 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 | 24.72 | 33 | 0.0 | pass |
-| skill-package-contract | with_skill | command | local-output-eval-runner | 23.92 | 73 | 100.0 | pass |
-| output-eval-expectation | baseline | command | local-output-eval-runner | 24.18 | 36 | 0.0 | pass |
-| output-eval-expectation | with_skill | command | local-output-eval-runner | 25.49 | 80 | 100.0 | pass |
-| ir-before-packaging | baseline | command | local-output-eval-runner | 24.68 | 33 | 0.0 | pass |
-| ir-before-packaging | with_skill | command | local-output-eval-runner | 24.46 | 80 | 100.0 | pass |
-| near-neighbor-boundary | baseline | command | local-output-eval-runner | 24.04 | 36 | 0.0 | pass |
-| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 24.01 | 65 | 100.0 | pass |
-| file-backed-governed-package | baseline | command | local-output-eval-runner | 23.99 | 37 | 0.0 | pass |
-| file-backed-governed-package | with_skill | command | local-output-eval-runner | 24.34 | 98 | 100.0 | pass |
+| skill-package-contract | baseline | command | local-output-eval-runner | 30.68 | 33 | 0.0 | pass |
+| skill-package-contract | with_skill | command | local-output-eval-runner | 28.53 | 73 | 100.0 | pass |
+| output-eval-expectation | baseline | command | local-output-eval-runner | 29.59 | 36 | 0.0 | pass |
+| output-eval-expectation | with_skill | command | local-output-eval-runner | 31.84 | 80 | 100.0 | pass |
+| ir-before-packaging | baseline | command | local-output-eval-runner | 30.95 | 33 | 0.0 | pass |
+| ir-before-packaging | with_skill | command | local-output-eval-runner | 27.6 | 80 | 100.0 | pass |
+| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.76 | 36 | 0.0 | pass |
+| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.87 | 65 | 100.0 | pass |
+| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.9 | 37 | 0.0 | pass |
+| file-backed-governed-package | with_skill | command | local-output-eval-runner | 27.3 | 98 | 100.0 | pass |
 
 ## Next Fixes
 
diff --git a/reports/package_verification.json b/reports/package_verification.json
index c071aab5..01c17c20 100644
--- a/reports/package_verification.json
+++ b/reports/package_verification.json
@@ -8,8 +8,8 @@
     "target_count": 4,
     "adapter_count": 4,
     "archive_present": true,
-    "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e",
-    "archive_entry_count": 573,
+    "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe",
+    "archive_entry_count": 574,
     "failure_count": 0,
     "warning_count": 0
   },
diff --git a/reports/package_verification.md b/reports/package_verification.md
index b452b759..bc468a28 100644
--- a/reports/package_verification.md
+++ b/reports/package_verification.md
@@ -4,7 +4,7 @@
 - Package directory: `dist`
 - Targets: `4 / 4` adapters present
 - Archive present: `True`
-- Archive SHA256: `8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e`
+- Archive SHA256: `76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe`
 - Failures: `0`
 - Warnings: `0`
 
diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json
index 850f303b..0b4f6d3b 100644
--- a/reports/python_compatibility.json
+++ b/reports/python_compatibility.json
@@ -5,7 +5,7 @@
   "root": ".",
   "summary": {
     "target_python": "3.11",
-    "file_count": 156,
+    "file_count": 157,
     "issue_count": 0,
     "syntax_error_count": 0,
     "fstring_311_violation_count": 0,
@@ -562,6 +562,12 @@
       "issue_count": 0,
       "issues": []
     },
+    {
+      "path": "scripts/world_class_evidence_contract.py",
+      "ok": true,
+      "issue_count": 0,
+      "issues": []
+    },
     {
       "path": "scripts/yao.py",
       "ok": true,
diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md
index c9259ec3..cef6ad7d 100644
--- a/reports/python_compatibility.md
+++ b/reports/python_compatibility.md
@@ -6,7 +6,7 @@ Generated at: `2026-06-13`
 
 - decision: `pass`
 - target python: `3.11`
-- files scanned: `156`
+- files scanned: `157`
 - issues: `0`
 - syntax errors: `0`
 - f-string 3.11 violations: `0`
diff --git a/reports/registry_audit.json b/reports/registry_audit.json
index 37ce36e5..91979125 100644
--- a/reports/registry_audit.json
+++ b/reports/registry_audit.json
@@ -21,8 +21,8 @@
     "trust_level": "local",
     "license": "MIT",
     "checksums": {
-      "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c",
-      "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e"
+      "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb",
+      "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe"
     },
     "compatibility": {
       "openai": "pass",
@@ -53,16 +53,16 @@
     },
     "distribution": {
       "archive_verified": true,
-      "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e",
+      "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe",
       "package_verification": "reports/package_verification.json",
       "install_simulated": true,
       "install_simulation": "reports/install_simulation.json"
     },
-    "generated_at": "2026-06-14"
+    "generated_at": "2026-06-13"
   },
   "index": {
     "schema_version": "2.0",
-    "generated_at": "2026-06-14",
+    "generated_at": "2026-06-13",
     "package_count": 1,
     "packages": [
       {
@@ -78,7 +78,7 @@
           "vscode"
         ],
         "package_metadata": "registry/packages/yao-meta-skill.json",
-        "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+        "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
       }
     ]
   },
diff --git a/reports/registry_audit.md b/reports/registry_audit.md
index f17044fd..777807a0 100644
--- a/reports/registry_audit.md
+++ b/reports/registry_audit.md
@@ -6,8 +6,8 @@
 - Maturity: `governed`
 - Owner: `Yao Team`
 - License: `MIT`
-- Package SHA256: `08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c`
-- Archive SHA256: `8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e`
+- Package SHA256: `c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb`
+- Archive SHA256: `76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe`
 - Install simulated: `True`
 
 ## Compatibility
diff --git a/reports/review-studio.html b/reports/review-studio.html
index 0f9bd02c..8d61ee49 100644
--- a/reports/review-studio.html
+++ b/reports/review-studio.html
@@ -434,12 +434,12 @@
 
     <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>Blueprint</span><strong>20/20</strong><p>2.0 coverage; 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>94 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>156 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>899 largest lines; 34 CLI handlers</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>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>73 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>573 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>Blueprint</span><strong>20/20</strong><p>2.0 coverage; 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>95 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>157 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>899 largest lines; 34 CLI handlers</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>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>73 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>574 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 944/1000; quality density 137.7</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; 94 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; 156 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>153 Python files; 0 hotspots; 0 blockers; largest 899 lines; 34 CLI handlers</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</p><footer>reports/adoption_drift_report.json <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; 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 944/1000; quality density 137.7</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; 95 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; 157 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>154 Python files; 0 hotspots; 0 blockers; largest 899 lines; 34 CLI handlers</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</p><footer>reports/adoption_drift_report.json <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; 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">
@@ -506,12 +506,12 @@
     </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>94</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>08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c</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>95</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>c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb</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>
 
     <section class="twocol">
-      <div class="panel"><h2>Python 兼容</h2><dl class='kv-grid'><div><dt>目标 Python</dt><dd>3.11</dd></div><div><dt>文件数</dt><dd>156</dd></div><div><dt>问题数</dt><dd>0</dd></div><div><dt>语法错误</dt><dd>0</dd></div><div><dt>F-string 3.11</dt><dd>0</dd></div></dl></div>
+      <div class="panel"><h2>Python 兼容</h2><dl class='kv-grid'><div><dt>目标 Python</dt><dd>3.11</dd></div><div><dt>文件数</dt><dd>157</dd></div><div><dt>问题数</dt><dd>0</dd></div><div><dt>语法错误</dt><dd>0</dd></div><div><dt>F-string 3.11</dt><dd>0</dd></div></dl></div>
       <div class="panel"><h2>解释器边界</h2><p>CI 和发布审查以 Python 3.11 兼容为底线；本地更高版本允许的新语法不能绕过兼容门禁。</p></div>
     </section>
 
@@ -574,12 +574,12 @@
 
     <section id="registry" class="twocol">
       <div class="panel"><h2>注册审计</h2><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p></div>
-      <div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e</code></dd></div></dl></div>
+      <div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe</code></dd></div></dl></div>
     </section>
 
     <section id="release" class="twocol">
       <div class="panel"><h2>发布路线</h2><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p></div>
-      <div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>573</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e</code></dd></div></dl></div>
+      <div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>574</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe</code></dd></div></dl></div>
     </section>
 
     <section class="twocol">
diff --git a/reports/review-studio.json b/reports/review-studio.json
index 9aa86fd3..9d0e3fd3 100644
--- a/reports/review-studio.json
+++ b/reports/review-studio.json
@@ -59,7 +59,7 @@
       "key": "trust-report",
       "label": "信任报告",
       "status": "pass",
-      "detail": "0 secrets; 94 scripts; 3 network-capable scripts; 0 help smoke failures",
+      "detail": "0 secrets; 95 scripts; 3 network-capable scripts; 0 help smoke failures",
       "evidence": "reports/security_trust_report.json",
       "link": "security_trust_report.md"
     },
@@ -67,7 +67,7 @@
       "key": "python-compat",
       "label": "Python 兼容",
       "status": "pass",
-      "detail": "Python 3.11; 156 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
+      "detail": "Python 3.11; 157 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
       "evidence": "reports/python_compatibility.json",
       "link": "python_compatibility.md"
     },
@@ -75,7 +75,7 @@
       "key": "architecture-maintainability",
       "label": "架构维护",
       "status": "pass",
-      "detail": "153 Python files; 0 hotspots; 0 blockers; largest 899 lines; 34 CLI handlers",
+      "detail": "154 Python files; 0 hotspots; 0 blockers; largest 899 lines; 34 CLI handlers",
       "evidence": "reports/architecture_maintainability.json",
       "link": "architecture_maintainability.md"
     },
@@ -851,7 +851,7 @@
             "path": "scripts",
             "label": "Deterministic helpers or local tooling",
             "kind": "folder",
-            "file_count": 94
+            "file_count": 95
           },
           {
             "path": "evals",
@@ -866,7 +866,7 @@
             "file_count": 203
           }
         ],
-        "file_count": 361,
+        "file_count": 362,
         "folder_count": 4,
         "distribution": [
           {
@@ -891,7 +891,7 @@
           },
           {
             "label": "scripts",
-            "value": 94
+            "value": 95
           },
           {
             "label": "evals",
@@ -1020,7 +1020,7 @@
           "path": "scripts",
           "label": "Deterministic helpers or local tooling",
           "kind": "folder",
-          "file_count": 94
+          "file_count": 95
         },
         {
           "path": "evals",
@@ -1349,9 +1349,9 @@
           "world_class_task_count": 4,
           "world_class_ledger_pending_count": 4,
           "working_tree_dirty": true,
-          "changed_file_count": 45
+          "changed_file_count": 50
         },
-        "commit": "bd7f1d8cccbebac1222c0ee7bbc01c1e3b991126",
+        "commit": "48f2826b8c9ebad3a9cc90e6166f4fd253f98308",
         "missing_artifacts": [],
         "limitations": [
           "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
@@ -1434,9 +1434,9 @@
         "failures": []
       },
       "trust_security": {
-        "scanned_files": 178,
-        "script_count": 94,
-        "internal_module_count": 17,
+        "scanned_files": 179,
+        "script_count": 95,
+        "internal_module_count": 18,
         "secret_findings": 0,
         "dependency_files": [
           "requirements-ci.txt"
@@ -1454,8 +1454,8 @@
         "help_smoke_failed_count": 0,
         "interactive_script_count": 0,
         "package_hash_scope": "source-contract-without-generated-reports",
-        "package_hash_file_count": 178,
-        "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+        "package_hash_file_count": 179,
+        "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
       },
       "skill_atlas": {
         "skill_count": 12,
@@ -1493,8 +1493,8 @@
           "trust_level": "local",
           "license": "MIT",
           "checksums": {
-            "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c",
-            "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e"
+            "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb",
+            "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe"
           },
           "compatibility": {
             "openai": "pass",
@@ -1525,12 +1525,12 @@
           },
           "distribution": {
             "archive_verified": true,
-            "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e",
+            "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe",
             "package_verification": "reports/package_verification.json",
             "install_simulated": true,
             "install_simulation": "reports/install_simulation.json"
           },
-          "generated_at": "2026-06-14"
+          "generated_at": "2026-06-13"
         },
         "failures": [],
         "warnings": []
@@ -1541,8 +1541,8 @@
           "target_count": 4,
           "adapter_count": 4,
           "archive_present": true,
-          "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e",
-          "archive_entry_count": 573,
+          "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe",
+          "archive_entry_count": 574,
           "failure_count": 0,
           "warning_count": 0
         },
@@ -1553,7 +1553,7 @@
         "ok": true,
         "summary": {
           "archive_present": true,
-          "archive_entry_count": 573,
+          "archive_entry_count": 574,
           "archive_extracted": true,
           "entrypoint_loaded": true,
           "manifest_loaded": true,
@@ -1620,12 +1620,12 @@
             {
               "field": "archive_sha256",
               "from": "",
-              "to": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e"
+              "to": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe"
             },
             {
               "field": "package_sha256",
               "from": "0000000000000000000000000000000000000000000000000000000000000000",
-              "to": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+              "to": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
             }
           ]
         },
@@ -1745,7 +1745,10 @@
         "summary": {
           "audit_decision": "continue-iteration",
           "world_class_ready": false,
+          "audit_world_class_ready": false,
           "ready_to_claim_world_class": false,
+          "ledger_completion_required": true,
+          "evidence_requirement_count": 4,
           "task_count": 4,
           "human_task_count": 1,
           "external_task_count": 3,
@@ -1920,6 +1923,7 @@
         "ok": true,
         "summary": {
           "ledger_entry_count": 4,
+          "source_accepted_count": 0,
           "accepted_count": 0,
           "pending_count": 4,
           "human_pending_count": 1,
@@ -1928,6 +1932,7 @@
           "missing_submission_count": 4,
           "invalid_submission_count": 0,
           "submitted_but_pending_count": 0,
+          "source_accepted_without_valid_submission_count": 0,
           "overclaim_guard_active": true,
           "ready_to_claim_world_class": false,
           "decision": "evidence-pending"
@@ -1940,6 +1945,7 @@
             "owner": "operator with provider credentials",
             "status": "pending",
             "source_status": "external_required",
+            "source_accepted": false,
             "current": "model-executed 0; token-observed 0",
             "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
             "provenance_requirements": [
@@ -1995,6 +2001,7 @@
             "owner": "human reviewer",
             "status": "pending",
             "source_status": "human_required",
+            "source_accepted": false,
             "current": "0/5 decisions; pending 5",
             "objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
             "provenance_requirements": [
@@ -2054,6 +2061,7 @@
             "owner": "target client or installer integrator",
             "status": "pending",
             "source_status": "external_required",
+            "source_accepted": false,
             "current": "native-enforced targets 0; installer-enforced targets 4",
             "objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
             "provenance_requirements": [
@@ -2116,6 +2124,7 @@
             "owner": "Browser/Chrome/IDE/provider client integrator",
             "status": "pending",
             "source_status": "external_required",
+            "source_accepted": false,
             "current": "external source events 0; adoption samples 1",
             "objective": "Import production metadata-only events from a real external client into the local drift loop.",
             "provenance_requirements": [
@@ -2169,7 +2178,8 @@
         "source_plan": {
           "json": "reports/world_class_evidence_plan.json",
           "markdown": "reports/world_class_evidence_plan.md",
-          "task_count": 4
+          "task_count": 4,
+          "evidence_requirement_count": 4
         }
       },
       "synthesis_highlights": [
@@ -3794,7 +3804,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 24.72,
+          "duration_ms": 28.38,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3822,7 +3832,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 23.92,
+          "duration_ms": 27.21,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3845,7 +3855,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 24.18,
+          "duration_ms": 27.7,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3873,7 +3883,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 25.49,
+          "duration_ms": 27.35,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3896,7 +3906,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 24.68,
+          "duration_ms": 28.38,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3924,7 +3934,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 24.46,
+          "duration_ms": 28.65,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3947,7 +3957,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 24.04,
+          "duration_ms": 28.6,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3974,7 +3984,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 24.01,
+          "duration_ms": 27.75,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3997,7 +4007,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 23.99,
+          "duration_ms": 27.86,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4026,7 +4036,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 24.34,
+          "duration_ms": 27.32,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4866,7 +4876,7 @@
           "label": "Trust Security",
           "status": "pass",
           "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
-          "current": "94 scripts; secrets 0; help failures 0",
+          "current": "95 scripts; secrets 0; help failures 0",
           "command": "python3 scripts/yao.py trust .",
           "test": "python3 tests/verify_trust_check.py",
           "evidence": [
@@ -4940,7 +4950,7 @@
           "label": "Registry Distribution",
           "status": "pass",
           "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
-          "current": "archive entries 573; install failures 0",
+          "current": "archive entries 574; install failures 0",
           "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .",
           "test": "python3 tests/verify_registry_audit.py",
           "evidence": [
@@ -5361,7 +5371,7 @@
     "compiled_targets": {
       "schema_version": "1.0",
       "ok": true,
-      "generated_at": "2026-06-14",
+      "generated_at": "2026-06-13",
       "skill_dir": ".",
       "summary": {
         "target_count": 5,
@@ -10221,9 +10231,9 @@
       "ok": true,
       "skill_dir": ".",
       "summary": {
-        "scanned_files": 178,
-        "script_count": 94,
-        "internal_module_count": 17,
+        "scanned_files": 179,
+        "script_count": 95,
+        "internal_module_count": 18,
         "secret_findings": 0,
         "dependency_files": [
           "requirements-ci.txt"
@@ -10241,8 +10251,8 @@
         "help_smoke_failed_count": 0,
         "interactive_script_count": 0,
         "package_hash_scope": "source-contract-without-generated-reports",
-        "package_hash_file_count": 178,
-        "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+        "package_hash_file_count": 179,
+        "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
       },
       "failures": [],
       "warnings": [],
@@ -11483,6 +11493,20 @@
           "network_urls": [],
           "network_hosts": []
         },
+        {
+          "path": "scripts/world_class_evidence_contract.py",
+          "interface": "internal-module",
+          "interface_declared": true,
+          "interface_reason": "Imported by world-class evidence reports to share intake validation and artifact integrity checks.",
+          "has_argparse": false,
+          "has_main_guard": false,
+          "uses_input": false,
+          "uses_network": false,
+          "uses_file_write": false,
+          "uses_subprocess": false,
+          "network_urls": [],
+          "network_hosts": []
+        },
         {
           "path": "scripts/yao.py",
           "interface": "cli",
@@ -11616,7 +11640,7 @@
         "checked_count": 77,
         "passed_count": 77,
         "failed_count": 0,
-        "skipped_count": 17,
+        "skipped_count": 18,
         "failed_scripts": [],
         "results": [
           {
@@ -12435,6 +12459,10 @@
             "path": "scripts/skill_report_model.py",
             "reason": "internal module"
           },
+          {
+            "path": "scripts/world_class_evidence_contract.py",
+            "reason": "internal module"
+          },
           {
             "path": "scripts/yao_cli_config.py",
             "reason": "internal module"
@@ -12644,7 +12672,7 @@
       "root": ".",
       "summary": {
         "target_python": "3.11",
-        "file_count": 156,
+        "file_count": 157,
         "issue_count": 0,
         "syntax_error_count": 0,
         "fstring_311_violation_count": 0,
@@ -13201,6 +13229,12 @@
           "issue_count": 0,
           "issues": []
         },
+        {
+          "path": "scripts/world_class_evidence_contract.py",
+          "ok": true,
+          "issue_count": 0,
+          "issues": []
+        },
         {
           "path": "scripts/yao.py",
           "ok": true,
@@ -13610,10 +13644,10 @@
       "generated_at": "2026-06-13",
       "skill_dir": ".",
       "summary": {
-        "python_file_count": 153,
-        "script_file_count": 94,
+        "python_file_count": 154,
+        "script_file_count": 95,
         "test_file_count": 59,
-        "internal_module_count": 19,
+        "internal_module_count": 20,
         "cli_script_count": 76,
         "command_handler_count": 34,
         "warn_line_threshold": 900,
@@ -13724,10 +13758,10 @@
         "context_budget_tier": "production",
         "context_budget_limit": 1000,
         "skill_body_tokens": 751,
-        "other_text_tokens": 1178333,
+        "other_text_tokens": 1183524,
         "estimated_initial_load_tokens": 944,
-        "estimated_total_text_tokens": 1179084,
-        "relevant_file_count": 498,
+        "estimated_total_text_tokens": 1184275,
+        "relevant_file_count": 500,
         "unused_resource_dirs": [],
         "quality_signal_points": 130,
         "quality_density": 137.7
@@ -14678,6 +14712,7 @@
               "scripts/upgrade_check.py",
               "scripts/validate_skill.py",
               "scripts/verify_package.py",
+              "scripts/world_class_evidence_contract.py",
               "scripts/yao.py",
               "scripts/yao_cli_config.py",
               "scripts/yao_cli_create_commands.py",
@@ -15580,7 +15615,7 @@
     "adoption_drift": {
       "ok": true,
       "schema_version": "2.0",
-      "generated_at": "2026-06-14T00:32:04Z",
+      "generated_at": "2026-06-14T00:50:30Z",
       "skill_dir": ".",
       "privacy_contract": {
         "storage": "local-first",
@@ -15768,10 +15803,11 @@
     "world_class_evidence_ledger": {
       "schema_version": "1.0",
       "ok": true,
-      "generated_at": "2026-06-14",
+      "generated_at": "2026-06-13",
       "skill_dir": ".",
       "summary": {
         "ledger_entry_count": 4,
+        "source_accepted_count": 0,
         "accepted_count": 0,
         "pending_count": 4,
         "human_pending_count": 1,
@@ -15780,6 +15816,7 @@
         "missing_submission_count": 4,
         "invalid_submission_count": 0,
         "submitted_but_pending_count": 0,
+        "source_accepted_without_valid_submission_count": 0,
         "overclaim_guard_active": true,
         "ready_to_claim_world_class": false,
         "decision": "evidence-pending"
@@ -15792,6 +15829,7 @@
           "owner": "operator with provider credentials",
           "status": "pending",
           "source_status": "external_required",
+          "source_accepted": false,
           "current": "model-executed 0; token-observed 0",
           "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
           "provenance_requirements": [
@@ -15847,6 +15885,7 @@
           "owner": "human reviewer",
           "status": "pending",
           "source_status": "human_required",
+          "source_accepted": false,
           "current": "0/5 decisions; pending 5",
           "objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
           "provenance_requirements": [
@@ -15906,6 +15945,7 @@
           "owner": "target client or installer integrator",
           "status": "pending",
           "source_status": "external_required",
+          "source_accepted": false,
           "current": "native-enforced targets 0; installer-enforced targets 4",
           "objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
           "provenance_requirements": [
@@ -15968,6 +16008,7 @@
           "owner": "Browser/Chrome/IDE/provider client integrator",
           "status": "pending",
           "source_status": "external_required",
+          "source_accepted": false,
           "current": "external source events 0; adoption samples 1",
           "objective": "Import production metadata-only events from a real external client into the local drift loop.",
           "provenance_requirements": [
@@ -16021,11 +16062,13 @@
       "source_plan": {
         "json": "reports/world_class_evidence_plan.json",
         "markdown": "reports/world_class_evidence_plan.md",
-        "task_count": 4
+        "task_count": 4,
+        "evidence_requirement_count": 4
       },
       "submissions": {
         "directory": "evidence/world_class/submissions",
-        "ledger_counts_submission_as_completion": false
+        "ledger_counts_submission_as_completion": false,
+        "source_pass_requires_valid_submission": true
       },
       "artifacts": {
         "json": "reports/world_class_evidence_ledger.json",
@@ -16036,7 +16079,7 @@
     "world_class_evidence_intake": {
       "schema_version": "1.0",
       "ok": true,
-      "generated_at": "2026-06-14",
+      "generated_at": "2026-06-13",
       "skill_dir": ".",
       "summary": {
         "schema_present": true,
@@ -16330,7 +16373,7 @@
     "world_class_submission_review": {
       "schema_version": "1.0",
       "ok": true,
-      "generated_at": "2026-06-14",
+      "generated_at": "2026-06-13",
       "skill_dir": ".",
       "summary": {
         "review_item_count": 4,
@@ -16506,7 +16549,7 @@
     "world_class_operator_runbook": {
       "schema_version": "1.0",
       "ok": true,
-      "generated_at": "2026-06-14",
+      "generated_at": "2026-06-13",
       "skill_dir": ".",
       "summary": {
         "evidence_item_count": 4,
@@ -16825,7 +16868,7 @@
     "world_class_claim_guard": {
       "schema_version": "1.0",
       "ok": true,
-      "generated_at": "2026-06-14",
+      "generated_at": "2026-06-13",
       "skill_dir": ".",
       "summary": {
         "ledger_ready_to_claim_world_class": false,
@@ -17189,8 +17232,8 @@
         "trust_level": "local",
         "license": "MIT",
         "checksums": {
-          "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c",
-          "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e"
+          "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb",
+          "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe"
         },
         "compatibility": {
           "openai": "pass",
@@ -17221,16 +17264,16 @@
         },
         "distribution": {
           "archive_verified": true,
-          "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e",
+          "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe",
           "package_verification": "reports/package_verification.json",
           "install_simulated": true,
           "install_simulation": "reports/install_simulation.json"
         },
-        "generated_at": "2026-06-14"
+        "generated_at": "2026-06-13"
       },
       "index": {
         "schema_version": "2.0",
-        "generated_at": "2026-06-14",
+        "generated_at": "2026-06-13",
         "package_count": 1,
         "packages": [
           {
@@ -17246,7 +17289,7 @@
               "vscode"
             ],
             "package_metadata": "registry/packages/yao-meta-skill.json",
-            "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+            "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
           }
         ]
       },
@@ -17269,8 +17312,8 @@
         "target_count": 4,
         "adapter_count": 4,
         "archive_present": true,
-        "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e",
-        "archive_entry_count": 573,
+        "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe",
+        "archive_entry_count": 574,
         "failure_count": 0,
         "warning_count": 0
       },
@@ -17928,14 +17971,14 @@
     "install_simulation": {
       "ok": true,
       "schema_version": "2.0",
-      "generated_at": "2026-06-14",
+      "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": 573,
+        "archive_entry_count": 574,
         "archive_extracted": true,
         "entrypoint_loaded": true,
         "manifest_loaded": true,
@@ -17953,7 +17996,7 @@
         {
           "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",
@@ -18199,16 +18242,16 @@
       "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": "2026-06-14",
+      "generated_at": "2026-06-13",
       "previous": {
         "name": "yao-meta-skill",
         "version": "1.0.0",
@@ -18277,12 +18320,12 @@
           {
             "field": "archive_sha256",
             "from": "",
-            "to": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e"
+            "to": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe"
           },
           {
             "field": "package_sha256",
             "from": "0000000000000000000000000000000000000000000000000000000000000000",
-            "to": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+            "to": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
           }
         ]
       },
@@ -18297,8 +18340,8 @@
       "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/security_trust_report.json b/reports/security_trust_report.json
index 0f475ac5..bcabbe82 100644
--- a/reports/security_trust_report.json
+++ b/reports/security_trust_report.json
@@ -2,9 +2,9 @@
   "ok": true,
   "skill_dir": ".",
   "summary": {
-    "scanned_files": 178,
-    "script_count": 94,
-    "internal_module_count": 17,
+    "scanned_files": 179,
+    "script_count": 95,
+    "internal_module_count": 18,
     "secret_findings": 0,
     "dependency_files": [
       "requirements-ci.txt"
@@ -22,8 +22,8 @@
     "help_smoke_failed_count": 0,
     "interactive_script_count": 0,
     "package_hash_scope": "source-contract-without-generated-reports",
-    "package_hash_file_count": 178,
-    "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+    "package_hash_file_count": 179,
+    "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
   },
   "failures": [],
   "warnings": [],
@@ -1264,6 +1264,20 @@
       "network_urls": [],
       "network_hosts": []
     },
+    {
+      "path": "scripts/world_class_evidence_contract.py",
+      "interface": "internal-module",
+      "interface_declared": true,
+      "interface_reason": "Imported by world-class evidence reports to share intake validation and artifact integrity checks.",
+      "has_argparse": false,
+      "has_main_guard": false,
+      "uses_input": false,
+      "uses_network": false,
+      "uses_file_write": false,
+      "uses_subprocess": false,
+      "network_urls": [],
+      "network_hosts": []
+    },
     {
       "path": "scripts/yao.py",
       "interface": "cli",
@@ -1397,7 +1411,7 @@
     "checked_count": 77,
     "passed_count": 77,
     "failed_count": 0,
-    "skipped_count": 17,
+    "skipped_count": 18,
     "failed_scripts": [],
     "results": [
       {
@@ -2216,6 +2230,10 @@
         "path": "scripts/skill_report_model.py",
         "reason": "internal module"
       },
+      {
+        "path": "scripts/world_class_evidence_contract.py",
+        "reason": "internal module"
+      },
       {
         "path": "scripts/yao_cli_config.py",
         "reason": "internal module"
diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md
index 4033f209..47ec8a56 100644
--- a/reports/security_trust_report.md
+++ b/reports/security_trust_report.md
@@ -1,9 +1,9 @@
 # Security Trust Report
 
 - OK: `True`
-- Scanned files: `178`
-- Scripts: `94`
-- Internal script modules: `17`
+- Scanned files: `179`
+- Scripts: `95`
+- Internal script modules: `18`
 - Secret findings: `0`
 - Network-capable scripts: `3`
 - Network policy covered scripts: `3`
@@ -15,8 +15,8 @@
 - CLI help smoke failures: `0`
 - Interactive scripts: `0`
 - Package hash scope: `source-contract-without-generated-reports`
-- Package hash files: `178`
-- Package SHA256: `08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c`
+- Package hash files: `179`
+- Package SHA256: `c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb`
 
 ## Failures
 
@@ -149,6 +149,7 @@
 | scripts/upgrade_check.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
 | scripts/validate_skill.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
 | scripts/verify_package.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
+| scripts/world_class_evidence_contract.py | internal-module | True | False | False | False | False | False | False | Imported by world-class evidence reports to share intake validation and artifact integrity checks. |
 | scripts/yao.py | cli | False | True | True | False | False | False | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
 | scripts/yao_cli_config.py | internal-module | True | False | False | False | False | False | False | Imported by yao.py for CLI target maps and side-effect-free shaping helpers. |
 | scripts/yao_cli_create_commands.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep skill creation and quickstart command handlers out of the CLI orchestrator. |
diff --git a/reports/skill-overview.html b/reports/skill-overview.html
index edee53be..68891621 100644
--- a/reports/skill-overview.html
+++ b/reports/skill-overview.html
@@ -771,7 +771,7 @@
           <p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
         </div>
         <div class="two-col">
-          <figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text x="20" y="30" class="chart-title">资产分布</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-0.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-1.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-2.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="24.6 75.4" stroke-dashoffset="-3.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="72.3 27.7" stroke-dashoffset="-27.7" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">361项</text><text x="235" y="78">SKILL.md</text><text x="235" y="100">README.md</text><text x="235" y="122">agents/interface.yaml</text><text x="235" y="144">manifest.json</text><text x="235" y="166">references</text><text x="235" y="188">scripts</text></svg><figcaption>资产分布图展示当前包体的文件和目录重心。</figcaption></figure>
+          <figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text x="20" y="30" class="chart-title">资产分布</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-0.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-1.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-2.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="24.4 75.6" stroke-dashoffset="-3.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="72.5 27.5" stroke-dashoffset="-27.5" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">362项</text><text x="235" y="78">SKILL.md</text><text x="235" y="100">README.md</text><text x="235" y="122">agents/interface.yaml</text><text x="235" y="144">manifest.json</text><text x="235" y="166">references</text><text x="235" y="188">scripts</text></svg><figcaption>资产分布图展示当前包体的文件和目录重心。</figcaption></figure>
           <table>
             <thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
             <tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
diff --git a/reports/skill-overview.json b/reports/skill-overview.json
index fd317a77..2ea2e2f2 100644
--- a/reports/skill-overview.json
+++ b/reports/skill-overview.json
@@ -437,7 +437,7 @@
         "path": "scripts",
         "label": "Deterministic helpers or local tooling",
         "kind": "folder",
-        "file_count": 94
+        "file_count": 95
       },
       {
         "path": "evals",
@@ -452,7 +452,7 @@
         "file_count": 203
       }
     ],
-    "file_count": 361,
+    "file_count": 362,
     "folder_count": 4,
     "distribution": [
       {
@@ -477,7 +477,7 @@
       },
       {
         "label": "scripts",
-        "value": 94
+        "value": 95
       },
       {
         "label": "evals",
@@ -606,7 +606,7 @@
       "path": "scripts",
       "label": "Deterministic helpers or local tooling",
       "kind": "folder",
-      "file_count": 94
+      "file_count": 95
     },
     {
       "path": "evals",
@@ -935,9 +935,9 @@
       "world_class_task_count": 4,
       "world_class_ledger_pending_count": 4,
       "working_tree_dirty": true,
-      "changed_file_count": 45
+      "changed_file_count": 50
     },
-    "commit": "bd7f1d8cccbebac1222c0ee7bbc01c1e3b991126",
+    "commit": "48f2826b8c9ebad3a9cc90e6166f4fd253f98308",
     "missing_artifacts": [],
     "limitations": [
       "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
@@ -1020,9 +1020,9 @@
     "failures": []
   },
   "trust_security": {
-    "scanned_files": 178,
-    "script_count": 94,
-    "internal_module_count": 17,
+    "scanned_files": 179,
+    "script_count": 95,
+    "internal_module_count": 18,
     "secret_findings": 0,
     "dependency_files": [
       "requirements-ci.txt"
@@ -1040,8 +1040,8 @@
     "help_smoke_failed_count": 0,
     "interactive_script_count": 0,
     "package_hash_scope": "source-contract-without-generated-reports",
-    "package_hash_file_count": 178,
-    "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+    "package_hash_file_count": 179,
+    "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
   },
   "skill_atlas": {
     "skill_count": 12,
@@ -1079,8 +1079,8 @@
       "trust_level": "local",
       "license": "MIT",
       "checksums": {
-        "package_sha256": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c",
-        "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e"
+        "package_sha256": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb",
+        "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe"
       },
       "compatibility": {
         "openai": "pass",
@@ -1111,12 +1111,12 @@
       },
       "distribution": {
         "archive_verified": true,
-        "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e",
+        "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe",
         "package_verification": "reports/package_verification.json",
         "install_simulated": true,
         "install_simulation": "reports/install_simulation.json"
       },
-      "generated_at": "2026-06-14"
+      "generated_at": "2026-06-13"
     },
     "failures": [],
     "warnings": []
@@ -1127,8 +1127,8 @@
       "target_count": 4,
       "adapter_count": 4,
       "archive_present": true,
-      "archive_sha256": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e",
-      "archive_entry_count": 573,
+      "archive_sha256": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe",
+      "archive_entry_count": 574,
       "failure_count": 0,
       "warning_count": 0
     },
@@ -1139,7 +1139,7 @@
     "ok": true,
     "summary": {
       "archive_present": true,
-      "archive_entry_count": 573,
+      "archive_entry_count": 574,
       "archive_extracted": true,
       "entrypoint_loaded": true,
       "manifest_loaded": true,
@@ -1206,12 +1206,12 @@
         {
           "field": "archive_sha256",
           "from": "",
-          "to": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e"
+          "to": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe"
         },
         {
           "field": "package_sha256",
           "from": "0000000000000000000000000000000000000000000000000000000000000000",
-          "to": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+          "to": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
         }
       ]
     },
@@ -1331,7 +1331,10 @@
     "summary": {
       "audit_decision": "continue-iteration",
       "world_class_ready": false,
+      "audit_world_class_ready": false,
       "ready_to_claim_world_class": false,
+      "ledger_completion_required": true,
+      "evidence_requirement_count": 4,
       "task_count": 4,
       "human_task_count": 1,
       "external_task_count": 3,
@@ -1506,6 +1509,7 @@
     "ok": true,
     "summary": {
       "ledger_entry_count": 4,
+      "source_accepted_count": 0,
       "accepted_count": 0,
       "pending_count": 4,
       "human_pending_count": 1,
@@ -1514,6 +1518,7 @@
       "missing_submission_count": 4,
       "invalid_submission_count": 0,
       "submitted_but_pending_count": 0,
+      "source_accepted_without_valid_submission_count": 0,
       "overclaim_guard_active": true,
       "ready_to_claim_world_class": false,
       "decision": "evidence-pending"
@@ -1526,6 +1531,7 @@
         "owner": "operator with provider credentials",
         "status": "pending",
         "source_status": "external_required",
+        "source_accepted": false,
         "current": "model-executed 0; token-observed 0",
         "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
         "provenance_requirements": [
@@ -1581,6 +1587,7 @@
         "owner": "human reviewer",
         "status": "pending",
         "source_status": "human_required",
+        "source_accepted": false,
         "current": "0/5 decisions; pending 5",
         "objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
         "provenance_requirements": [
@@ -1640,6 +1647,7 @@
         "owner": "target client or installer integrator",
         "status": "pending",
         "source_status": "external_required",
+        "source_accepted": false,
         "current": "native-enforced targets 0; installer-enforced targets 4",
         "objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
         "provenance_requirements": [
@@ -1702,6 +1710,7 @@
         "owner": "Browser/Chrome/IDE/provider client integrator",
         "status": "pending",
         "source_status": "external_required",
+        "source_accepted": false,
         "current": "external source events 0; adoption samples 1",
         "objective": "Import production metadata-only events from a real external client into the local drift loop.",
         "provenance_requirements": [
@@ -1755,7 +1764,8 @@
     "source_plan": {
       "json": "reports/world_class_evidence_plan.json",
       "markdown": "reports/world_class_evidence_plan.md",
-      "task_count": 4
+      "task_count": 4,
+      "evidence_requirement_count": 4
     }
   },
   "synthesis_highlights": [
diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json
index 09f7c547..d7f86aec 100644
--- a/reports/skill_atlas.json
+++ b/reports/skill_atlas.json
@@ -151,6 +151,7 @@
           "scripts/upgrade_check.py",
           "scripts/validate_skill.py",
           "scripts/verify_package.py",
+          "scripts/world_class_evidence_contract.py",
           "scripts/yao.py",
           "scripts/yao_cli_config.py",
           "scripts/yao_cli_create_commands.py",
diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json
index d085c79e..a96090b4 100644
--- a/reports/skill_os2_audit.json
+++ b/reports/skill_os2_audit.json
@@ -197,7 +197,7 @@
       "key": "trust-security",
       "label": "Trust Security",
       "status": "pass",
-      "current": "secrets 0; scripts 94; help failures 0",
+      "current": "secrets 0; scripts 95; help failures 0",
       "target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable",
       "evidence": [
         {
@@ -285,7 +285,7 @@
       "key": "registry-distribution",
       "label": "Registry Distribution",
       "status": "pass",
-      "current": "zip entries 573; install failures 0; permission failures 0",
+      "current": "zip entries 574; install failures 0; permission failures 0",
       "target": "Package metadata, archive checksum, package verification, and install simulation pass",
       "evidence": [
         {
diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md
index 1bed703e..b385bb16 100644
--- a/reports/skill_os2_audit.md
+++ b/reports/skill_os2_audit.md
@@ -23,11 +23,11 @@ Generated at: `2026-06-13`
 | Human Adjudication | human-required | 0/5 decisions; pending 5 | Real reviewer decisions recorded before claiming output review completion | Record real A/B choices in the decision template, then regenerate adjudication. |
 | Benchmark Reproducibility | pass | artifacts 24; missing 0; failures 3 | Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable | Keep the manifest current with every benchmark, package, and release evidence change. |
 | Runtime Conformance | pass | 5/5 targets pass | Target package structure, metadata, relative paths, and degradation notes pass | Keep target conformance fixtures updated as platform contracts change. |
-| Trust Security | pass | secrets 0; scripts 94; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. |
+| Trust Security | pass | secrets 0; scripts 95; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. |
 | Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. |
 | Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
 | Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. |
-| Registry Distribution | pass | zip entries 573; 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. |
+| Registry Distribution | pass | zip entries 574; 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 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. |
diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json
index 7f768f25..45e97363 100644
--- a/reports/skill_os2_coverage.json
+++ b/reports/skill_os2_coverage.json
@@ -122,7 +122,7 @@
       "label": "Trust Security",
       "status": "pass",
       "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
-      "current": "94 scripts; secrets 0; help failures 0",
+      "current": "95 scripts; secrets 0; help failures 0",
       "command": "python3 scripts/yao.py trust .",
       "test": "python3 tests/verify_trust_check.py",
       "evidence": [
@@ -196,7 +196,7 @@
       "label": "Registry Distribution",
       "status": "pass",
       "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
-      "current": "archive entries 573; install failures 0",
+      "current": "archive entries 574; install failures 0",
       "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .",
       "test": "python3 tests/verify_registry_audit.py",
       "evidence": [
diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md
index d60139bc..2a7ef08c 100644
--- a/reports/skill_os2_coverage.md
+++ b/reports/skill_os2_coverage.md
@@ -21,9 +21,9 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
 | Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` |
 | Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` |
 | Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` |
-| Trust Security | `pass` | 94 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
+| Trust Security | `pass` | 95 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
 | Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` |
-| Registry Distribution | `pass` | archive entries 573; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
+| Registry Distribution | `pass` | archive entries 574; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
 | Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` |
 | Telemetry Drift | `pass` | events 1; recipes 5; risk low | `python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .` | `python3 tests/verify_telemetry_hooks.py` |
 
diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json
index e40544d3..4b80c227 100644
--- a/reports/upgrade_check.json
+++ b/reports/upgrade_check.json
@@ -1,7 +1,7 @@
 {
   "ok": true,
   "schema_version": "2.0",
-  "generated_at": "2026-06-14",
+  "generated_at": "2026-06-13",
   "previous": {
     "name": "yao-meta-skill",
     "version": "1.0.0",
@@ -70,12 +70,12 @@
       {
         "field": "archive_sha256",
         "from": "",
-        "to": "8d1c803b4008860c73b47f8abeed721877304521c2e2da11083aeb2e66ce156e"
+        "to": "76793bd367e9aaf6c25e6b11ac1139156950827bd87ba3dd8a1bdc883f7d70fe"
       },
       {
         "field": "package_sha256",
         "from": "0000000000000000000000000000000000000000000000000000000000000000",
-        "to": "08d744e0aa33d726b497ecdbdb6eaf2a5ec666a6ea3938068f6007be27f5021c"
+        "to": "c42643ea854dd90bb03ca607595f6a6b2c00118da64a78e8bdbb4392d7f204fb"
       }
     ]
   },
@@ -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_claim_guard.json b/reports/world_class_claim_guard.json
index 88dc21e5..edf4d040 100644
--- a/reports/world_class_claim_guard.json
+++ b/reports/world_class_claim_guard.json
@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-14",
+  "generated_at": "2026-06-13",
   "skill_dir": ".",
   "summary": {
     "ledger_ready_to_claim_world_class": false,
diff --git a/reports/world_class_claim_guard.md b/reports/world_class_claim_guard.md
index b3eaa58f..3318385b 100644
--- a/reports/world_class_claim_guard.md
+++ b/reports/world_class_claim_guard.md
@@ -1,6 +1,6 @@
 # World-Class Claim Guard
 
-Generated at: `2026-06-14`
+Generated at: `2026-06-13`
 
 ## Summary
 
diff --git a/reports/world_class_evidence_intake.json b/reports/world_class_evidence_intake.json
index 2cfe6e1e..356c6383 100644
--- a/reports/world_class_evidence_intake.json
+++ b/reports/world_class_evidence_intake.json
@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-14",
+  "generated_at": "2026-06-13",
   "skill_dir": ".",
   "summary": {
     "schema_present": true,
diff --git a/reports/world_class_evidence_intake.md b/reports/world_class_evidence_intake.md
index 04ebda85..4376838f 100644
--- a/reports/world_class_evidence_intake.md
+++ b/reports/world_class_evidence_intake.md
@@ -1,6 +1,6 @@
 # World-Class Evidence Intake
 
-Generated at: `2026-06-14`
+Generated at: `2026-06-13`
 
 ## Summary
 
diff --git a/reports/world_class_evidence_ledger.json b/reports/world_class_evidence_ledger.json
index efea089e..3225daee 100644
--- a/reports/world_class_evidence_ledger.json
+++ b/reports/world_class_evidence_ledger.json
@@ -1,10 +1,11 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-14",
+  "generated_at": "2026-06-13",
   "skill_dir": ".",
   "summary": {
     "ledger_entry_count": 4,
+    "source_accepted_count": 0,
     "accepted_count": 0,
     "pending_count": 4,
     "human_pending_count": 1,
@@ -13,6 +14,7 @@
     "missing_submission_count": 4,
     "invalid_submission_count": 0,
     "submitted_but_pending_count": 0,
+    "source_accepted_without_valid_submission_count": 0,
     "overclaim_guard_active": true,
     "ready_to_claim_world_class": false,
     "decision": "evidence-pending"
@@ -25,6 +27,7 @@
       "owner": "operator with provider credentials",
       "status": "pending",
       "source_status": "external_required",
+      "source_accepted": false,
       "current": "model-executed 0; token-observed 0",
       "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
       "provenance_requirements": [
@@ -80,6 +83,7 @@
       "owner": "human reviewer",
       "status": "pending",
       "source_status": "human_required",
+      "source_accepted": false,
       "current": "0/5 decisions; pending 5",
       "objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
       "provenance_requirements": [
@@ -139,6 +143,7 @@
       "owner": "target client or installer integrator",
       "status": "pending",
       "source_status": "external_required",
+      "source_accepted": false,
       "current": "native-enforced targets 0; installer-enforced targets 4",
       "objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
       "provenance_requirements": [
@@ -201,6 +206,7 @@
       "owner": "Browser/Chrome/IDE/provider client integrator",
       "status": "pending",
       "source_status": "external_required",
+      "source_accepted": false,
       "current": "external source events 0; adoption samples 1",
       "objective": "Import production metadata-only events from a real external client into the local drift loop.",
       "provenance_requirements": [
@@ -254,11 +260,13 @@
   "source_plan": {
     "json": "reports/world_class_evidence_plan.json",
     "markdown": "reports/world_class_evidence_plan.md",
-    "task_count": 4
+    "task_count": 4,
+    "evidence_requirement_count": 4
   },
   "submissions": {
     "directory": "evidence/world_class/submissions",
-    "ledger_counts_submission_as_completion": false
+    "ledger_counts_submission_as_completion": false,
+    "source_pass_requires_valid_submission": true
   },
   "artifacts": {
     "json": "reports/world_class_evidence_ledger.json",
diff --git a/reports/world_class_evidence_ledger.md b/reports/world_class_evidence_ledger.md
index e6b0f882..71d63aef 100644
--- a/reports/world_class_evidence_ledger.md
+++ b/reports/world_class_evidence_ledger.md
@@ -1,22 +1,24 @@
 # World-Class Evidence Ledger
 
-Generated at: `2026-06-14`
+Generated at: `2026-06-13`
 
 ## Summary
 
 - decision: `evidence-pending`
 - ready to claim world-class: `false`
 - entries: `4`
+- source accepted: `0`
 - accepted: `0`
 - pending: `4`
 - human pending: `1`
 - external pending: `3`
 - submitted entries: `0`
 - submitted but pending: `0`
+- source accepted without valid submission: `0`
 - invalid submissions: `0`
 - overclaim guard active: `true`
 
-This ledger records the current evidence state. It does not treat planned work, metadata fallback, pending review, or local command-runner output as world-class completion evidence.
+This ledger records the current evidence state. It requires both passing source evidence and a validated intake submission with artifact SHA-256 checks before accepting an item. It does not treat planned work, metadata fallback, pending review, or local command-runner output as world-class completion evidence.
 
 ## Ledger
 
diff --git a/reports/world_class_evidence_plan.json b/reports/world_class_evidence_plan.json
index ae80126b..47ea5508 100644
--- a/reports/world_class_evidence_plan.json
+++ b/reports/world_class_evidence_plan.json
@@ -1,12 +1,15 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-14",
+  "generated_at": "2026-06-13",
   "skill_dir": ".",
   "summary": {
     "audit_decision": "continue-iteration",
     "world_class_ready": false,
+    "audit_world_class_ready": false,
     "ready_to_claim_world_class": false,
+    "ledger_completion_required": true,
+    "evidence_requirement_count": 4,
     "task_count": 4,
     "human_task_count": 1,
     "external_task_count": 3,
@@ -171,6 +174,164 @@
       "audit_next_action": "Install a real client against the native host and import production metadata-only events."
     }
   ],
+  "evidence_requirements": [
+    {
+      "key": "provider-holdout",
+      "label": "Provider Holdout",
+      "status": "external_required",
+      "category": "external",
+      "owner": "operator with provider credentials",
+      "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",
+        "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 ."
+      ],
+      "success_checks": [
+        "reports/output_execution_runs.json summary.model_executed_count > 0",
+        "reports/output_execution_runs.json summary.timing_observed_count > 0",
+        "reports/output_execution_runs.json summary.token_observed_count > 0",
+        "reports/skill_os2_audit.json item provider-holdout status becomes pass"
+      ],
+      "evidence_artifacts": [
+        "reports/output_execution_runs.json",
+        "reports/output_execution_runs.md",
+        "reports/skill_os2_audit.json",
+        "evidence/world_class/intake.schema.json",
+        "evidence/world_class/templates/provider-holdout.intake.json",
+        "reports/world_class_evidence_intake.json",
+        "reports/world_class_evidence_intake.md"
+      ],
+      "privacy_contract": [
+        "Do not commit provider credentials or environment dumps.",
+        "The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
+      ],
+      "audit_next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
+    },
+    {
+      "key": "human-adjudication",
+      "label": "Human Adjudication",
+      "status": "human_required",
+      "category": "human",
+      "owner": "human reviewer",
+      "current": "0/5 decisions; pending 5",
+      "objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
+      "runbook": [
+        "python3 scripts/yao.py output-review-kit --write-template",
+        "Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
+        "python3 scripts/adjudicate_output_review.py --write-template",
+        "Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
+        "python3 scripts/yao.py output-review",
+        "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
+        "Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
+        "python3 scripts/yao.py world-class-intake ."
+      ],
+      "success_checks": [
+        "reports/output_review_adjudication.json summary.pending_count == 0",
+        "reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
+        "reports/output_review_adjudication.json summary.invalid_decision_count == 0",
+        "reports/skill_os2_audit.json item human-adjudication status becomes pass"
+      ],
+      "evidence_artifacts": [
+        "reports/output_blind_review_pack.md",
+        "reports/output_review_kit.md",
+        "reports/output_review_decisions.json",
+        "reports/output_review_adjudication.json",
+        "reports/output_review_adjudication.md",
+        "evidence/world_class/intake.schema.json",
+        "evidence/world_class/templates/human-adjudication.intake.json",
+        "reports/world_class_evidence_intake.json",
+        "reports/world_class_evidence_intake.md"
+      ],
+      "privacy_contract": [
+        "Reviewer decisions should not include raw user data or private customer detail.",
+        "Keep the answer key separate until after decisions are recorded."
+      ],
+      "audit_next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
+    },
+    {
+      "key": "native-permission-enforcement",
+      "label": "Native Permission Enforcement",
+      "status": "external_required",
+      "category": "external",
+      "owner": "target client or installer integrator",
+      "current": "native-enforced targets 0; installer-enforced targets 4",
+      "objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
+      "runbook": [
+        "Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
+        "Update the generated target adapter only when the guard is actually enforced by that target.",
+        "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
+        "python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
+        "python3 scripts/yao.py runtime-permissions . --package-dir dist",
+        "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
+        "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.",
+        "python3 scripts/yao.py world-class-intake ."
+      ],
+      "success_checks": [
+        "reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
+        "reports/runtime_permission_probes.json summary.failure_count == 0",
+        "reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
+        "reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
+      ],
+      "evidence_artifacts": [
+        "dist/targets/*/adapter.json",
+        "reports/runtime_permission_probes.json",
+        "reports/runtime_permission_probes.md",
+        "reports/install_simulation.json",
+        "reports/install_simulation.md",
+        "security/permission_policy.json",
+        "evidence/world_class/intake.schema.json",
+        "evidence/world_class/templates/native-permission-enforcement.intake.json",
+        "reports/world_class_evidence_intake.json",
+        "reports/world_class_evidence_intake.md"
+      ],
+      "privacy_contract": [
+        "Do not mark native_enforcement true for metadata-only fallbacks.",
+        "Keep residual risks visible for targets that still rely on operator enforcement."
+      ],
+      "audit_next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
+    },
+    {
+      "key": "native-client-telemetry",
+      "label": "Native Client Telemetry",
+      "status": "external_required",
+      "category": "external",
+      "owner": "Browser/Chrome/IDE/provider client integrator",
+      "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>/",
+        "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
+        "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
+        "python3 scripts/yao.py skill-atlas --workspace-root .",
+        "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
+        "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.",
+        "python3 scripts/yao.py world-class-intake ."
+      ],
+      "success_checks": [
+        "reports/adoption_drift_report.json summary.source_types.external > 0",
+        "reports/adoption_drift_report.json summary.adoption_sample_count > 0",
+        "reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
+      ],
+      "evidence_artifacts": [
+        "reports/adoption_drift_report.json",
+        "reports/adoption_drift_report.md",
+        "reports/telemetry_hook_recipes.json",
+        "scripts/telemetry_native_host.py",
+        "evidence/world_class/intake.schema.json",
+        "evidence/world_class/templates/native-client-telemetry.intake.json",
+        "reports/world_class_evidence_intake.json",
+        "reports/world_class_evidence_intake.md"
+      ],
+      "privacy_contract": [
+        "Telemetry must remain metadata-only and local-first.",
+        "Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
+      ],
+      "audit_next_action": "Install a real client against the native host and import production metadata-only events."
+    }
+  ],
   "source_audit": {
     "json": "reports/skill_os2_audit.json",
     "markdown": "reports/skill_os2_audit.md",
diff --git a/reports/world_class_evidence_plan.md b/reports/world_class_evidence_plan.md
index c8f1d162..63bf0848 100644
--- a/reports/world_class_evidence_plan.md
+++ b/reports/world_class_evidence_plan.md
@@ -1,17 +1,19 @@
 # World-Class Evidence Plan
 
-Generated at: `2026-06-14`
+Generated at: `2026-06-13`
 
 ## Summary
 
 - decision: `collect-external-evidence`
 - audit decision: `continue-iteration`
 - ready to claim world-class: `false`
+- ledger completion required: `true`
+- evidence requirements: `4`
 - tasks: `4`
 - human tasks: `1`
 - external tasks: `3`
 
-This report is an execution plan for the remaining world-class evidence gaps. It does not count a plan as completion.
+This report is an execution plan for the remaining world-class evidence gaps. It does not count a plan or source-report pass as completion; the ledger must still validate accepted submissions.
 
 ## Task Table
 
diff --git a/reports/world_class_operator_runbook.json b/reports/world_class_operator_runbook.json
index c7f73901..c7a608a0 100644
--- a/reports/world_class_operator_runbook.json
+++ b/reports/world_class_operator_runbook.json
@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-14",
+  "generated_at": "2026-06-13",
   "skill_dir": ".",
   "summary": {
     "evidence_item_count": 4,
diff --git a/reports/world_class_operator_runbook.md b/reports/world_class_operator_runbook.md
index 449a0dc2..5cc913bf 100644
--- a/reports/world_class_operator_runbook.md
+++ b/reports/world_class_operator_runbook.md
@@ -1,6 +1,6 @@
 # World-Class Operator Runbook
 
-Generated at: `2026-06-14`
+Generated at: `2026-06-13`
 
 ## Summary
 
diff --git a/reports/world_class_submission_review.json b/reports/world_class_submission_review.json
index b462c0bb..f5cd09b6 100644
--- a/reports/world_class_submission_review.json
+++ b/reports/world_class_submission_review.json
@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-14",
+  "generated_at": "2026-06-13",
   "skill_dir": ".",
   "summary": {
     "review_item_count": 4,
diff --git a/reports/world_class_submission_review.md b/reports/world_class_submission_review.md
index f8f7527b..11389553 100644
--- a/reports/world_class_submission_review.md
+++ b/reports/world_class_submission_review.md
@@ -1,6 +1,6 @@
 # World-Class Submission Review
 
-Generated at: `2026-06-14`
+Generated at: `2026-06-13`
 
 ## Summary
 
diff --git a/scripts/render_world_class_evidence_intake.py b/scripts/render_world_class_evidence_intake.py
index 50000742..576387fb 100644
--- a/scripts/render_world_class_evidence_intake.py
+++ b/scripts/render_world_class_evidence_intake.py
@@ -1,255 +1,19 @@
 #!/usr/bin/env python3
 import argparse
-import hashlib
 import json
-import re
 import shlex
 from datetime import date
 from pathlib import Path
 from typing import Any
 
 from render_world_class_evidence_ledger import build_ledger
+from world_class_evidence_contract import load_json, rel_path, validate_payload
 
 
 ROOT = Path(__file__).resolve().parent.parent
 SCRIPT_INTERFACE = "cli"
 SCRIPT_INTERFACE_REASON = "Validates world-class human and external evidence intake packets before ledger review."
 
-REQUIRED_TOP_LEVEL = [
-    "schema_version",
-    "evidence_key",
-    "template_only",
-    "category",
-    "source_type",
-    "submitted_by",
-    "submitted_at",
-    "summary",
-    "artifact_refs",
-    "provenance",
-    "privacy",
-    "anti_overclaim",
-    "attestation",
-]
-REQUIRED_PRIVACY_FALSE = [
-    "raw_user_content_included",
-    "raw_provider_prompt_included",
-    "credentials_included",
-    "secrets_included",
-]
-REQUIRED_ANTI_OVERCLAIM_FALSE = [
-    "planned_work_counts_as_evidence",
-    "metadata_fallback_counts_as_native_enforcement",
-    "pending_review_counts_as_human_decision",
-    "local_command_runner_counts_as_provider_model",
-]
-REQUIRED_ATTESTATION_TRUE = [
-    "real_external_or_human_evidence",
-    "reviewer_or_operator_identity_present",
-    "artifact_refs_reviewed",
-    "privacy_contract_satisfied",
-]
-EXPECTED_SOURCE_TYPES = {
-    "provider-holdout": "provider-output-eval",
-    "human-adjudication": "blind-ab-review",
-    "native-permission-enforcement": "runtime-permission-guard",
-    "native-client-telemetry": "native-client-telemetry",
-}
-SHA256_RE = re.compile(r"^[0-9a-fA-F]{64}$")
-DISALLOWED_REAL_ARTIFACTS = {"reports/telemetry_events.jsonl"}
-
-
-def load_json(path: Path) -> dict[str, Any]:
-    if not path.exists():
-        return {}
-    try:
-        payload = json.loads(path.read_text(encoding="utf-8"))
-    except json.JSONDecodeError:
-        return {}
-    return payload if isinstance(payload, dict) else {}
-
-
-def rel_path(path: Path, root: Path) -> str:
-    try:
-        return str(path.resolve().relative_to(root.resolve()))
-    except ValueError:
-        return str(path.resolve())
-
-
-def add_error(errors: list[str], condition: bool, message: str) -> None:
-    if not condition:
-        errors.append(message)
-
-
-def sha256_file(path: Path) -> str:
-    digest = hashlib.sha256()
-    with path.open("rb") as handle:
-        for chunk in iter(lambda: handle.read(1024 * 1024), b""):
-            digest.update(chunk)
-    return digest.hexdigest()
-
-
-def resolve_artifact_path(raw_path: str, root: Path) -> tuple[Path | None, str | None]:
-    text = raw_path.strip()
-    if any(token in text for token in ("<", ">", "*", "?")):
-        return None, "artifact_refs path must be concrete, not a placeholder or glob"
-    candidate = Path(text)
-    if candidate.is_absolute():
-        return None, "artifact_refs path must be relative to the skill directory"
-    if ".." in candidate.parts:
-        return None, "artifact_refs path must not escape the skill directory"
-    resolved = (root / candidate).resolve()
-    try:
-        resolved.relative_to(root.resolve())
-    except ValueError:
-        return None, "artifact_refs path must stay inside the skill directory"
-    return resolved, None
-
-
-def validate_artifact_refs(
-    payload: dict[str, Any],
-    errors: list[str],
-    *,
-    root: Path,
-    template_expected: bool,
-) -> dict[str, int]:
-    refs = payload.get("artifact_refs")
-    add_error(errors, isinstance(refs, list) and len(refs) > 0, "artifact_refs must contain at least one reference")
-    stats = {
-        "artifact_ref_count": len(refs) if isinstance(refs, list) else 0,
-        "artifact_existing_count": 0,
-        "artifact_sha256_verified_count": 0,
-    }
-    if not isinstance(refs, list):
-        return stats
-    for index, ref in enumerate(refs):
-        if not isinstance(ref, dict):
-            errors.append(f"artifact_refs[{index}] must be an object")
-            continue
-        path_text = str(ref.get("path", "")).strip()
-        add_error(errors, bool(path_text), f"artifact_refs[{index}].path is required")
-        add_error(errors, bool(str(ref.get("kind", "")).strip()), f"artifact_refs[{index}].kind is required")
-        add_error(errors, ref.get("contains_raw_content") is False, f"artifact_refs[{index}] must not contain raw content")
-        if template_expected or not path_text:
-            continue
-        resolved, path_error = resolve_artifact_path(path_text, root)
-        if path_error:
-            errors.append(f"artifact_refs[{index}].path {path_error}")
-            continue
-        rel = rel_path(resolved, root)
-        if rel in DISALLOWED_REAL_ARTIFACTS:
-            errors.append(f"artifact_refs[{index}].path must not reference raw local telemetry logs")
-        if not resolved.exists() or not resolved.is_file():
-            errors.append(f"artifact_refs[{index}].path does not exist as a local file")
-            continue
-        stats["artifact_existing_count"] += 1
-        declared = str(ref.get("sha256", "")).strip()
-        if not declared:
-            errors.append(f"artifact_refs[{index}].sha256 is required for a real submission")
-            continue
-        if not SHA256_RE.match(declared):
-            errors.append(f"artifact_refs[{index}].sha256 must be a 64-character hex digest")
-            continue
-        actual = sha256_file(resolved)
-        if actual.lower() != declared.lower():
-            errors.append(f"artifact_refs[{index}].sha256 does not match local artifact")
-            continue
-        stats["artifact_sha256_verified_count"] += 1
-    return stats
-
-
-def validate_evidence_specific(payload: dict[str, Any], errors: list[str]) -> None:
-    key = str(payload.get("evidence_key", ""))
-    provenance = payload.get("provenance", {}) if isinstance(payload.get("provenance", {}), dict) else {}
-    if key == "provider-holdout":
-        add_error(errors, bool(str(provenance.get("provider", "")).strip()), "provider-holdout provenance.provider is required")
-        add_error(errors, bool(str(provenance.get("model", "")).strip()), "provider-holdout provenance.model is required")
-        add_error(
-            errors,
-            provenance.get("credential_material_committed") is False,
-            "provider-holdout must attest credential_material_committed is false",
-        )
-    elif key == "human-adjudication":
-        add_error(errors, bool(str(provenance.get("reviewer", "")).strip()), "human-adjudication provenance.reviewer is required")
-        add_error(
-            errors,
-            provenance.get("answer_key_opened_after_decisions") is True,
-            "human-adjudication must attest answer_key_opened_after_decisions is true",
-        )
-    elif key == "native-permission-enforcement":
-        add_error(errors, bool(str(provenance.get("target", "")).strip()), "native-permission-enforcement provenance.target is required")
-        add_error(
-            errors,
-            bool(str(provenance.get("guard_location", "")).strip()),
-            "native-permission-enforcement provenance.guard_location is required",
-        )
-        add_error(
-            errors,
-            str(provenance.get("guard_scope", "")).strip()
-            in {"target-client-native", "external-installer-runtime-guard"},
-            "native-permission-enforcement provenance.guard_scope must be target-client-native or external-installer-runtime-guard",
-        )
-        add_error(
-            errors,
-            provenance.get("guard_blocks_undeclared_capability") is True,
-            "native-permission-enforcement must attest guard_blocks_undeclared_capability is true",
-        )
-        add_error(
-            errors,
-            provenance.get("metadata_fallback_retained_for_other_targets") is True,
-            "native-permission-enforcement must retain metadata fallback for non-native targets",
-        )
-    elif key == "native-client-telemetry":
-        add_error(errors, bool(str(provenance.get("client", "")).strip()), "native-client-telemetry provenance.client is required")
-        add_error(errors, provenance.get("event_source") == "external", "native-client-telemetry event_source must be external")
-        add_error(errors, provenance.get("metadata_only") is True, "native-client-telemetry must be metadata_only")
-
-
-def validate_payload(
-    payload: dict[str, Any],
-    entry: dict[str, Any],
-    *,
-    path: Path,
-    root: Path,
-    template_expected: bool,
-) -> dict[str, Any]:
-    errors: list[str] = []
-    for key in REQUIRED_TOP_LEVEL:
-        add_error(errors, key in payload, f"missing {key}")
-    evidence_key = str(entry.get("key", ""))
-    add_error(errors, payload.get("schema_version") == "1.0", "schema_version must be 1.0")
-    add_error(errors, payload.get("evidence_key") == evidence_key, f"evidence_key must be {evidence_key}")
-    add_error(errors, payload.get("template_only") is template_expected, f"template_only must be {str(template_expected).lower()}")
-    add_error(errors, payload.get("category") == entry.get("category"), f"category must be {entry.get('category')}")
-    add_error(
-        errors,
-        payload.get("source_type") == EXPECTED_SOURCE_TYPES.get(evidence_key),
-        f"source_type must be {EXPECTED_SOURCE_TYPES.get(evidence_key)}",
-    )
-    add_error(errors, bool(str(payload.get("submitted_by", "")).strip()), "submitted_by is required")
-    add_error(errors, bool(str(payload.get("submitted_at", "")).strip()), "submitted_at is required")
-    add_error(errors, bool(str(payload.get("summary", "")).strip()), "summary is required")
-    artifact_integrity = validate_artifact_refs(payload, errors, root=root, template_expected=template_expected)
-    privacy = payload.get("privacy", {}) if isinstance(payload.get("privacy", {}), dict) else {}
-    for key in REQUIRED_PRIVACY_FALSE:
-        add_error(errors, privacy.get(key) is False, f"privacy.{key} must be false")
-    anti_overclaim = payload.get("anti_overclaim", {}) if isinstance(payload.get("anti_overclaim", {}), dict) else {}
-    for key in REQUIRED_ANTI_OVERCLAIM_FALSE:
-        add_error(errors, anti_overclaim.get(key) is False, f"anti_overclaim.{key} must be false")
-    validate_evidence_specific(payload, errors)
-    attestation = payload.get("attestation", {}) if isinstance(payload.get("attestation", {}), dict) else {}
-    if not template_expected:
-        for key in REQUIRED_ATTESTATION_TRUE:
-            add_error(errors, attestation.get(key) is True, f"attestation.{key} must be true for a real submission")
-    return {
-        "path": rel_path(path, root),
-        "evidence_key": evidence_key,
-        "status": "pass" if not errors else "fail",
-        "template_only": template_expected,
-        "artifact_integrity": artifact_integrity,
-        "errors": errors,
-    }
-
-
 def template_paths(skill_dir: Path, keys: list[str]) -> dict[str, Path]:
     template_dir = skill_dir / "evidence" / "world_class" / "templates"
     return {key: template_dir / f"{key}.intake.json" for key in keys}
diff --git a/scripts/render_world_class_evidence_ledger.py b/scripts/render_world_class_evidence_ledger.py
index 68ec50ea..38a49e40 100644
--- a/scripts/render_world_class_evidence_ledger.py
+++ b/scripts/render_world_class_evidence_ledger.py
@@ -6,6 +6,7 @@ from pathlib import Path
 from typing import Any
 
 from render_world_class_evidence_plan import build_plan
+from world_class_evidence_contract import load_json, load_json_with_status, rel_path, validate_payload
 
 
 ROOT = Path(__file__).resolve().parent.parent
@@ -13,35 +14,6 @@ SCRIPT_INTERFACE = "cli"
 SCRIPT_INTERFACE_REASON = "Renders a machine-checkable ledger for world-class external and human evidence gaps."
 
 
-def load_json(path: Path) -> dict[str, Any]:
-    if not path.exists():
-        return {}
-    try:
-        payload = json.loads(path.read_text(encoding="utf-8"))
-    except json.JSONDecodeError:
-        return {}
-    return payload if isinstance(payload, dict) else {}
-
-
-def load_json_with_status(path: Path) -> tuple[dict[str, Any], str]:
-    if not path.exists():
-        return {}, "missing"
-    try:
-        payload = json.loads(path.read_text(encoding="utf-8"))
-    except json.JSONDecodeError:
-        return {}, "invalid-json"
-    if not isinstance(payload, dict):
-        return {}, "invalid-json"
-    return payload, "present"
-
-
-def rel_path(path: Path, root: Path) -> str:
-    try:
-        return str(path.resolve().relative_to(root.resolve()))
-    except ValueError:
-        return str(path.resolve())
-
-
 def provider_state(skill_dir: Path) -> dict[str, Any]:
     summary = load_json(skill_dir / "reports" / "output_execution_runs.json").get("summary", {})
     return {
@@ -120,7 +92,8 @@ PROVENANCE_REQUIREMENTS = {
 }
 
 
-def submission_state(skill_dir: Path, key: str, submissions_dir: Path) -> dict[str, Any]:
+def submission_state(skill_dir: Path, task: dict[str, Any], submissions_dir: Path) -> dict[str, Any]:
+    key = str(task.get("key", ""))
     path = submissions_dir / f"{key}.json"
     payload, load_status = load_json_with_status(path)
     if load_status != "present":
@@ -132,32 +105,32 @@ def submission_state(skill_dir: Path, key: str, submissions_dir: Path) -> dict[s
             "privacy_contract_satisfied": False,
             "ledger_counts_as_completion": False,
         }
-    errors = []
-    if payload.get("evidence_key") != key:
-        errors.append("evidence_key mismatch")
-    if payload.get("template_only") is not False:
-        errors.append("template_only must be false")
+    validation = validate_payload(payload, task, path=path, root=skill_dir, template_expected=False)
     refs = payload.get("artifact_refs", [])
     attestation = payload.get("attestation", {}) if isinstance(payload.get("attestation", {}), dict) else {}
-    status = "submitted" if not errors else "invalid-contract"
+    status = "submitted" if validation["status"] == "pass" else "invalid-contract"
+    artifact_integrity = validation.get("artifact_integrity", {})
     return {
         "status": status,
         "path": rel_path(path, skill_dir),
         "submitted_by": payload.get("submitted_by", ""),
         "submitted_at": payload.get("submitted_at", ""),
         "artifact_ref_count": len(refs) if isinstance(refs, list) else 0,
+        "artifact_existing_count": artifact_integrity.get("artifact_existing_count", 0),
+        "artifact_sha256_verified_count": artifact_integrity.get("artifact_sha256_verified_count", 0),
         "attested_real_evidence": attestation.get("real_external_or_human_evidence") is True,
         "reviewer_or_operator_identity_present": attestation.get("reviewer_or_operator_identity_present") is True,
         "privacy_contract_satisfied": attestation.get("privacy_contract_satisfied") is True,
-        "errors": errors,
+        "errors": validation.get("errors", []),
         "ledger_counts_as_completion": False,
     }
 
 
 def build_entry(skill_dir: Path, task: dict[str, Any], submissions_dir: Path) -> dict[str, Any]:
     state = STATE_LOADERS.get(task["key"], lambda _: {"accepted": task["status"] == "pass"})(skill_dir)
-    accepted = bool(state.get("accepted"))
-    submission = submission_state(skill_dir, task["key"], submissions_dir)
+    submission = submission_state(skill_dir, task, submissions_dir)
+    source_accepted = bool(state.get("accepted"))
+    accepted = source_accepted and submission.get("status") == "submitted"
     return {
         "key": task["key"],
         "label": task["label"],
@@ -165,6 +138,7 @@ def build_entry(skill_dir: Path, task: dict[str, Any], submissions_dir: Path) ->
         "owner": task["owner"],
         "status": "accepted" if accepted else "pending",
         "source_status": task["status"],
+        "source_accepted": source_accepted,
         "current": task["current"],
         "objective": task["objective"],
         "provenance_requirements": PROVENANCE_REQUIREMENTS.get(task["key"], ["release reviewer evidence"]),
@@ -186,7 +160,9 @@ def build_entry(skill_dir: Path, task: dict[str, Any], submissions_dir: Path) ->
 def build_ledger(skill_dir: Path, generated_at: str, submissions_dir: Path | None = None) -> dict[str, Any]:
     plan = build_plan(skill_dir, generated_at)
     submissions_dir = submissions_dir or (skill_dir / "evidence" / "world_class" / "submissions")
-    entries = [build_entry(skill_dir, task, submissions_dir) for task in plan["tasks"]]
+    evidence_requirements = plan.get("evidence_requirements") or plan.get("tasks", [])
+    entries = [build_entry(skill_dir, task, submissions_dir) for task in evidence_requirements]
+    source_accepted_count = sum(1 for entry in entries if entry.get("source_accepted") is True)
     accepted_count = sum(1 for entry in entries if entry["status"] == "accepted")
     pending_count = len(entries) - accepted_count
     human_pending_count = sum(1 for entry in entries if entry["category"] == "human" and entry["status"] == "pending")
@@ -197,7 +173,12 @@ def build_ledger(skill_dir: Path, generated_at: str, submissions_dir: Path | Non
     submitted_but_pending_count = sum(
         1 for entry in entries if entry["submission_state"]["status"] == "submitted" and entry["status"] == "pending"
     )
-    ready = pending_count == 0 and plan["summary"].get("world_class_ready") is True
+    source_accepted_without_valid_submission_count = sum(
+        1
+        for entry in entries
+        if entry.get("source_accepted") is True and entry["submission_state"]["status"] != "submitted"
+    )
+    ready = bool(entries) and pending_count == 0 and plan["summary"].get("world_class_ready") is True
     return {
         "schema_version": "1.0",
         "ok": True,
@@ -205,6 +186,7 @@ def build_ledger(skill_dir: Path, generated_at: str, submissions_dir: Path | Non
         "skill_dir": rel_path(skill_dir, ROOT),
         "summary": {
             "ledger_entry_count": len(entries),
+            "source_accepted_count": source_accepted_count,
             "accepted_count": accepted_count,
             "pending_count": pending_count,
             "human_pending_count": human_pending_count,
@@ -213,6 +195,7 @@ def build_ledger(skill_dir: Path, generated_at: str, submissions_dir: Path | Non
             "missing_submission_count": missing_submission_count,
             "invalid_submission_count": invalid_submission_count,
             "submitted_but_pending_count": submitted_but_pending_count,
+            "source_accepted_without_valid_submission_count": source_accepted_without_valid_submission_count,
             "overclaim_guard_active": True,
             "ready_to_claim_world_class": ready,
             "decision": "ready-for-completion-audit" if ready else "evidence-pending",
@@ -222,10 +205,12 @@ def build_ledger(skill_dir: Path, generated_at: str, submissions_dir: Path | Non
             "json": "reports/world_class_evidence_plan.json",
             "markdown": "reports/world_class_evidence_plan.md",
             "task_count": plan["summary"].get("task_count", 0),
+            "evidence_requirement_count": len(evidence_requirements),
         },
         "submissions": {
             "directory": rel_path(submissions_dir, skill_dir),
             "ledger_counts_submission_as_completion": False,
+            "source_pass_requires_valid_submission": True,
         },
         "artifacts": {
             "json": "reports/world_class_evidence_ledger.json",
@@ -247,16 +232,18 @@ def render_markdown(ledger: dict[str, Any]) -> str:
         f"- decision: `{summary['decision']}`",
         f"- ready to claim world-class: `{str(summary['ready_to_claim_world_class']).lower()}`",
         f"- entries: `{summary['ledger_entry_count']}`",
+        f"- source accepted: `{summary.get('source_accepted_count', 0)}`",
         f"- accepted: `{summary['accepted_count']}`",
         f"- pending: `{summary['pending_count']}`",
         f"- human pending: `{summary['human_pending_count']}`",
         f"- external pending: `{summary['external_pending_count']}`",
         f"- submitted entries: `{summary['submitted_entry_count']}`",
         f"- submitted but pending: `{summary['submitted_but_pending_count']}`",
+        f"- source accepted without valid submission: `{summary.get('source_accepted_without_valid_submission_count', 0)}`",
         f"- invalid submissions: `{summary['invalid_submission_count']}`",
         f"- overclaim guard active: `{str(summary['overclaim_guard_active']).lower()}`",
         "",
-        "This ledger records the current evidence state. It does not treat planned work, metadata fallback, pending review, or local command-runner output as world-class completion evidence.",
+        "This ledger records the current evidence state. It requires both passing source evidence and a validated intake submission with artifact SHA-256 checks before accepting an item. It does not treat planned work, metadata fallback, pending review, or local command-runner output as world-class completion evidence.",
         "",
         "## Ledger",
         "",
diff --git a/scripts/render_world_class_evidence_plan.py b/scripts/render_world_class_evidence_plan.py
index 3579bce2..31c097eb 100644
--- a/scripts/render_world_class_evidence_plan.py
+++ b/scripts/render_world_class_evidence_plan.py
@@ -175,11 +175,14 @@ def build_task(item: dict[str, Any]) -> dict[str, Any]:
 
 def build_plan(skill_dir: Path, generated_at: str) -> dict[str, Any]:
     audit = build_audit(skill_dir, generated_at)
-    tasks = [build_task(item) for item in audit["items"] if item["status"] != "pass"]
+    evidence_keys = set(TASK_TEMPLATES)
+    evidence_requirements = [build_task(item) for item in audit["items"] if item["key"] in evidence_keys]
+    tasks = [task for task in evidence_requirements if task["status"] != "pass"]
+    tasks.extend(build_task(item) for item in audit["items"] if item["status"] != "pass" and item["key"] not in evidence_keys)
     category_counts: dict[str, int] = {}
     for task in tasks:
         category_counts[task["category"]] = category_counts.get(task["category"], 0) + 1
-    ready = len(tasks) == 0 and audit["summary"].get("world_class_ready") is True
+    audit_world_class_ready = audit["summary"].get("world_class_ready") is True
     return {
         "schema_version": "1.0",
         "ok": audit["ok"],
@@ -188,14 +191,18 @@ def build_plan(skill_dir: Path, generated_at: str) -> dict[str, Any]:
         "summary": {
             "audit_decision": audit["summary"]["decision"],
             "world_class_ready": bool(audit["summary"]["world_class_ready"]),
-            "ready_to_claim_world_class": ready,
+            "audit_world_class_ready": audit_world_class_ready,
+            "ready_to_claim_world_class": False,
+            "ledger_completion_required": True,
+            "evidence_requirement_count": len(evidence_requirements),
             "task_count": len(tasks),
             "human_task_count": category_counts.get("human", 0),
             "external_task_count": category_counts.get("external", 0),
             "review_task_count": category_counts.get("review", 0),
-            "decision": "ready-for-completion-audit" if ready else "collect-external-evidence",
+            "decision": "audit-ready-ledger-required" if audit_world_class_ready and not tasks else "collect-external-evidence",
         },
         "tasks": tasks,
+        "evidence_requirements": evidence_requirements,
         "source_audit": {
             "json": "reports/skill_os2_audit.json",
             "markdown": "reports/skill_os2_audit.md",
@@ -222,11 +229,13 @@ def render_markdown(plan: dict[str, Any]) -> str:
         f"- decision: `{summary['decision']}`",
         f"- audit decision: `{summary['audit_decision']}`",
         f"- ready to claim world-class: `{str(summary['ready_to_claim_world_class']).lower()}`",
+        f"- ledger completion required: `{str(summary.get('ledger_completion_required', True)).lower()}`",
+        f"- evidence requirements: `{summary.get('evidence_requirement_count', 0)}`",
         f"- tasks: `{summary['task_count']}`",
         f"- human tasks: `{summary['human_task_count']}`",
         f"- external tasks: `{summary['external_task_count']}`",
         "",
-        "This report is an execution plan for the remaining world-class evidence gaps. It does not count a plan as completion.",
+        "This report is an execution plan for the remaining world-class evidence gaps. It does not count a plan or source-report pass as completion; the ledger must still validate accepted submissions.",
         "",
         "## Task Table",
         "",
@@ -239,7 +248,7 @@ def render_markdown(plan: dict[str, Any]) -> str:
             f"| `{task['key']}` | `{task['status']}` | `{task['category']}` | {task['owner']} | {current} |"
         )
     if not plan["tasks"]:
-        lines.append("| `none` | `pass` | `none` | none | all evidence collected |")
+        lines.append("| `none` | `pass` | `none` | none | audit gaps closed; ledger validation still required |")
     for task in plan["tasks"]:
         lines.extend(
             [
diff --git a/scripts/world_class_evidence_contract.py b/scripts/world_class_evidence_contract.py
new file mode 100644
index 00000000..4bd462d4
--- /dev/null
+++ b/scripts/world_class_evidence_contract.py
@@ -0,0 +1,256 @@
+#!/usr/bin/env python3
+import hashlib
+import json
+import re
+from pathlib import Path
+from typing import Any
+
+
+SCRIPT_INTERFACE = "internal-module"
+SCRIPT_INTERFACE_REASON = "Imported by world-class evidence reports to share intake validation and artifact integrity checks."
+
+REQUIRED_TOP_LEVEL = [
+    "schema_version",
+    "evidence_key",
+    "template_only",
+    "category",
+    "source_type",
+    "submitted_by",
+    "submitted_at",
+    "summary",
+    "artifact_refs",
+    "provenance",
+    "privacy",
+    "anti_overclaim",
+    "attestation",
+]
+REQUIRED_PRIVACY_FALSE = [
+    "raw_user_content_included",
+    "raw_provider_prompt_included",
+    "credentials_included",
+    "secrets_included",
+]
+REQUIRED_ANTI_OVERCLAIM_FALSE = [
+    "planned_work_counts_as_evidence",
+    "metadata_fallback_counts_as_native_enforcement",
+    "pending_review_counts_as_human_decision",
+    "local_command_runner_counts_as_provider_model",
+]
+REQUIRED_ATTESTATION_TRUE = [
+    "real_external_or_human_evidence",
+    "reviewer_or_operator_identity_present",
+    "artifact_refs_reviewed",
+    "privacy_contract_satisfied",
+]
+EXPECTED_SOURCE_TYPES = {
+    "provider-holdout": "provider-output-eval",
+    "human-adjudication": "blind-ab-review",
+    "native-permission-enforcement": "runtime-permission-guard",
+    "native-client-telemetry": "native-client-telemetry",
+}
+SHA256_RE = re.compile(r"^[0-9a-fA-F]{64}$")
+DISALLOWED_REAL_ARTIFACTS = {"reports/telemetry_events.jsonl"}
+
+
+def load_json(path: Path) -> dict[str, Any]:
+    if not path.exists():
+        return {}
+    try:
+        payload = json.loads(path.read_text(encoding="utf-8"))
+    except json.JSONDecodeError:
+        return {}
+    return payload if isinstance(payload, dict) else {}
+
+
+def load_json_with_status(path: Path) -> tuple[dict[str, Any], str]:
+    if not path.exists():
+        return {}, "missing"
+    try:
+        payload = json.loads(path.read_text(encoding="utf-8"))
+    except json.JSONDecodeError:
+        return {}, "invalid-json"
+    if not isinstance(payload, dict):
+        return {}, "invalid-json"
+    return payload, "present"
+
+
+def rel_path(path: Path, root: Path) -> str:
+    try:
+        return str(path.resolve().relative_to(root.resolve()))
+    except ValueError:
+        return str(path.resolve())
+
+
+def add_error(errors: list[str], condition: bool, message: str) -> None:
+    if not condition:
+        errors.append(message)
+
+
+def sha256_file(path: Path) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as handle:
+        for chunk in iter(lambda: handle.read(1024 * 1024), b""):
+            digest.update(chunk)
+    return digest.hexdigest()
+
+
+def resolve_artifact_path(raw_path: str, root: Path) -> tuple[Path | None, str | None]:
+    text = raw_path.strip()
+    if any(token in text for token in ("<", ">", "*", "?")):
+        return None, "artifact_refs path must be concrete, not a placeholder or glob"
+    candidate = Path(text)
+    if candidate.is_absolute():
+        return None, "artifact_refs path must be relative to the skill directory"
+    if ".." in candidate.parts:
+        return None, "artifact_refs path must not escape the skill directory"
+    resolved = (root / candidate).resolve()
+    try:
+        resolved.relative_to(root.resolve())
+    except ValueError:
+        return None, "artifact_refs path must stay inside the skill directory"
+    return resolved, None
+
+
+def validate_artifact_refs(
+    payload: dict[str, Any],
+    errors: list[str],
+    *,
+    root: Path,
+    template_expected: bool,
+) -> dict[str, int]:
+    refs = payload.get("artifact_refs")
+    add_error(errors, isinstance(refs, list) and len(refs) > 0, "artifact_refs must contain at least one reference")
+    stats = {
+        "artifact_ref_count": len(refs) if isinstance(refs, list) else 0,
+        "artifact_existing_count": 0,
+        "artifact_sha256_verified_count": 0,
+    }
+    if not isinstance(refs, list):
+        return stats
+    for index, ref in enumerate(refs):
+        if not isinstance(ref, dict):
+            errors.append(f"artifact_refs[{index}] must be an object")
+            continue
+        path_text = str(ref.get("path", "")).strip()
+        add_error(errors, bool(path_text), f"artifact_refs[{index}].path is required")
+        add_error(errors, bool(str(ref.get("kind", "")).strip()), f"artifact_refs[{index}].kind is required")
+        add_error(errors, ref.get("contains_raw_content") is False, f"artifact_refs[{index}] must not contain raw content")
+        if template_expected or not path_text:
+            continue
+        resolved, path_error = resolve_artifact_path(path_text, root)
+        if path_error:
+            errors.append(f"artifact_refs[{index}].path {path_error}")
+            continue
+        rel = rel_path(resolved, root)
+        if rel in DISALLOWED_REAL_ARTIFACTS:
+            errors.append(f"artifact_refs[{index}].path must not reference raw local telemetry logs")
+        if not resolved.exists() or not resolved.is_file():
+            errors.append(f"artifact_refs[{index}].path does not exist as a local file")
+            continue
+        stats["artifact_existing_count"] += 1
+        declared = str(ref.get("sha256", "")).strip()
+        if not declared:
+            errors.append(f"artifact_refs[{index}].sha256 is required for a real submission")
+            continue
+        if not SHA256_RE.match(declared):
+            errors.append(f"artifact_refs[{index}].sha256 must be a 64-character hex digest")
+            continue
+        actual = sha256_file(resolved)
+        if actual.lower() != declared.lower():
+            errors.append(f"artifact_refs[{index}].sha256 does not match local artifact")
+            continue
+        stats["artifact_sha256_verified_count"] += 1
+    return stats
+
+
+def validate_evidence_specific(payload: dict[str, Any], errors: list[str]) -> None:
+    key = str(payload.get("evidence_key", ""))
+    provenance = payload.get("provenance", {}) if isinstance(payload.get("provenance", {}), dict) else {}
+    if key == "provider-holdout":
+        add_error(errors, bool(str(provenance.get("provider", "")).strip()), "provider-holdout provenance.provider is required")
+        add_error(errors, bool(str(provenance.get("model", "")).strip()), "provider-holdout provenance.model is required")
+        add_error(
+            errors,
+            provenance.get("credential_material_committed") is False,
+            "provider-holdout must attest credential_material_committed is false",
+        )
+    elif key == "human-adjudication":
+        add_error(errors, bool(str(provenance.get("reviewer", "")).strip()), "human-adjudication provenance.reviewer is required")
+        add_error(
+            errors,
+            provenance.get("answer_key_opened_after_decisions") is True,
+            "human-adjudication must attest answer_key_opened_after_decisions is true",
+        )
+    elif key == "native-permission-enforcement":
+        add_error(errors, bool(str(provenance.get("target", "")).strip()), "native-permission-enforcement provenance.target is required")
+        add_error(
+            errors,
+            bool(str(provenance.get("guard_location", "")).strip()),
+            "native-permission-enforcement provenance.guard_location is required",
+        )
+        add_error(
+            errors,
+            str(provenance.get("guard_scope", "")).strip()
+            in {"target-client-native", "external-installer-runtime-guard"},
+            "native-permission-enforcement provenance.guard_scope must be target-client-native or external-installer-runtime-guard",
+        )
+        add_error(
+            errors,
+            provenance.get("guard_blocks_undeclared_capability") is True,
+            "native-permission-enforcement must attest guard_blocks_undeclared_capability is true",
+        )
+        add_error(
+            errors,
+            provenance.get("metadata_fallback_retained_for_other_targets") is True,
+            "native-permission-enforcement must retain metadata fallback for non-native targets",
+        )
+    elif key == "native-client-telemetry":
+        add_error(errors, bool(str(provenance.get("client", "")).strip()), "native-client-telemetry provenance.client is required")
+        add_error(errors, provenance.get("event_source") == "external", "native-client-telemetry event_source must be external")
+        add_error(errors, provenance.get("metadata_only") is True, "native-client-telemetry must be metadata_only")
+
+
+def validate_payload(
+    payload: dict[str, Any],
+    entry: dict[str, Any],
+    *,
+    path: Path,
+    root: Path,
+    template_expected: bool,
+) -> dict[str, Any]:
+    errors: list[str] = []
+    for key in REQUIRED_TOP_LEVEL:
+        add_error(errors, key in payload, f"missing {key}")
+    evidence_key = str(entry.get("key", ""))
+    add_error(errors, payload.get("schema_version") == "1.0", "schema_version must be 1.0")
+    add_error(errors, payload.get("evidence_key") == evidence_key, f"evidence_key must be {evidence_key}")
+    add_error(errors, payload.get("template_only") is template_expected, f"template_only must be {str(template_expected).lower()}")
+    add_error(errors, payload.get("category") == entry.get("category"), f"category must be {entry.get('category')}")
+    add_error(
+        errors,
+        payload.get("source_type") == EXPECTED_SOURCE_TYPES.get(evidence_key),
+        f"source_type must be {EXPECTED_SOURCE_TYPES.get(evidence_key)}",
+    )
+    add_error(errors, bool(str(payload.get("submitted_by", "")).strip()), "submitted_by is required")
+    add_error(errors, bool(str(payload.get("submitted_at", "")).strip()), "submitted_at is required")
+    add_error(errors, bool(str(payload.get("summary", "")).strip()), "summary is required")
+    artifact_integrity = validate_artifact_refs(payload, errors, root=root, template_expected=template_expected)
+    privacy = payload.get("privacy", {}) if isinstance(payload.get("privacy", {}), dict) else {}
+    for key in REQUIRED_PRIVACY_FALSE:
+        add_error(errors, privacy.get(key) is False, f"privacy.{key} must be false")
+    anti_overclaim = payload.get("anti_overclaim", {}) if isinstance(payload.get("anti_overclaim", {}), dict) else {}
+    for key in REQUIRED_ANTI_OVERCLAIM_FALSE:
+        add_error(errors, anti_overclaim.get(key) is False, f"anti_overclaim.{key} must be false")
+    validate_evidence_specific(payload, errors)
+    attestation = payload.get("attestation", {}) if isinstance(payload.get("attestation", {}), dict) else {}
+    if not template_expected:
+        for key in REQUIRED_ATTESTATION_TRUE:
+            add_error(errors, attestation.get(key) is True, f"attestation.{key} must be true for a real submission")
+    return {
+        "path": rel_path(path, root),
+        "evidence_key": evidence_key,
+        "status": "pass" if not errors else "fail",
+        "template_only": template_expected,
+        "artifact_integrity": artifact_integrity,
+        "errors": errors,
+    }
diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json
index 701cc3c6..b1f21ea5 100644
--- a/skill_atlas/catalog.json
+++ b/skill_atlas/catalog.json
@@ -107,6 +107,7 @@
         "scripts/upgrade_check.py",
         "scripts/validate_skill.py",
         "scripts/verify_package.py",
+        "scripts/world_class_evidence_contract.py",
         "scripts/yao.py",
         "scripts/yao_cli_config.py",
         "scripts/yao_cli_create_commands.py",
diff --git a/tests/verify_trust_check.py b/tests/verify_trust_check.py
index ae968679..22d99412 100644
--- a/tests/verify_trust_check.py
+++ b/tests/verify_trust_check.py
@@ -95,6 +95,7 @@ def main() -> None:
         "scripts/skill_report_layout.py",
         "scripts/skill_report_metrics.py",
         "scripts/skill_report_model.py",
+        "scripts/world_class_evidence_contract.py",
         "scripts/yao_cli_config.py",
         "scripts/yao_cli_parser.py",
         "scripts/yao_cli_telemetry.py",
@@ -109,6 +110,7 @@ def main() -> None:
     assert "skill_report_layout.py" not in warning_text, payload["warnings"]
     assert "skill_report_metrics.py" not in warning_text, payload["warnings"]
     assert "skill_report_model.py" not in warning_text, payload["warnings"]
+    assert "world_class_evidence_contract.py" not in warning_text, payload["warnings"]
     assert "yao_cli_config.py" not in warning_text, payload["warnings"]
     assert "yao_cli_parser.py" not in warning_text, payload["warnings"]
     assert "yao_cli_telemetry.py" not in warning_text, payload["warnings"]
diff --git a/tests/verify_world_class_claim_guard.py b/tests/verify_world_class_claim_guard.py
index 6b5a5e33..4562a990 100644
--- a/tests/verify_world_class_claim_guard.py
+++ b/tests/verify_world_class_claim_guard.py
@@ -52,13 +52,23 @@ def main() -> None:
 
     safe_surface = TMP / "safe.md"
     safe_surface.write_text("ready to claim world-class: `false`\nworld-class evidence is pending.\n", encoding="utf-8")
-    safe_proc = run_guard("--claim-surface", str(safe_surface), check=True)
+    safe_proc = run_guard(
+        "--claim-surface", str(safe_surface),
+        "--output-json", str(TMP / "safe_guard.json"),
+        "--output-md", str(TMP / "safe_guard.md"),
+        check=True,
+    )
     safe_payload = json.loads(safe_proc.stdout)
     assert safe_payload["summary"]["violation_count"] == 0, safe_payload
 
     unsafe_surface = TMP / "unsafe.md"
     unsafe_surface.write_text("ready to claim world-class: `true`\n世界级已完成\n", encoding="utf-8")
-    unsafe_proc = run_guard("--claim-surface", str(unsafe_surface), check=False)
+    unsafe_proc = run_guard(
+        "--claim-surface", str(unsafe_surface),
+        "--output-json", str(TMP / "unsafe_guard.json"),
+        "--output-md", str(TMP / "unsafe_guard.md"),
+        check=False,
+    )
     assert unsafe_proc.returncode == 2, unsafe_proc.stdout
     unsafe_payload = json.loads(unsafe_proc.stdout)
     assert unsafe_payload["ok"] is False, unsafe_payload
@@ -72,6 +82,10 @@ def main() -> None:
     relative_proc = run_guard(
         "--claim-surface",
         relative_unsafe_surface.relative_to(ROOT).as_posix(),
+        "--output-json",
+        str(TMP / "relative_unsafe_guard.json"),
+        "--output-md",
+        str(TMP / "relative_unsafe_guard.md"),
         check=False,
         cwd=TMP,
     )
diff --git a/tests/verify_world_class_evidence_ledger.py b/tests/verify_world_class_evidence_ledger.py
index 836929c9..db2d33c0 100644
--- a/tests/verify_world_class_evidence_ledger.py
+++ b/tests/verify_world_class_evidence_ledger.py
@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+import hashlib
 import json
 import shutil
 import subprocess
@@ -11,7 +12,15 @@ SCRIPT = ROOT / "scripts" / "render_world_class_evidence_ledger.py"
 TMP = ROOT / "tests" / "tmp_world_class_evidence_ledger"
 
 
-def provider_submission() -> dict:
+def sha256_file(path: Path) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as handle:
+        for chunk in iter(lambda: handle.read(1024 * 1024), b""):
+            digest.update(chunk)
+    return digest.hexdigest()
+
+
+def provider_submission(artifact_root: Path = ROOT) -> dict:
     return {
         "schema_version": "1.0",
         "evidence_key": "provider-holdout",
@@ -26,8 +35,26 @@ def provider_submission() -> dict:
                 "path": "reports/output_execution_runs.json",
                 "kind": "aggregate-report",
                 "contains_raw_content": False,
+                "sha256": sha256_file(artifact_root / "reports" / "output_execution_runs.json"),
             }
         ],
+        "provenance": {
+            "provider": "openai",
+            "model": "gpt-4.1-mini",
+            "credential_material_committed": False,
+        },
+        "privacy": {
+            "raw_user_content_included": False,
+            "raw_provider_prompt_included": False,
+            "credentials_included": False,
+            "secrets_included": False,
+        },
+        "anti_overclaim": {
+            "planned_work_counts_as_evidence": False,
+            "metadata_fallback_counts_as_native_enforcement": False,
+            "pending_review_counts_as_human_decision": False,
+            "local_command_runner_counts_as_provider_model": False,
+        },
         "attestation": {
             "real_external_or_human_evidence": True,
             "reviewer_or_operator_identity_present": True,
@@ -136,8 +163,90 @@ def main() -> None:
     submitted_provider = {entry["key"]: entry for entry in submitted_payload["entries"]}["provider-holdout"]
     assert submitted_provider["status"] == "pending", submitted_provider
     assert submitted_provider["submission_state"]["status"] == "submitted", submitted_provider
+    assert submitted_provider["submission_state"]["artifact_sha256_verified_count"] == 1, submitted_provider
     assert submitted_provider["submission_state"]["attested_real_evidence"] is True, submitted_provider
     assert submitted_provider["submission_state"]["ledger_counts_as_completion"] is False, submitted_provider
+
+    accepted_source_skill = TMP / "accepted_source_skill"
+    (accepted_source_skill / "reports").mkdir(parents=True)
+    (accepted_source_skill / "reports" / "output_execution_runs.json").write_text(
+        json.dumps(
+            {
+                "summary": {
+                    "model_executed_count": 1,
+                    "timing_observed_count": 1,
+                    "token_observed_count": 1,
+                }
+            },
+            ensure_ascii=False,
+            indent=2,
+        )
+        + "\n",
+        encoding="utf-8",
+    )
+    accepted_source_proc = subprocess.run(
+        [
+            sys.executable,
+            str(SCRIPT),
+            str(accepted_source_skill),
+            "--output-json",
+            str(TMP / "accepted_source_without_submission.json"),
+            "--output-md",
+            str(TMP / "accepted_source_without_submission.md"),
+            "--generated-at",
+            "2026-06-13",
+        ],
+        cwd=ROOT,
+        capture_output=True,
+        text=True,
+        check=True,
+    )
+    accepted_source_payload = json.loads(accepted_source_proc.stdout)
+    accepted_source_summary = accepted_source_payload["summary"]
+    assert accepted_source_summary["source_accepted_count"] == 1, accepted_source_summary
+    assert accepted_source_summary["accepted_count"] == 0, accepted_source_summary
+    assert accepted_source_summary["source_accepted_without_valid_submission_count"] == 1, accepted_source_summary
+    accepted_source_provider = {
+        entry["key"]: entry for entry in accepted_source_payload["entries"]
+    }["provider-holdout"]
+    assert accepted_source_provider["source_accepted"] is True, accepted_source_provider
+    assert accepted_source_provider["status"] == "pending", accepted_source_provider
+    assert accepted_source_provider["submission_state"]["status"] == "missing", accepted_source_provider
+
+    accepted_submissions = TMP / "accepted_submissions"
+    accepted_submissions.mkdir()
+    (accepted_submissions / "provider-holdout.json").write_text(
+        json.dumps(provider_submission(accepted_source_skill), ensure_ascii=False, indent=2) + "\n",
+        encoding="utf-8",
+    )
+    accepted_proc = subprocess.run(
+        [
+            sys.executable,
+            str(SCRIPT),
+            str(accepted_source_skill),
+            "--output-json",
+            str(TMP / "accepted_provider_ledger.json"),
+            "--output-md",
+            str(TMP / "accepted_provider_ledger.md"),
+            "--submissions-dir",
+            str(accepted_submissions),
+            "--generated-at",
+            "2026-06-13",
+        ],
+        cwd=ROOT,
+        capture_output=True,
+        text=True,
+        check=True,
+    )
+    accepted_payload = json.loads(accepted_proc.stdout)
+    accepted_summary = accepted_payload["summary"]
+    assert accepted_summary["source_accepted_count"] == 1, accepted_summary
+    assert accepted_summary["accepted_count"] == 1, accepted_summary
+    assert accepted_summary["pending_count"] == 3, accepted_summary
+    assert accepted_summary["source_accepted_without_valid_submission_count"] == 0, accepted_summary
+    accepted_provider = {entry["key"]: entry for entry in accepted_payload["entries"]}["provider-holdout"]
+    assert accepted_provider["status"] == "accepted", accepted_provider
+    assert accepted_provider["submission_state"]["status"] == "submitted", accepted_provider
     print(json.dumps({"ok": True}, ensure_ascii=False, indent=2))
 
 
diff --git a/tests/verify_world_class_evidence_plan.py b/tests/verify_world_class_evidence_plan.py
index 8c046a78..548eaf1a 100644
--- a/tests/verify_world_class_evidence_plan.py
+++ b/tests/verify_world_class_evidence_plan.py
@@ -38,18 +38,22 @@ def main() -> None:
     assert payload["ok"] is True, payload
     assert payload["summary"]["decision"] == "collect-external-evidence", payload
     assert payload["summary"]["ready_to_claim_world_class"] is False, payload
+    assert payload["summary"]["ledger_completion_required"] is True, payload
+    assert payload["summary"]["evidence_requirement_count"] == 4, payload
     assert payload["summary"]["task_count"] == 4, payload
     assert payload["summary"]["human_task_count"] == 1, payload
     assert payload["summary"]["external_task_count"] == 3, payload
     assert payload["artifacts"]["ledger"] == "reports/world_class_evidence_ledger.md", payload
     assert payload["artifacts"]["intake"] == "reports/world_class_evidence_intake.md", payload
     tasks = {item["key"]: item for item in payload["tasks"]}
+    requirements = {item["key"]: item for item in payload["evidence_requirements"]}
     assert set(tasks) == {
         "provider-holdout",
         "human-adjudication",
         "native-permission-enforcement",
         "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"]
     assert any("world-class-intake" 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"]
@@ -68,6 +72,7 @@ def main() -> None:
     assert "World-Class Evidence Plan" in markdown, markdown
     assert "`provider-holdout`" in markdown, markdown
     assert "ready to claim world-class: `false`" in markdown, markdown
+    assert "ledger completion required: `true`" in markdown, markdown
     print(json.dumps({"ok": True}, ensure_ascii=False, indent=2))