diff --git a/AGENTS.md b/AGENTS.md
index 223cb817..1fedfd40 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -48,6 +48,7 @@ python3 scripts/render_world_class_submission_review.py . --generated-at "$GENER
 python3 scripts/render_world_class_operator_runbook.py . --generated-at "$GENERATED_AT"
 python3 scripts/render_world_class_claim_guard.py . --generated-at "$GENERATED_AT"
 python3 scripts/render_skill_os2_coverage.py . --generated-at "$GENERATED_AT"
+python3 scripts/render_context_reports.py --generated-at "$GENERATED_AT"
 python3 scripts/render_benchmark_reproducibility.py . --generated-at "$GENERATED_AT"
 python3 scripts/render_skill_overview.py .
 python3 scripts/render_skill_interpretation.py .
@@ -60,6 +61,7 @@ python3 scripts/render_evidence_consistency.py . --generated-at "$GENERATED_AT"
 For final release evidence, commit source and generated package evidence first, then run the clean-lock reports from a clean worktree:
 
 ```bash
+python3 scripts/render_context_reports.py --generated-at "$GENERATED_AT"
 python3 scripts/render_benchmark_reproducibility.py . --generated-at "$GENERATED_AT"
 python3 scripts/render_skill_overview.py .
 python3 scripts/render_skill_interpretation.py .
diff --git a/registry/index.json b/registry/index.json
index 31ea0b4a..5af60f22 100644
--- a/registry/index.json
+++ b/registry/index.json
@@ -16,7 +16,7 @@
         "vscode"
       ],
       "package_metadata": "registry/packages/yao-meta-skill.json",
-      "package_sha256": "e44836d63020474dc3343d6325d80ea05d62c581ffe16223411e8ca36362bc6d"
+      "package_sha256": "f984a1c13df542406c8f446d9675ddefc1c80c1b286019387f5c541602a2a29c"
     }
   ]
 }
diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json
index f407a866..f2031ea9 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": "e44836d63020474dc3343d6325d80ea05d62c581ffe16223411e8ca36362bc6d",
-    "archive_sha256": "0709752db84703b213aa24bf92dedf83761571f92dc94221ae1d420f5f62e903"
+    "package_sha256": "f984a1c13df542406c8f446d9675ddefc1c80c1b286019387f5c541602a2a29c",
+    "archive_sha256": "bd4764d23c759a7e51e24eae68f9df70385156f38e6d958119556ff9635a18f3"
   },
   "compatibility": {
     "openai": "pass",
@@ -48,7 +48,7 @@
   },
   "distribution": {
     "archive_verified": true,
-    "archive_sha256": "0709752db84703b213aa24bf92dedf83761571f92dc94221ae1d420f5f62e903",
+    "archive_sha256": "bd4764d23c759a7e51e24eae68f9df70385156f38e6d958119556ff9635a18f3",
     "package_verification": "reports/package_verification.json",
     "install_simulated": true,
     "install_simulation": "reports/install_simulation.json"
diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json
index e8e1bc12..f792e823 100644
--- a/reports/architecture_maintainability.json
+++ b/reports/architecture_maintainability.json
@@ -16,7 +16,7 @@
     "watch_line_threshold": 720,
     "block_line_threshold": 1500,
     "largest_file_lines": 899,
-    "watchlist_count": 8,
+    "watchlist_count": 9,
     "hotspot_count": 0,
     "blocker_count": 0,
     "decision": "pass"
@@ -43,6 +43,13 @@
       "severity": "pass",
       "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
     },
+    {
+      "path": "scripts/render_evidence_consistency.py",
+      "lines": 804,
+      "kind": "cli-script",
+      "severity": "pass",
+      "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
+    },
     {
       "path": "scripts/skill_report_model.py",
       "lines": 801,
@@ -85,13 +92,6 @@
       "severity": "pass",
       "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
     },
-    {
-      "path": "scripts/render_evidence_consistency.py",
-      "lines": 707,
-      "kind": "cli-script",
-      "severity": "pass",
-      "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
-    },
     {
       "path": "scripts/apply_adaptation.py",
       "lines": 706,
@@ -129,6 +129,13 @@
       "severity": "pass",
       "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
     },
+    {
+      "path": "scripts/render_evidence_consistency.py",
+      "lines": 804,
+      "kind": "cli-script",
+      "severity": "pass",
+      "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
+    },
     {
       "path": "scripts/skill_report_model.py",
       "lines": 801,
diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md
index 2fceb410..01a2705b 100644
--- a/reports/architecture_maintainability.md
+++ b/reports/architecture_maintainability.md
@@ -15,7 +15,7 @@ Generated at: `2026-06-16`
 - command modules: `6`
 - largest file lines: `899`
 - watch threshold lines: `720`
-- watchlist: `8`
+- watchlist: `9`
 - hotspots: `0`
 - blockers: `0`
 
@@ -32,6 +32,7 @@ No file-size hotspots found.
 | `tests/verify_yao_cli.py` | `899` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
 | `scripts/yao_cli_parser.py` | `821` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
 | `scripts/skill_report_layout.py` | `808` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
+| `scripts/render_evidence_consistency.py` | `804` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
 | `scripts/skill_report_model.py` | `801` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
 | `tests/verify_review_studio.py` | `763` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
 | `scripts/compile_skill.py` | `734` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
@@ -45,13 +46,13 @@ No file-size hotspots found.
 | `tests/verify_yao_cli.py` | `899` | `test` | `pass` |
 | `scripts/yao_cli_parser.py` | `821` | `internal-module` | `pass` |
 | `scripts/skill_report_layout.py` | `808` | `internal-module` | `pass` |
+| `scripts/render_evidence_consistency.py` | `804` | `cli-script` | `pass` |
 | `scripts/skill_report_model.py` | `801` | `internal-module` | `pass` |
 | `tests/verify_review_studio.py` | `763` | `test` | `pass` |
 | `scripts/compile_skill.py` | `734` | `cli-script` | `pass` |
 | `scripts/build_skill_atlas.py` | `730` | `cli-script` | `pass` |
 | `scripts/optimize_description.py` | `723` | `cli-script` | `pass` |
 | `scripts/trust_check.py` | `714` | `internal-module` | `pass` |
-| `scripts/render_evidence_consistency.py` | `707` | `cli-script` | `pass` |
 | `scripts/apply_adaptation.py` | `706` | `cli-script` | `pass` |
 | `scripts/review_studio_layout.py` | `694` | `internal-module` | `pass` |
 
diff --git a/reports/context_budget.json b/reports/context_budget.json
index 9fb71409..530d7af4 100644
--- a/reports/context_budget.json
+++ b/reports/context_budget.json
@@ -1,22 +1,20 @@
 {
   "ok": true,
   "failures": [],
-  "warnings": [
-    "Deferred resource footprint is high: 442670 estimated tokens across references/scripts/evals. Keep Review Studio warnings visible until the largest resource dirs are split, archived, or justified."
-  ],
+  "warnings": [],
   "stats": {
     "context_budget_tier": "production",
     "context_budget_limit": 1000,
     "skill_body_tokens": 767,
-    "other_text_tokens": 1395152,
+    "other_text_tokens": 1404003,
     "estimated_initial_load_tokens": 960,
-    "estimated_total_text_tokens": 1395919,
-    "deferred_resource_tokens": 442670,
+    "estimated_total_text_tokens": 1404770,
+    "deferred_resource_tokens": 444818,
     "deferred_resource_warn_threshold": 120000,
     "deferred_resource_dirs": [
       {
         "path": "scripts",
-        "estimated_tokens": 393459,
+        "estimated_tokens": 395607,
         "file_count": 113
       },
       {
@@ -33,36 +31,35 @@
     "large_deferred_resource_dirs": [
       {
         "path": "scripts",
-        "estimated_tokens": 393459,
+        "estimated_tokens": 395607,
         "file_count": 113
       }
     ],
     "deferred_resource_governance": {
-      "status": "needs-review",
+      "status": "governed",
       "large_dir_count": 1,
-      "governed_large_dir_count": 0,
+      "governed_large_dir_count": 1,
       "directories": [
         {
-          "status": "needs-review",
+          "status": "governed",
           "evidence": [
             "reports/security_trust_report.json",
             "reports/architecture_maintainability.json",
             "reports/python_compatibility.json"
           ],
           "reasons": [
+            "trust report covers scripts",
             "architecture report has no script hotspots or blockers",
             "Python compatibility report has no issues"
           ],
-          "missing": [
-            "trust report covers scripts"
-          ],
+          "missing": [],
           "path": "scripts",
-          "estimated_tokens": 393459,
+          "estimated_tokens": 395607,
           "file_count": 113,
           "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
         }
       ],
-      "summary": "One or more large deferred resource directories still need explicit governance evidence."
+      "summary": "Large deferred resources are indexed and backed by evidence."
     },
     "relevant_file_count": 573,
     "unused_resource_dirs": [],
diff --git a/reports/context_budget.md b/reports/context_budget.md
index 0f44c15c..2e26705a 100644
--- a/reports/context_budget.md
+++ b/reports/context_budget.md
@@ -2,7 +2,7 @@
 
 | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
 | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
-| root | `.` | `production` | 1000 | 960 | 767 | 442670 | `needs-review` | scripts:393459 | 135.4 | - | ok |
+| root | `.` | `production` | 1000 | 960 | 767 | 444818 | `governed` | scripts:395607 | 135.4 | - | ok |
 | complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok |
 | governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok |
 
diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json
index 2c8bec4d..69afd732 100644
--- a/reports/context_budget_summary.json
+++ b/reports/context_budget_summary.json
@@ -1,5 +1,5 @@
 {
-  "generated_at": "2026-03-31",
+  "generated_at": "2026-06-16",
   "targets": [
     {
       "label": "root",
@@ -8,47 +8,44 @@
       "budget_limit": 1000,
       "initial_tokens": 960,
       "skill_body_tokens": 767,
-      "deferred_resource_tokens": 442670,
+      "deferred_resource_tokens": 444818,
       "large_deferred_resource_dirs": [
         {
           "path": "scripts",
-          "estimated_tokens": 393459,
+          "estimated_tokens": 395607,
           "file_count": 113
         }
       ],
       "deferred_resource_governance": {
-        "status": "needs-review",
+        "status": "governed",
         "large_dir_count": 1,
-        "governed_large_dir_count": 0,
+        "governed_large_dir_count": 1,
         "directories": [
           {
-            "status": "needs-review",
+            "status": "governed",
             "evidence": [
               "reports/security_trust_report.json",
               "reports/architecture_maintainability.json",
               "reports/python_compatibility.json"
             ],
             "reasons": [
+              "trust report covers scripts",
               "architecture report has no script hotspots or blockers",
               "Python compatibility report has no issues"
             ],
-            "missing": [
-              "trust report covers scripts"
-            ],
+            "missing": [],
             "path": "scripts",
-            "estimated_tokens": 393459,
+            "estimated_tokens": 395607,
             "file_count": 113,
             "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
           }
         ],
-        "summary": "One or more large deferred resource directories still need explicit governance evidence."
+        "summary": "Large deferred resources are indexed and backed by evidence."
       },
       "quality_density": 135.4,
       "unused_resource_dirs": [],
       "ok": true,
-      "warnings": [
-        "Deferred resource footprint is high: 442670 estimated tokens across references/scripts/evals. Keep Review Studio warnings visible until the largest resource dirs are split, archived, or justified."
-      ]
+      "warnings": []
     },
     {
       "label": "complex-release-orchestrator",
diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json
index 64a93145..3f791de1 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": 28.53,
+      "duration_ms": 28.19,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -62,7 +62,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 27.53,
+      "duration_ms": 26.4,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -85,7 +85,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 27.52,
+      "duration_ms": 27.25,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -113,7 +113,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 29.95,
+      "duration_ms": 29.37,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -136,7 +136,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 30.22,
+      "duration_ms": 29.61,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -164,7 +164,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 28.17,
+      "duration_ms": 26.32,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -187,7 +187,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 26.13,
+      "duration_ms": 25.92,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -214,7 +214,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 25.95,
+      "duration_ms": 26.18,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -237,7 +237,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 25.55,
+      "duration_ms": 26.51,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -266,7 +266,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 28.76,
+      "duration_ms": 26.36,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md
index 5ae5b824..033695ca 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 | 28.53 | 33 | 0.0 | pass |
-| skill-package-contract | with_skill | command | local-output-eval-runner | 27.53 | 73 | 100.0 | pass |
-| output-eval-expectation | baseline | command | local-output-eval-runner | 27.52 | 36 | 0.0 | pass |
-| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.95 | 80 | 100.0 | pass |
-| ir-before-packaging | baseline | command | local-output-eval-runner | 30.22 | 33 | 0.0 | pass |
-| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.17 | 80 | 100.0 | pass |
-| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.13 | 36 | 0.0 | pass |
-| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 25.95 | 65 | 100.0 | pass |
-| file-backed-governed-package | baseline | command | local-output-eval-runner | 25.55 | 37 | 0.0 | pass |
-| file-backed-governed-package | with_skill | command | local-output-eval-runner | 28.76 | 98 | 100.0 | pass |
+| skill-package-contract | baseline | command | local-output-eval-runner | 28.19 | 33 | 0.0 | pass |
+| skill-package-contract | with_skill | command | local-output-eval-runner | 26.4 | 73 | 100.0 | pass |
+| output-eval-expectation | baseline | command | local-output-eval-runner | 27.25 | 36 | 0.0 | pass |
+| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.37 | 80 | 100.0 | pass |
+| ir-before-packaging | baseline | command | local-output-eval-runner | 29.61 | 33 | 0.0 | pass |
+| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.32 | 80 | 100.0 | pass |
+| near-neighbor-boundary | baseline | command | local-output-eval-runner | 25.92 | 36 | 0.0 | pass |
+| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.18 | 65 | 100.0 | pass |
+| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.51 | 37 | 0.0 | pass |
+| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.36 | 98 | 100.0 | pass |
 
 ## Next Fixes
 
diff --git a/reports/package_verification.json b/reports/package_verification.json
index ccc7dea3..56f69339 100644
--- a/reports/package_verification.json
+++ b/reports/package_verification.json
@@ -8,7 +8,7 @@
     "target_count": 4,
     "adapter_count": 4,
     "archive_present": true,
-    "archive_sha256": "0709752db84703b213aa24bf92dedf83761571f92dc94221ae1d420f5f62e903",
+    "archive_sha256": "bd4764d23c759a7e51e24eae68f9df70385156f38e6d958119556ff9635a18f3",
     "archive_entry_count": 623,
     "failure_count": 0,
     "warning_count": 0
diff --git a/reports/package_verification.md b/reports/package_verification.md
index 63d85716..690ebbc1 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: `0709752db84703b213aa24bf92dedf83761571f92dc94221ae1d420f5f62e903`
+- Archive SHA256: `bd4764d23c759a7e51e24eae68f9df70385156f38e6d958119556ff9635a18f3`
 - Failures: `0`
 - Warnings: `0`
 
diff --git a/reports/registry_audit.json b/reports/registry_audit.json
index 41e1703a..a693d76c 100644
--- a/reports/registry_audit.json
+++ b/reports/registry_audit.json
@@ -21,8 +21,8 @@
     "trust_level": "local",
     "license": "MIT",
     "checksums": {
-      "package_sha256": "e44836d63020474dc3343d6325d80ea05d62c581ffe16223411e8ca36362bc6d",
-      "archive_sha256": "0709752db84703b213aa24bf92dedf83761571f92dc94221ae1d420f5f62e903"
+      "package_sha256": "f984a1c13df542406c8f446d9675ddefc1c80c1b286019387f5c541602a2a29c",
+      "archive_sha256": "bd4764d23c759a7e51e24eae68f9df70385156f38e6d958119556ff9635a18f3"
     },
     "compatibility": {
       "openai": "pass",
@@ -53,7 +53,7 @@
     },
     "distribution": {
       "archive_verified": true,
-      "archive_sha256": "0709752db84703b213aa24bf92dedf83761571f92dc94221ae1d420f5f62e903",
+      "archive_sha256": "bd4764d23c759a7e51e24eae68f9df70385156f38e6d958119556ff9635a18f3",
       "package_verification": "reports/package_verification.json",
       "install_simulated": true,
       "install_simulation": "reports/install_simulation.json"
@@ -78,7 +78,7 @@
           "vscode"
         ],
         "package_metadata": "registry/packages/yao-meta-skill.json",
-        "package_sha256": "e44836d63020474dc3343d6325d80ea05d62c581ffe16223411e8ca36362bc6d"
+        "package_sha256": "f984a1c13df542406c8f446d9675ddefc1c80c1b286019387f5c541602a2a29c"
       }
     ]
   },
diff --git a/reports/registry_audit.md b/reports/registry_audit.md
index 03330217..60e218de 100644
--- a/reports/registry_audit.md
+++ b/reports/registry_audit.md
@@ -6,8 +6,8 @@
 - Maturity: `governed`
 - Owner: `Yao Team`
 - License: `MIT`
-- Package SHA256: `e44836d63020474dc3343d6325d80ea05d62c581ffe16223411e8ca36362bc6d`
-- Archive SHA256: `0709752db84703b213aa24bf92dedf83761571f92dc94221ae1d420f5f62e903`
+- Package SHA256: `f984a1c13df542406c8f446d9675ddefc1c80c1b286019387f5c541602a2a29c`
+- Archive SHA256: `bd4764d23c759a7e51e24eae68f9df70385156f38e6d958119556ff9635a18f3`
 - Install simulated: `True`
 
 ## Compatibility
diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json
index 97c05252..1a9999a5 100644
--- a/reports/security_trust_report.json
+++ b/reports/security_trust_report.json
@@ -23,7 +23,7 @@
     "interactive_script_count": 0,
     "package_hash_scope": "source-contract-without-generated-reports",
     "package_hash_file_count": 200,
-    "package_sha256": "e44836d63020474dc3343d6325d80ea05d62c581ffe16223411e8ca36362bc6d"
+    "package_sha256": "f984a1c13df542406c8f446d9675ddefc1c80c1b286019387f5c541602a2a29c"
   },
   "failures": [],
   "warnings": [],
diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md
index 7ffb814a..77e5ae16 100644
--- a/reports/security_trust_report.md
+++ b/reports/security_trust_report.md
@@ -16,7 +16,7 @@
 - Interactive scripts: `0`
 - Package hash scope: `source-contract-without-generated-reports`
 - Package hash files: `200`
-- Package SHA256: `e44836d63020474dc3343d6325d80ea05d62c581ffe16223411e8ca36362bc6d`
+- Package SHA256: `f984a1c13df542406c8f446d9675ddefc1c80c1b286019387f5c541602a2a29c`
 
 ## Failures
 
diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json
index 7ec4ba23..de52f6a2 100644
--- a/reports/skill_atlas.json
+++ b/reports/skill_atlas.json
@@ -44,7 +44,7 @@
   },
   "catalog": {
     "workspace_root": ".",
-    "generated_at": "2026-06-13",
+    "generated_at": "2026-06-16",
     "skills": [
       {
         "name": "yao-meta-skill",
@@ -65,6 +65,7 @@
         ],
         "resources": [
           "scripts/adjudicate_output_review.py",
+          "scripts/apply_adaptation.py",
           "scripts/build_confusion_matrix.py",
           "scripts/build_skill_atlas.py",
           "scripts/check_update.py",
@@ -76,6 +77,8 @@
           "scripts/cross_packager.py",
           "scripts/diff_eval.py",
           "scripts/emit_telemetry_event.py",
+          "scripts/evidence_consistency_release.py",
+          "scripts/evidence_consistency_world_class.py",
           "scripts/export_skill_ir.py",
           "scripts/github_benchmark_scan.py",
           "scripts/governance_check.py",
@@ -129,6 +132,7 @@
           "scripts/render_world_class_evidence_ledger.py",
           "scripts/render_world_class_evidence_plan.py",
           "scripts/render_world_class_operator_runbook.py",
+          "scripts/render_world_class_preflight.py",
           "scripts/render_world_class_submission_review.py",
           "scripts/resource_boundary_check.py",
           "scripts/review_studio_action_evidence.py",
@@ -167,6 +171,8 @@
           "scripts/yao_cli_adaptation_commands.py",
           "scripts/yao_cli_config.py",
           "scripts/yao_cli_create_commands.py",
+          "scripts/yao_cli_distribution_commands.py",
+          "scripts/yao_cli_output_commands.py",
           "scripts/yao_cli_parser.py",
           "scripts/yao_cli_report_commands.py",
           "scripts/yao_cli_runtime.py",
@@ -236,8 +242,8 @@
           "report": "reports/adoption_drift_report.json",
           "risk_band": "low",
           "event_count": 1,
-          "adoption_sample_count": 1,
-          "adoption_rate": 100.0,
+          "adoption_sample_count": 0,
+          "adoption_rate": 0,
           "candidate_count": 0
         }
       },
@@ -900,7 +906,7 @@
       "name": "incident-command-governor",
       "path": "examples/governed-incident-command/generated-skill",
       "reason": "review overdue by cadence monthly",
-      "age_days": 74,
+      "age_days": 77,
       "allowed_days": 31,
       "actionable": false,
       "scope": "example"
diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json
index a752643a..0316789a 100644
--- a/reports/skill_os2_audit.json
+++ b/reports/skill_os2_audit.json
@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-06-15",
+  "generated_at": "2026-06-16",
   "skill_dir": ".",
   "summary": {
     "item_count": 15,
@@ -145,7 +145,7 @@
       "key": "benchmark-reproducibility",
       "label": "Benchmark Reproducibility",
       "status": "pass",
-      "current": "artifacts 24; missing 0; failures 3",
+      "current": "artifacts 25; missing 0; failures 3",
       "target": "Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable",
       "evidence": [
         {
@@ -197,7 +197,7 @@
       "key": "trust-security",
       "label": "Trust Security",
       "status": "pass",
-      "current": "secrets 0; scripts 110; help failures 0",
+      "current": "secrets 0; scripts 113; 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 613; install failures 0; permission failures 0",
+      "current": "zip entries 623; 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 89da79aa..9023414d 100644
--- a/reports/skill_os2_audit.md
+++ b/reports/skill_os2_audit.md
@@ -1,6 +1,6 @@
 # Skill OS 2.0 Audit
 
-Generated at: `2026-06-15`
+Generated at: `2026-06-16`
 
 ## Summary
 
@@ -21,13 +21,13 @@ Generated at: `2026-06-15`
 | Output Eval Lab | pass | 5 cases; delta 100.0; exec 10; blind 5 | with-skill/baseline, assertions, execution evidence, blind A/B, failure taxonomy | Add more real-file and adversarial holdout cases as usage grows. |
 | Provider Holdout | external-required | model-executed 0; token-observed 0 | At least one real provider-backed holdout run with observed model/timing/token metadata | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
 | 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. |
+| Benchmark Reproducibility | pass | artifacts 25; 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 110; 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 113; 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 613; 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 623; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
 | Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. |
 | Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. |
 | Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json
index c373c3bd..84c7d43e 100644
--- a/reports/skill_os2_coverage.json
+++ b/reports/skill_os2_coverage.json
@@ -245,7 +245,7 @@
       "label": "Review Studio",
       "status": "pass",
       "objective": "One HTML page supports first-pass production review across trigger, output, runtime, trust, release, and evidence actions.",
-      "current": "16 gates; decision review; warnings 4",
+      "current": "16 gates; decision review; warnings 3",
       "command": "python3 scripts/yao.py review-studio .",
       "test": "python3 tests/verify_review_studio.py",
       "evidence": [
@@ -613,7 +613,7 @@
       "label": "Evidence Consistency",
       "status": "pass",
       "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
-      "current": "31 consistency checks",
+      "current": "33 consistency checks",
       "command": "make ci-test",
       "test": "tests/verify_evidence_consistency.py",
       "evidence": [
diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md
index b4341b17..1576220d 100644
--- a/reports/skill_os2_coverage.md
+++ b/reports/skill_os2_coverage.md
@@ -29,7 +29,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
 | Trust Security | `pass` | 113 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 623; 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 4 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.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` |
 
 ## Recommended PR Coverage
@@ -48,7 +48,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
 | Registry Package Format | `pass` | registry ok True | `make ci-test` | `tests/verify_registry_audit.py` |
 | Review Studio 2.0 | `pass` | 16 review gates | `make ci-test` | `tests/verify_review_studio.py` |
 | Migration V2 Docs | `pass` | migration guide present | `make ci-test` | `docs review` |
-| Evidence Consistency | `pass` | 31 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` |
+| Evidence Consistency | `pass` | 33 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` |
 
 ## Reference Extension Tracks
 
diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json
index 0720254f..3af74f03 100644
--- a/reports/upgrade_check.json
+++ b/reports/upgrade_check.json
@@ -70,12 +70,12 @@
       {
         "field": "archive_sha256",
         "from": "",
-        "to": "0709752db84703b213aa24bf92dedf83761571f92dc94221ae1d420f5f62e903"
+        "to": "bd4764d23c759a7e51e24eae68f9df70385156f38e6d958119556ff9635a18f3"
       },
       {
         "field": "package_sha256",
         "from": "0000000000000000000000000000000000000000000000000000000000000000",
-        "to": "e44836d63020474dc3343d6325d80ea05d62c581ffe16223411e8ca36362bc6d"
+        "to": "f984a1c13df542406c8f446d9675ddefc1c80c1b286019387f5c541602a2a29c"
       }
     ]
   },
diff --git a/scripts/evidence_consistency_release.py b/scripts/evidence_consistency_release.py
index a73186a7..83d0b9b5 100644
--- a/scripts/evidence_consistency_release.py
+++ b/scripts/evidence_consistency_release.py
@@ -10,6 +10,7 @@ CLEAN_LOCK_HEADER = "For final release evidence"
 CLEAN_LOCK_END = "If `reports/benchmark_reproducibility.json`"
 
 SOURCE_REFRESH_REPORT_COMMANDS = [
+    'python3 scripts/render_context_reports.py --generated-at "$GENERATED_AT"',
     'python3 scripts/render_benchmark_reproducibility.py . --generated-at "$GENERATED_AT"',
     "python3 scripts/render_skill_overview.py .",
     "python3 scripts/render_skill_interpretation.py .",
@@ -61,6 +62,8 @@ def build_release_evidence_flow_check(skill_dir: Path) -> dict[str, Any]:
         "actual": actual,
         "paths": [
             "AGENTS.md",
+            "reports/context_budget.json",
+            "reports/context_budget_summary.json",
             "reports/benchmark_reproducibility.json",
             "reports/skill-overview.json",
             "reports/skill-interpretation.json",
diff --git a/scripts/render_evidence_consistency.py b/scripts/render_evidence_consistency.py
index ca6a893c..19c98ffa 100644
--- a/scripts/render_evidence_consistency.py
+++ b/scripts/render_evidence_consistency.py
@@ -222,6 +222,16 @@ def compare_summary_keys(
     )
 
 
+def gate_by_key(review_studio: dict[str, Any], key: str) -> dict[str, Any]:
+    gates = review_studio.get("gates")
+    if not isinstance(gates, list):
+        return {}
+    for item in gates:
+        if isinstance(item, dict) and item.get("key") == key:
+            return item
+    return {}
+
+
 def report_contract(payload: dict[str, Any]) -> dict[str, Any]:
     contract = payload.get("report_contract")
     return contract if isinstance(contract, dict) else {}
@@ -283,6 +293,48 @@ def build_report(skill_dir: Path, generated_at: str) -> dict[str, Any]:
     context_stats = nested(context_budget, ["stats"], {})
     claim_guard_summary = nested(claim_guard, ["summary"], {})
     preflight_summary = nested(world_class_preflight, ["summary"], {})
+    context_governance = (
+        context_stats.get("deferred_resource_governance", {}) if isinstance(context_stats, dict) else {}
+    )
+    if not isinstance(context_governance, dict):
+        context_governance = {}
+    large_deferred_dirs = context_stats.get("large_deferred_resource_dirs", []) if isinstance(context_stats, dict) else []
+    top_deferred = "none"
+    if isinstance(large_deferred_dirs, list) and large_deferred_dirs:
+        first = large_deferred_dirs[0] if isinstance(large_deferred_dirs[0], dict) else {}
+        top_deferred = f"{first.get('path', 'resource')} {first.get('estimated_tokens', 'n/a')}"
+    context_expected_status = "pass" if context_budget.get("ok") else "block"
+    if context_budget.get("warnings") and context_expected_status == "pass":
+        context_expected_status = "warn"
+    context_expected_detail = (
+        f"initial load {context_stats.get('estimated_initial_load_tokens', 'n/a')}/"
+        f"{context_stats.get('context_budget_limit', 'n/a')}; "
+        f"deferred {context_stats.get('deferred_resource_tokens', 'n/a')}/"
+        f"{context_stats.get('deferred_resource_warn_threshold', 'n/a')}; "
+        f"top deferred {top_deferred}; "
+        f"resource governance {context_governance.get('status', 'unknown')}; "
+        f"quality density {context_stats.get('quality_density', 'n/a')}"
+    )
+    context_gate = gate_by_key(review_studio, "context-budget")
+    compare_values(
+        checks,
+        key="review-studio-context-budget-mirror",
+        label="Review Studio mirrors context budget governance",
+        expected={
+            "status": context_expected_status,
+            "detail": context_expected_detail,
+            "evidence": REQUIRED_REPORTS["context_budget"],
+        },
+        actual={
+            "status": context_gate.get("status"),
+            "detail": context_gate.get("detail"),
+            "evidence": context_gate.get("evidence"),
+        },
+        paths=[REQUIRED_REPORTS["context_budget"], REQUIRED_REPORTS["review_studio"]],
+        detail=(
+            "Review Studio must not keep stale context warnings after context reports prove large deferred resources are governed."
+        ),
+    )
     if isinstance(benchmark_summary, dict):
         compare_values(
             checks,
diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json
index 5406929d..e6cb4627 100644
--- a/skill_atlas/catalog.json
+++ b/skill_atlas/catalog.json
@@ -1,6 +1,6 @@
 {
   "workspace_root": ".",
-  "generated_at": "2026-06-13",
+  "generated_at": "2026-06-16",
   "skills": [
     {
       "name": "yao-meta-skill",
@@ -21,6 +21,7 @@
       ],
       "resources": [
         "scripts/adjudicate_output_review.py",
+        "scripts/apply_adaptation.py",
         "scripts/build_confusion_matrix.py",
         "scripts/build_skill_atlas.py",
         "scripts/check_update.py",
@@ -32,6 +33,8 @@
         "scripts/cross_packager.py",
         "scripts/diff_eval.py",
         "scripts/emit_telemetry_event.py",
+        "scripts/evidence_consistency_release.py",
+        "scripts/evidence_consistency_world_class.py",
         "scripts/export_skill_ir.py",
         "scripts/github_benchmark_scan.py",
         "scripts/governance_check.py",
@@ -85,6 +88,7 @@
         "scripts/render_world_class_evidence_ledger.py",
         "scripts/render_world_class_evidence_plan.py",
         "scripts/render_world_class_operator_runbook.py",
+        "scripts/render_world_class_preflight.py",
         "scripts/render_world_class_submission_review.py",
         "scripts/resource_boundary_check.py",
         "scripts/review_studio_action_evidence.py",
@@ -123,6 +127,8 @@
         "scripts/yao_cli_adaptation_commands.py",
         "scripts/yao_cli_config.py",
         "scripts/yao_cli_create_commands.py",
+        "scripts/yao_cli_distribution_commands.py",
+        "scripts/yao_cli_output_commands.py",
         "scripts/yao_cli_parser.py",
         "scripts/yao_cli_report_commands.py",
         "scripts/yao_cli_runtime.py",
@@ -192,8 +198,8 @@
         "report": "reports/adoption_drift_report.json",
         "risk_band": "low",
         "event_count": 1,
-        "adoption_sample_count": 1,
-        "adoption_rate": 100.0,
+        "adoption_sample_count": 0,
+        "adoption_rate": 0,
         "candidate_count": 0
       }
     },
diff --git a/skill_atlas/stale_skills.json b/skill_atlas/stale_skills.json
index 6602e829..b57d361d 100644
--- a/skill_atlas/stale_skills.json
+++ b/skill_atlas/stale_skills.json
@@ -24,7 +24,7 @@
     "name": "incident-command-governor",
     "path": "examples/governed-incident-command/generated-skill",
     "reason": "review overdue by cadence monthly",
-    "age_days": 74,
+    "age_days": 77,
     "allowed_days": 31,
     "actionable": false,
     "scope": "example"
diff --git a/tests/verify_evidence_consistency.py b/tests/verify_evidence_consistency.py
index 9f518618..dbfa9d13 100644
--- a/tests/verify_evidence_consistency.py
+++ b/tests/verify_evidence_consistency.py
@@ -49,6 +49,7 @@ def copy_reports(dst: Path) -> None:
 
 def refresh_embedded_reports() -> None:
     script_names = [
+        "render_context_reports.py",
         "render_benchmark_reproducibility.py",
         "render_skill_os2_coverage.py",
         "render_world_class_evidence_plan.py",
@@ -60,10 +61,15 @@ def refresh_embedded_reports() -> None:
         "render_world_class_claim_guard.py",
         "render_skill_overview.py",
         "render_skill_interpretation.py",
+        "render_review_viewer.py",
+        "render_review_studio.py",
     ]
     for script_name in script_names:
+        command = [sys.executable, str(ROOT / "scripts" / script_name)]
+        if script_name != "render_context_reports.py":
+            command.append(str(ROOT))
         subprocess.run(
-            [sys.executable, str(ROOT / "scripts" / script_name), str(ROOT)],
+            command,
             cwd=ROOT,
             check=True,
             capture_output=True,
@@ -109,6 +115,7 @@ def assert_release_evidence_instructions_cover_first_class_reports() -> None:
     source_refresh = agents_text.split(source_refresh_header, 1)[1].split(clean_lock_header, 1)[0]
     clean_lock = agents_text.split(clean_lock_header, 1)[1].split("If `reports/benchmark_reproducibility.json`", 1)[0]
     for block in [source_refresh, clean_lock]:
+        assert "python3 scripts/render_context_reports.py --generated-at \"$GENERATED_AT\"" in block, block
         assert benchmark_command in block, block
         assert "python3 scripts/render_skill_interpretation.py ." in block, block
         assert "python3 scripts/render_world_class_preflight.py . --generated-at \"$GENERATED_AT\"" in block, block
@@ -147,6 +154,9 @@ def main() -> None:
     assert checks["release-evidence-flow-covers-first-class-reports"]["status"] == "pass", checks[
         "release-evidence-flow-covers-first-class-reports"
     ]
+    assert checks["review-studio-context-budget-mirror"]["status"] == "pass", checks[
+        "review-studio-context-budget-mirror"
+    ]
     assert checks["overview-benchmark-summary"]["status"] == "pass", checks["overview-benchmark-summary"]
     assert checks["interpretation-adoption-summary"]["status"] == "pass", checks["interpretation-adoption-summary"]
     assert checks["coverage-world-class-boundary"]["status"] == "pass", checks["coverage-world-class-boundary"]
@@ -306,6 +316,33 @@ def main() -> None:
         release_flow_drift_checks["release-evidence-flow-covers-first-class-reports"]
     )
 
+    context_drift_root = TMP / "context-drift-skill"
+    copy_reports(context_drift_root)
+    context_path = context_drift_root / "reports" / "context_budget.json"
+    context_payload = json.loads(context_path.read_text(encoding="utf-8"))
+    context_payload["warnings"] = ["Deferred resource footprint is high: stale test warning."]
+    context_payload["stats"]["deferred_resource_governance"]["status"] = "needs-review"
+    context_path.write_text(json.dumps(context_payload, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+    context_drift_proc = run(
+        [
+            sys.executable,
+            str(SCRIPT),
+            str(context_drift_root),
+            "--output-json",
+            str(TMP / "context_drift.json"),
+            "--output-md",
+            str(TMP / "context_drift.md"),
+            "--generated-at",
+            "2026-06-15",
+        ]
+    )
+    assert context_drift_proc.returncode == 2, context_drift_proc.stdout
+    context_drift_payload = json.loads(context_drift_proc.stdout)
+    context_drift_checks = {item["key"]: item for item in context_drift_payload["checks"]}
+    assert context_drift_checks["review-studio-context-budget-mirror"]["status"] == "fail", (
+        context_drift_checks["review-studio-context-budget-mirror"]
+    )
+
     benchmark_flow_drift_root = TMP / "benchmark-flow-drift-skill"
     copy_reports(benchmark_flow_drift_root)
     agents_path = benchmark_flow_drift_root / "AGENTS.md"