@event4u/agent-config 8.7.0 → 8.9.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (171) hide show
  1. package/.claude-plugin/marketplace.json +1 -1
  2. package/CHANGELOG.md +109 -222
  3. package/CONTRIBUTING.md +25 -0
  4. package/README.md +7 -4
  5. package/dist/agent-src/commands/agent-handoff.md +39 -2
  6. package/dist/agent-src/commands/research/deep.md +8 -0
  7. package/dist/agent-src/commands/research/report.md +7 -0
  8. package/dist/agent-src/commands/roadmap/create.md +12 -0
  9. package/dist/agent-src/commands/roadmap/process-full.md +31 -5
  10. package/dist/agent-src/contexts/communication/rules-auto/think-before-action-mechanics.md +30 -1
  11. package/dist/agent-src/contexts/execution/auto-orchestration-activation.md +1 -1
  12. package/dist/agent-src/contexts/execution/orchestration-benchmark-gate.md +28 -16
  13. package/dist/agent-src/contexts/execution/orchestration-telemetry.md +36 -5
  14. package/dist/agent-src/contexts/execution/roadmap-process-loop.md +37 -0
  15. package/dist/agent-src/contexts/execution/subagent-topologies.md +34 -0
  16. package/dist/agent-src/contexts/execution/verification-mechanics.md +9 -9
  17. package/dist/agent-src/rules/active-remediation.md +92 -0
  18. package/dist/agent-src/rules/agent-authority.md +1 -1
  19. package/dist/agent-src/rules/broken-access-control.md +106 -0
  20. package/dist/agent-src/rules/communication-through-line.md +42 -0
  21. package/dist/agent-src/rules/decision-revisit-gate.md +8 -0
  22. package/dist/agent-src/rules/delegation-policy.md +5 -0
  23. package/dist/agent-src/rules/direct-answers.md +1 -1
  24. package/dist/agent-src/rules/downstream-changes.md +1 -0
  25. package/dist/agent-src/rules/external-code-graph-interop.md +65 -0
  26. package/dist/agent-src/rules/git-history-discipline.md +18 -0
  27. package/dist/agent-src/rules/lethal-trifecta-guard.md +6 -1
  28. package/dist/agent-src/rules/minimal-safe-diff.md +66 -1
  29. package/dist/agent-src/rules/non-destructive-by-default.md +3 -0
  30. package/dist/agent-src/rules/prefer-enums-over-literals.md +65 -0
  31. package/dist/agent-src/rules/question-not-instruction.md +76 -0
  32. package/dist/agent-src/rules/senior-engineering-discipline.md +82 -0
  33. package/dist/agent-src/rules/think-before-action.md +1 -0
  34. package/dist/agent-src/rules/tool-safety.md +8 -0
  35. package/dist/agent-src/rules/untrusted-input-defense.md +87 -22
  36. package/dist/agent-src/scripts/update_roadmap_progress.ts +2 -1
  37. package/dist/agent-src/skills/accessibility-auditor/SKILL.md +19 -0
  38. package/dist/agent-src/skills/ai-code-blindspots/SKILL.md +112 -0
  39. package/dist/agent-src/skills/ai-code-blindspots/evals/triggers.json +52 -0
  40. package/dist/agent-src/skills/authz-review/SKILL.md +21 -4
  41. package/dist/agent-src/skills/code-review/SKILL.md +2 -0
  42. package/dist/agent-src/skills/command-writing/SKILL.md +53 -40
  43. package/dist/agent-src/skills/dcf-modeling/evals/domain-truth.json +29 -0
  44. package/dist/agent-src/skills/deep-reading-analyst/SKILL.md +1 -0
  45. package/dist/agent-src/skills/dependency-upgrade/SKILL.md +20 -0
  46. package/dist/agent-src/skills/design-intelligence/SKILL.md +49 -12
  47. package/dist/agent-src/skills/design-review/SKILL.md +29 -15
  48. package/dist/agent-src/skills/design-system-capture/SKILL.md +63 -24
  49. package/dist/agent-src/skills/forecasting/evals/domain-truth.json +29 -0
  50. package/dist/agent-src/skills/frontend-render-security/SKILL.md +104 -0
  51. package/dist/agent-src/skills/frontend-render-security/evals/triggers.json +52 -0
  52. package/dist/agent-src/skills/markitdown/SKILL.md +1 -0
  53. package/dist/agent-src/skills/mcp/SKILL.md +24 -0
  54. package/dist/agent-src/skills/mcp-builder/SKILL.md +9 -1
  55. package/dist/agent-src/skills/memory-consolidation/SKILL.md +55 -4
  56. package/dist/agent-src/skills/roadmap-writing/SKILL.md +46 -5
  57. package/dist/agent-src/skills/runway-cognition/evals/domain-truth.json +29 -0
  58. package/dist/agent-src/skills/scenario-modeling/evals/domain-truth.json +29 -0
  59. package/dist/agent-src/skills/secrets-management/SKILL.md +7 -0
  60. package/dist/agent-src/skills/skill-writing/SKILL.md +12 -3
  61. package/dist/agent-src/skills/subagent-orchestration/SKILL.md +27 -33
  62. package/dist/agent-src/skills/supply-chain-intake/SKILL.md +112 -0
  63. package/dist/agent-src/skills/supply-chain-intake/evals/triggers.json +52 -0
  64. package/dist/agent-src/skills/testing-anti-patterns/SKILL.md +72 -2
  65. package/dist/agent-src/skills/ui-component-architect/SKILL.md +9 -0
  66. package/dist/agent-src/skills/unit-economics-modeling/evals/domain-truth.json +40 -0
  67. package/dist/agent-src/templates/agents/agent-project-settings.example.yml +1 -1
  68. package/dist/agent-src/templates/roadmaps.md +60 -0
  69. package/dist/cli/registry.js +3 -0
  70. package/dist/cli/registry.js.map +1 -1
  71. package/dist/discovery/deprecation-report.md +1 -1
  72. package/dist/discovery/discovery-manifest.json +268 -46
  73. package/dist/discovery/discovery-manifest.json.sha256 +1 -1
  74. package/dist/discovery/discovery-manifest.summary.md +4 -4
  75. package/dist/discovery/orphan-report.md +1 -1
  76. package/dist/discovery/packs.json +18 -8
  77. package/dist/discovery/trust-report.md +11 -11
  78. package/dist/discovery/workspaces.json +16 -6
  79. package/dist/install/install.mjs +141 -3
  80. package/dist/mcp/awesome-mcp-servers.row.md +1 -1
  81. package/dist/mcp/mcp-cloudflare-catalogue.json +1 -1
  82. package/dist/mcp/registry-manifest.json +4 -4
  83. package/dist/router.json +1 -1
  84. package/dist/scripts/_lib/claude_builtin_names.js +145 -0
  85. package/dist/scripts/_lib/claude_builtin_names.js.map +1 -0
  86. package/dist/scripts/condense.js +14 -0
  87. package/dist/scripts/condense.js.map +1 -1
  88. package/dist/server/schemas/settings.js +2 -1
  89. package/dist/server/schemas/settings.js.map +1 -1
  90. package/docs/CLAIMS.md +58 -2
  91. package/docs/architecture.md +3 -3
  92. package/docs/archive/CHANGELOG-pre-8.9.0.md +306 -0
  93. package/docs/benchmark.md +113 -0
  94. package/docs/catalog.md +32 -5
  95. package/docs/contracts/command-clusters.md +18 -0
  96. package/docs/contracts/design-artifact-verification.md +124 -0
  97. package/docs/contracts/injected-block-authenticity-model.md +66 -0
  98. package/docs/contracts/mcp-tool-inventory.md +31 -30
  99. package/docs/decisions/ADR-061-corpus-grounding-layer.md +13 -0
  100. package/docs/decisions/ADR-105-automatic-subagent-orchestration.md +6 -0
  101. package/docs/decisions/ADR-116-memory-tripwire-activation-path.md +11 -2
  102. package/docs/decisions/ADR-117-subagents-auto-default-on.md +88 -0
  103. package/docs/decisions/INDEX.md +1 -0
  104. package/docs/experiences/content_creator.md +2 -0
  105. package/docs/experiences/finance.md +2 -0
  106. package/docs/experiences/founder.md +2 -0
  107. package/docs/experiences/ops.md +2 -0
  108. package/docs/featured-skills.md +2 -2
  109. package/docs/getting-started-by-role.md +1 -1
  110. package/docs/getting-started.md +1 -1
  111. package/docs/governance-advantage.md +1 -1
  112. package/docs/guidelines/agent-infra/asking-and-brevity-examples.md +27 -0
  113. package/docs/guidelines/agent-infra/emphasis-budget.md +45 -0
  114. package/docs/guidelines/agent-infra/memory-access.md +12 -0
  115. package/docs/guidelines/agent-infra/simplicity-and-goal-demos.md +151 -0
  116. package/docs/guidelines/agent-infra/tool-description-as-policy.md +35 -0
  117. package/docs/guidelines/design-canon.md +1 -0
  118. package/docs/proof.md +60 -3
  119. package/docs/release-runbook.md +138 -0
  120. package/docs/second-brain-scope.md +116 -0
  121. package/docs/succession.md +80 -0
  122. package/package.json +2 -2
  123. package/src/agent-src/scripts/update_roadmap_progress.ts +2 -1
  124. package/src/config/agent-settings.template.yml +25 -6
  125. package/src/scripts/_dispatch.bash +27 -0
  126. package/src/scripts/_lib/claude_builtin_names.ts +148 -0
  127. package/src/scripts/_lib/file_slicer.ts +117 -0
  128. package/src/scripts/_lib/lexical_index.ts +155 -0
  129. package/src/scripts/_lib/orchestration_gate.ts +12 -8
  130. package/src/scripts/_lib/orchestration_record.ts +170 -0
  131. package/src/scripts/_lib/orchestration_savings.ts +180 -0
  132. package/src/scripts/_lib/retrieval_sanitize.ts +71 -0
  133. package/src/scripts/_lib/security_lint.ts +1 -0
  134. package/src/scripts/_lib/stat_index.ts +98 -0
  135. package/src/scripts/benchmark.ts +122 -0
  136. package/src/scripts/build_proof.ts +51 -0
  137. package/src/scripts/chat_history.ts +79 -7
  138. package/src/scripts/check_memory.ts +2 -0
  139. package/src/scripts/check_quality_regression.ts +51 -0
  140. package/src/scripts/check_roadmap_trackable.ts +3 -2
  141. package/src/scripts/condense.ts +14 -0
  142. package/src/scripts/discovery_graph.ts +0 -0
  143. package/src/scripts/domain_soundness_status.ts +236 -0
  144. package/src/scripts/external_sources_denylist.json +4 -1
  145. package/src/scripts/generate_index.ts +17 -0
  146. package/src/scripts/hot_context_hook.ts +47 -2
  147. package/src/scripts/install-hooks.sh +25 -0
  148. package/src/scripts/install.ts +35 -2
  149. package/src/scripts/learning_sidecar.ts +0 -0
  150. package/src/scripts/lint_agent_skill_names.ts +29 -0
  151. package/src/scripts/lint_behavioural_eval_freshness.ts +140 -0
  152. package/src/scripts/lint_knowledge_scale.ts +4 -3
  153. package/src/scripts/lint_roadmap_complexity.ts +124 -0
  154. package/src/scripts/lint_versioned_cache.ts +195 -0
  155. package/src/scripts/mcp_server/consumer_tool_catalog.json +23 -3
  156. package/src/scripts/mcp_server/tools.ts +182 -1
  157. package/src/scripts/measure_lexical_ranking.ts +173 -0
  158. package/src/scripts/memory_lookup.ts +0 -0
  159. package/src/scripts/memory_replay.ts +285 -0
  160. package/src/scripts/orchestration_record.ts +140 -0
  161. package/src/scripts/orchestration_savings_report.ts +124 -0
  162. package/src/scripts/schemas/domain-truth.schema.json +94 -0
  163. package/src/scripts/schemas/evals.schema.json +113 -0
  164. package/src/scripts/schemas/skill.schema.json +4 -0
  165. package/src/scripts/score_domain_truth.ts +192 -0
  166. package/src/scripts/second_brain_retrieval.ts +278 -0
  167. package/src/scripts/second_brain_run.ts +341 -0
  168. package/src/scripts/second_brain_score.ts +186 -0
  169. package/src/scripts/session_memory_index.ts +94 -0
  170. package/src/scripts/skill_eval_coverage.ts +318 -0
  171. package/src/server/schemas/settings.ts +5 -2
@@ -6,7 +6,7 @@
6
6
  },
7
7
  "metadata": {
8
8
  "description": "Bootstrap shim for the event4u agent-config suite. This plugin ships ONLY the dispatcher hooks plus one install-pointer skill — ALL content (skills, rules, commands) is installed via `npx -y @event4u/agent-config init`, which writes the file projection AND registers the same hooks in ~/.claude/settings.json. DEPRECATED as a content channel; kept so the marketplace listing stays discoverable and existing installs keep working hooks.",
9
- "version": "8.7.0",
9
+ "version": "8.9.0",
10
10
  "keywords": [
11
11
  "agent-config",
12
12
  "skills",
package/CHANGELOG.md CHANGED
@@ -982,252 +982,139 @@ our recommendation order, not its support status.
982
982
  > keeps the active era under the 250-line drift cap enforced by
983
983
  > `tests/test_changelog_eras.py`.
984
984
 
985
- # Era: 8.1.x — current
985
+ # Era: pre-8.9.0 — archived
986
986
 
987
- > Started at `8.1.0`. Full entries live inline below.
988
- > The drift test caps this era at 250 lines of entry body; growth past
989
- > that forces a new era split (`# Era: 8.2.x`, etc.) — see
990
- > [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
991
-
992
- ## [8.7.0](https://github.com/event4u-app/agent-config/compare/8.6.0...8.7.0) (2026-07-08)
993
-
994
- ### Features
995
-
996
- * **settings:** validate + surface projection.rule_workspaces/rule_packs ([a27bbf5](https://github.com/event4u-app/agent-config/commit/a27bbf53c7fca206176ed6ddd38b1ec5ee11e357))
997
- * **install:** consumer Cursor/Windsurf get host-native rule surfaces ([8b68ff5](https://github.com/event4u-app/agent-config/commit/8b68ff58e9c240e41acce1f25faa51bc47f3564b))
998
- * **install:** consumer rule scoping reaches both install pipelines ([88248e4](https://github.com/event4u-app/agent-config/commit/88248e4d39bd056db133021acc0cc2b0782e78cc))
999
- * **ci:** trigger-eval presence ratchet with shrink-only grandfather allowlist ([d8f0c0d](https://github.com/event4u-app/agent-config/commit/d8f0c0dd04b3388205becf2cce30c6e0ea09197b))
1000
-
1001
- ### Bug Fixes
1002
-
1003
- * **ci:** install repo-root deps in the MCP deploy workflow ([9183c4e](https://github.com/event4u-app/agent-config/commit/9183c4e358e76b344058eb01d7f945f246a44828))
1004
-
1005
- ### Documentation
1006
-
1007
- * add frontier quality roadmaps ([bfa9315](https://github.com/event4u-app/agent-config/commit/bfa93157848bf13020a6cb3dcd06381c013fb035))
1008
- * **skills:** skill-writing names the CI-enforced trigger-eval presence gate ([464722e](https://github.com/event4u-app/agent-config/commit/464722efe83243e3ae480411d59850dac92ca1ac))
1009
-
1010
- ### Chores
1011
-
1012
- * **roadmaps:** regenerate progress dashboard ([a8f4178](https://github.com/event4u-app/agent-config/commit/a8f4178a84ef8c66408afe3d5af195ce19ccf5d0))
1013
- * **gitignore:** ignore Codex CLI interop output (.agents/, .codex/) ([8756d52](https://github.com/event4u-app/agent-config/commit/8756d5226e8760c72d6205e98b9822620d303418))
1014
- * **dist:** rebuild install bundle after settings-schema extension ([44818d4](https://github.com/event4u-app/agent-config/commit/44818d4c8ad69ec545e99820e3292f0346bb2f20))
1015
- * **roadmap:** close Phase 1b with pinned consumer-install evidence ([3a2455f](https://github.com/event4u-app/agent-config/commit/3a2455f236279390eb5a8cfe986e6b911493391c))
1016
- * **condense:** refresh stale hash for commands/upstream-contribute ([c668370](https://github.com/event4u-app/agent-config/commit/c668370663bf7272932c33b5a7874dca4b08a9db))
1017
- * **roadmaps:** composition-ratchet roadmap executed + archived; adoption roadmap sequenced next ([1bde2ea](https://github.com/event4u-app/agent-config/commit/1bde2ea00478bd1e46c4e9596c8c0cd5962b9ee1))
1018
-
1019
- Tests: 6949 (+6 since 8.6.0)
1020
-
1021
- ## [8.6.0](https://github.com/event4u-app/agent-config/compare/8.5.0...8.6.0) (2026-07-08)
1022
-
1023
- ### Features
1024
-
1025
- * **cost-routing:** tier-downshift layer — telemetry fields, category defaults, tripwires, slice inference, verify-fail escalation ([e9839f5](https://github.com/event4u-app/agent-config/commit/e9839f5a034c3a0882e8956a2a3f580b3978056a))
1026
-
1027
- ### Bug Fixes
1028
-
1029
- * **ci:** install task in the release workflow ([19072d9](https://github.com/event4u-app/agent-config/commit/19072d9bcbb6d30cd943804f287dd79c9c709167))
1030
-
1031
- ### Documentation
1032
-
1033
- * **roadmaps:** add four frontier-prompt-harvest roadmaps ([e232e34](https://github.com/event4u-app/agent-config/commit/e232e342401bd6edafda79cd64ce8ed4ff6ddd93))
1034
- * **proof:** regenerate proof.md with the backed downshift-cost-reduction claim ([6f28604](https://github.com/event4u-app/agent-config/commit/6f286048b609442be81ac60a8c64df544a369df0))
1035
- * **roadmaps:** unify tripwire engine wording on the ADR-116 path ([f4ee375](https://github.com/event4u-app/agent-config/commit/f4ee37540ea6f9724014c63be05617e4abcdaa1b))
1036
- * **adr:** pin the memory scale-tripwire activation path (ADR-116) ([7efe88a](https://github.com/event4u-app/agent-config/commit/7efe88a7cda064e659a830a2d6a70e506ab21408))
1037
- * **claims:** back downshift-cost-reduction with the routing-downshift bench run ([38f3194](https://github.com/event4u-app/agent-config/commit/38f31942b16474fcc5977f0560da435ce84a81dd))
1038
-
1039
- ### Chores
987
+ > All entries before `8.9.0` live in
988
+ > [`docs/archive/CHANGELOG-pre-8.9.0.md`](docs/archive/CHANGELOG-pre-8.9.0.md).
989
+ > The archive is read-only; git tags remain the canonical
990
+ > source for what shipped. Splitting them out of the main file
991
+ > keeps the active era under the 250-line drift cap enforced by
992
+ > `tests/test_changelog_eras.py`.
1040
993
 
1041
- * **condense:** recondense cost-routing context/command edits into dist ([33fe1a3](https://github.com/event4u-app/agent-config/commit/33fe1a353a3eef52d024079016b32b9fe02b0531))
1042
- * **contexts:** durable verdict note for cost-aware model routing ([cbff1bd](https://github.com/event4u-app/agent-config/commit/cbff1bdc7f2b0b87843283443de534c48f5ddd54))
994
+ # Era: 8.9.x — current
1043
995
 
1044
- Tests: 6943 (+7 since 8.5.0)
996
+ > Started at `8.9.0`. Full entries live inline below.
997
+ > The drift test caps this era at 250 lines of entry body; growth past
998
+ > that forces a new era split (`# Era: 8.10.x`, etc.) — see
999
+ > [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
1045
1000
 
1046
- ## [8.5.0](https://github.com/event4u-app/agent-config/compare/8.4.1...8.5.0) (2026-07-08)
1001
+ ## [8.9.0](https://github.com/event4u-app/agent-config/compare/8.8.0...8.9.0) (2026-07-10)
1047
1002
 
1048
1003
  ### Features
1049
1004
 
1050
- * **counts:** single-source every public artefact count + drift gate ([34204ed](https://github.com/event4u-app/agent-config/commit/34204ed9b1048704cf3ebb917e2abc7f952ee62a))
1051
- * **doctor:** settings-review-pending check ([f2e5198](https://github.com/event4u-app/agent-config/commit/f2e51984cc32a44792660e1ef0ad5c66ed2b859f))
1052
- * **ui:** upgrade settings-review page + pending banner ([6272721](https://github.com/event4u-app/agent-config/commit/6272721f34f0a1f01d6ef3bccd08f468448ea8f0))
1053
- * **server:** pending settings-changes routes + API contract ([bddd2c5](https://github.com/event4u-app/agent-config/commit/bddd2c5a01c8ff04a69a786de8e3f076e9788217))
1054
- * **install:** snapshot the settings surface + write the upgrade delta ([21b2ddd](https://github.com/event4u-app/agent-config/commit/21b2ddd2e05eecc9996d43ab0a380c7ec45ec105))
1055
- * **settings:** shared settings-surface flatten/delta/classify engine ([c73adb8](https://github.com/event4u-app/agent-config/commit/c73adb859eb25562e382c735fea696d10f6657c3))
1056
- * **lint:** validate routes_to + bare-invocation story; repoint atomic-command linter ([8f5a5eb](https://github.com/event4u-app/agent-config/commit/8f5a5eb56b71c2451e510948dbbdc5d1d5d2737f))
1057
- * **server:** prefill local/dry-run tests from the real user-global config ([08c3a01](https://github.com/event4u-app/agent-config/commit/08c3a01a9c022709953cf4fb68e5e1a45792687e))
1058
- * **ui:** prune nav to real surfaces; gate Project and Workspace tabs ([4b437b9](https://github.com/event4u-app/agent-config/commit/4b437b95afbaee3765c87d93defc1065d779dcfe))
1059
- * **wizard:** remember roles and pack selection across runs ([befb5aa](https://github.com/event4u-app/agent-config/commit/befb5aaf14ea7b5b76db2600e9554375f5204340))
1060
- * **settings:** standalone hub with simple/advanced tiers, search, modified badges ([6138089](https://github.com/event4u-app/agent-config/commit/613808968a63dd5ceeda26245e2d055fdd0fd86c))
1061
- * **ui:** dark-first visual system v2 with theme toggle ([6204194](https://github.com/event4u-app/agent-config/commit/6204194b4c8777260fd68bc4087500af2be44b4a))
1062
- * **wizard:** consolidate flow, add start screen, review summary, finish checklist ([d58d4a4](https://github.com/event4u-app/agent-config/commit/d58d4a4f0a063bc051573d7df95bd35344432b66))
1063
- * **wizard:** prefill installed packs and flag removals ([8cad9d3](https://github.com/event4u-app/agent-config/commit/8cad9d367ce27c4393486349ed2d1428dd2834b9))
1064
- * **cli:** add config command and init --project routing ([7a4f26a](https://github.com/event4u-app/agent-config/commit/7a4f26ad6deada4567a8fc7f04df0bc3d460760b))
1005
+ * **rules:** simplicity-first bans, own-orphan cleanup, goal-driven execution ([3e4de80](https://github.com/event4u-app/agent-config/commit/3e4de80f9d1f7ece41162503fbcd6309620bf331))
1006
+ * **design:** design-artifact-fidelity Phase 0 — verification capability + eval baseline ([da9ff3a](https://github.com/event4u-app/agent-config/commit/da9ff3a41381e6ce0e749a74fd499de28b3ee7ea))
1007
+ * **kernel:** re-land direct-answers no-duration + never-cite-the-rule (#844 content lost from main) ([2c46e7f](https://github.com/event4u-app/agent-config/commit/2c46e7f3b194ad2179b92307939d588cdb3971f3))
1008
+ * **lint:** fail skills that claim a Claude Code built-in name ([4c0cd39](https://github.com/event4u-app/agent-config/commit/4c0cd39b9a0bf604e436bbc80327b0bddf26b9e3))
1009
+ * **install:** withhold Claude Code built-in names from /name projections ([6dcba71](https://github.com/event4u-app/agent-config/commit/6dcba71bc2e5660a00c3dd7106ece65754c71633))
1010
+ * **kernel:** re-land action-authority sharpening (#840 content lost from main) ([13f244c](https://github.com/event4u-app/agent-config/commit/13f244c9bcb5d92641e5c87e3964c5d4212c8b46))
1011
+ * **domain-soundness:** deterministic domain-truth fixtures + scorer + candidate run ([dfb27a2](https://github.com/event4u-app/agent-config/commit/dfb27a2e8f1871f436bac19446d76c569f33e3c6))
1012
+ * **execution:** amend-trap, tool-tier ladder, disconfirmation search, anti-over-engineering, authoring guidelines (P2-P6) ([2e7d4d2](https://github.com/event4u-app/agent-config/commit/2e7d4d2a6210672289a50441295f84e21f4f442a))
1013
+ * **design:** same-ramp contrast, componentization threshold, async-verifier, handoff template (P3/P4/P5) ([be49527](https://github.com/event4u-app/agent-config/commit/be49527050f235d9396c14f2fe077c3c38209798))
1014
+ * **design:** diagram-type routing + geometric pre-checks + embedded register (P1/P2/P4) ([32947b8](https://github.com/event4u-app/agent-config/commit/32947b8a63abc464edeec399929b3f5605b19ddb))
1015
+ * **handoff:** verbatim-first lossless template in agent-handoff (P4) ([76a5455](https://github.com/event4u-app/agent-config/commit/76a54557fb5c366b31b72e67d726a105de9e7a74))
1016
+ * **memory:** save-successes + reference-shape + verify-then-repair + derivability (P2/P3) ([d4c6e81](https://github.com/event4u-app/agent-config/commit/d4c6e810df365c8990ef9cf75f0289f970eb4a9a))
1017
+ * **orchestration:** worker-prompt contract in subagent-orchestration (P1) ([ba65867](https://github.com/event4u-app/agent-config/commit/ba65867f28273b97c16e7799a7c68d00bc16fccd))
1018
+ * **memory:** hostile-input write-guards at persist-time (P3) ([e08287b](https://github.com/event4u-app/agent-config/commit/e08287b663a56b4f6e85d0295f6229ca59cb77da))
1019
+ * **security:** found-instructions quarantine + injection-signal taxonomy (P1/P2) ([446909a](https://github.com/event4u-app/agent-config/commit/446909a007c2f7dbffee14adf32fc6cdcef9504e))
1020
+ * **lint:** cover human-gate phase headings and exit criteria; sharpen step patterns ([68c8738](https://github.com/event4u-app/agent-config/commit/68c8738d1ee10d5b433de02eaaaf3bf3f836b826))
1021
+ * **lint:** warn on human-gate checkbox steps in roadmap complexity lint ([64c5f6c](https://github.com/event4u-app/agent-config/commit/64c5f6cbbe5be69eaf4d84c523b6b6935a351ed9))
1022
+ * **knowledge:** document slicer (B8) + external code-graph interop rule (B9) ([c09bcb9](https://github.com/event4u-app/agent-config/commit/c09bcb994577f2ed87a19b7e11b617708bf60561))
1023
+ * **memory:** seed the curated corpus from the maintainer memory index ([2422f51](https://github.com/event4u-app/agent-config/commit/2422f51e4f07d5ab2b55ab5c9bf74b5950513957))
1024
+ * **bench:** self-measuring benchmark command + Cohen's Kappa judge (B7) ([58b9687](https://github.com/event4u-app/agent-config/commit/58b96878931ef976dce92dc333a966021d3b8e08))
1025
+ * **discovery:** stat-index primitive + lazy graph rebuild skip (B5a) ([04c34c6](https://github.com/event4u-app/agent-config/commit/04c34c65bc0b08331a9d8d2a1a9fae7ee20102c6))
1026
+ * **discovery:** artefact relation-graph + `affected`/`explain` verbs (B4) ([d9ffe0b](https://github.com/event4u-app/agent-config/commit/d9ffe0bff5f8326f4e077c9b27b7f604180d8242))
1027
+ * **memory:** merge learning-sidecar verdicts into retrieve() output (B3) ([46ddf98](https://github.com/event4u-app/agent-config/commit/46ddf98e915db50e6c4b75ef5dcf5ebc13b7c721))
1028
+ * **memory:** learning-sidecar aggregator — decay + corroboration + dead-ends (B3) ([11fc4a2](https://github.com/event4u-app/agent-config/commit/11fc4a28bf5e724eb09bf5eb07e66076ebfbc689))
1029
+ * **memory:** activate the lexical index in retrieve() above the tripwire (B2) ([6d6dbe8](https://github.com/event4u-app/agent-config/commit/6d6dbe8ae8153868c33fe6f867b953ceae375158))
1030
+ * **memory:** measure lexical ranking lift — the B2 ship-gate (proven) ([9f4feb9](https://github.com/event4u-app/agent-config/commit/9f4feb923a30f0462362ef1ae25cd3d482225247))
1031
+ * **memory:** add hand-rolled BM25 + trigram lexical index (B2) ([971c86e](https://github.com/event4u-app/agent-config/commit/971c86e982a7afc2ab28424195a7783f7ce1f1e9))
1032
+ * **lint:** add versioned-cache gate (B5b) ([5bfe14a](https://github.com/event4u-app/agent-config/commit/5bfe14a78e07b9eac130ee3b8e835080752d1424))
1033
+ * **memory:** add token_budget compact read surface to retrieve_v1 ([44b8c4c](https://github.com/event4u-app/agent-config/commit/44b8c4c8d6c4e014c5a1d91219fce57dfe60bfde))
1034
+ * **security:** sanitize floor on retrieval read-surfaces (B6) ([07802d6](https://github.com/event4u-app/agent-config/commit/07802d69a8ab501435b965a5a6aa9bf86d2004f7))
1035
+ * **orchestration:** modeled cost-% for the downshift rate win ([6a4ec50](https://github.com/event4u-app/agent-config/commit/6a4ec50350cf980fe17ba888957c37c615cc68ce))
1036
+ * **hooks:** pre-push changed-TypeScript static pass (typecheck + lint) ([640b789](https://github.com/event4u-app/agent-config/commit/640b789c76a2ac1637fa50fe3917557b7789f2a5))
1037
+ * **orchestration:** recorder that emits validated telemetry per dispatch ([12aa7b1](https://github.com/event4u-app/agent-config/commit/12aa7b131c7852734df85f920f079f5f1e01357b))
1038
+ * **second-brain:** retrieval-precision harness + store + pinned report ([350e9b7](https://github.com/event4u-app/agent-config/commit/350e9b7a3534cd3030272113a06818b3e384a278))
1039
+ * **security:** harden agentic-security rules + skills (Fable5 follow-ups) ([e6fdb23](https://github.com/event4u-app/agent-config/commit/e6fdb23bd919789374a3001a7c6d89170426907a))
1040
+ * **second-brain:** paired-run harness + pinned PASS report (Phase 2) ([85c9898](https://github.com/event4u-app/agent-config/commit/85c9898bcef8dfb2439096e38531b5d904233eb8))
1065
1041
 
1066
1042
  ### Bug Fixes
1067
1043
 
1068
- * **release:** guard the Tests: footer counter against vitest recursion ([6538636](https://github.com/event4u-app/agent-config/commit/653863666e7376280046a9570a2f9c65e6ee2f12))
1069
- * **converge:** surface the live-session remedy after a plugin-cache reap ([0c84dbc](https://github.com/event4u-app/agent-config/commit/0c84dbc9923916a00f4fd4738c2089997614fe82))
1070
- * **ci:** replaces arrays, legacy-path literal, cookbook test fixture ([a300ba0](https://github.com/event4u-app/agent-config/commit/a300ba03a4a17424ac5b24bf7713e7311c47a051))
1071
- * **pack:** ship src/shared + src/server/schemas with the tarball ([39f6b66](https://github.com/event4u-app/agent-config/commit/39f6b668f14f26d8dc9e768bb8b400aa35e36039))
1072
- * **cli:** list config in the Bash help output ([72f168e](https://github.com/event4u-app/agent-config/commit/72f168ec370671a0116ed7ff1ce76e4488b52390))
1073
- * **install:** work around Claude Code flat user-command discovery regression ([af00db9](https://github.com/event4u-app/agent-config/commit/af00db98e7bf26a47a525f59a272647f5342a7e4))
1074
- * **cli:** list every dispatched command in help output ([3e366d6](https://github.com/event4u-app/agent-config/commit/3e366d63dcced166ecfe54a184baf38def2c504c))
1075
- * **wizard:** review chip overflow + dry-run apply hard floor; add browser E2E ([d5b0977](https://github.com/event4u-app/agent-config/commit/d5b09775cf1276d22624236cf49818f6d77afb04))
1044
+ * **roadmap:** accept dotted sub-phase ids in PHASE_RE ([aaa54c3](https://github.com/event4u-app/agent-config/commit/aaa54c3ab7060b3e300bac99788325848400f954))
1045
+ * **skills:** mcp and code-review opt out of slash registration ([67d261a](https://github.com/event4u-app/agent-config/commit/67d261af0c06147ca3e771b3b6d57ceec34ede63))
1046
+ * **roadmap:** live-verify PR merge state before any in-flight/merged claim ([54ae7b0](https://github.com/event4u-app/agent-config/commit/54ae7b063a0bd641a931db423264ed0b8a4452f7))
1047
+ * **cli:** rename graph verb explain→graph-explain (collides with decision-chain explain); register verbs; recompile router ([8489858](https://github.com/event4u-app/agent-config/commit/84898580de0df92ec9f2f748d26c9a455c8c2468))
1048
+ * **rules:** assign new rules to the `meta` pack, not `core` (strict discovery) ([2a4d118](https://github.com/event4u-app/agent-config/commit/2a4d118fbacaf167d5a005803ef90e9524a7c7b5))
1049
+ * **roadmap:** harden /roadmap:process-full as law + add question-not-instruction rule ([b1eee65](https://github.com/event4u-app/agent-config/commit/b1eee65f0ff386b6461b72a39cae577b6582559f))
1050
+ * **memory:** align check_memory KNOWN_TYPES with the five write-side types ([1905648](https://github.com/event4u-app/agent-config/commit/1905648dabdfb0680ea1cf610bf43e8f07abda32))
1051
+ * **memory:** concrete summary type for measure_lexical_ranking (typecheck) ([475e7be](https://github.com/event4u-app/agent-config/commit/475e7be9af36b6fd7beff717502687f7a84a3e58))
1052
+ * **memory:** drop unused import + regenerate proof.md (CI) ([e415eb6](https://github.com/event4u-app/agent-config/commit/e415eb6184b697f1bb667872d6f1b8d08dea1ce6))
1053
+ * **second-brain:** restore proof § 3 heading + noUncheckedIndexedAccess guards ([b684a6c](https://github.com/event4u-app/agent-config/commit/b684a6cd1774dfd47d720d5be4cbe32ca854e213))
1054
+ * **verify:** require a changed-files static pass before pushing source ([ba3a9b5](https://github.com/event4u-app/agent-config/commit/ba3a9b5f467c5e4621637297366a4e58f84059b2))
1055
+ * **security:** post-review nits — through-line pack + FE-render greps + lint desc ([712a338](https://github.com/event4u-app/agent-config/commit/712a3389463453d01df19c421a310ed991a1fc9f))
1056
+ * **ci:** pin publish-npm to npm 11 for Node 20 compat ([4c0ed33](https://github.com/event4u-app/agent-config/commit/4c0ed33af0229b53e423a863d9e6946a49d08868))
1076
1057
 
1077
1058
  ### Documentation
1078
1059
 
1079
- * update cross-references to nested command paths ([6ca8b56](https://github.com/event4u-app/agent-config/commit/6ca8b564f44c3631d5b4d29272679e4e65eb8c95))
1080
- * **contracts:** register Phase-4 command clusters + bare-invocation rule (ADR-114) ([9e9f3c2](https://github.com/event4u-app/agent-config/commit/9e9f3c2fc437bce9066b0f4e3259c358ee80ada4))
1081
- * document config command, init --project, wizard flow and settings hub ([d4a5df1](https://github.com/event4u-app/agent-config/commit/d4a5df1c050831f29d655775a2ad8a38b037f4bb))
1060
+ * **contracts:** document the reserved host-name floor ([7ef51e9](https://github.com/event4u-app/agent-config/commit/7ef51e99d913f1d0e3ce48dd8caefc8804612ea5))
1061
+ * **roadmap:** flip execution-discipline non-kernel phases; counts + dashboard + hashes ([9da5da5](https://github.com/event4u-app/agent-config/commit/9da5da576c08f0eae3d7577079cd4f913a7f69ca))
1062
+ * **design:** reference-over-vendor pointer + close design-mechanism harvest (P6) ([e41f45c](https://github.com/event4u-app/agent-config/commit/e41f45cdc1297a6fa4293836b5a7a5cbf43a1c00))
1063
+ * **roadmap:** record drift-audit disposition (P5); flip + archive orchestration-memory harvest ([a6caca8](https://github.com/event4u-app/agent-config/commit/a6caca8cd5857be9a188ec5c704835e11921c16e))
1064
+ * **roadmap:** blocker sweep per template rule 22 — resolve 7 non-gates, unblock ci-native Phase 1 ([fabbbc3](https://github.com/event4u-app/agent-config/commit/fabbbc320dd65be51dc552ff12bde628ee7402a6))
1065
+ * **roadmap:** flip injection-authority Phases 1-3,5; sync hashes + dashboard ([0ca2310](https://github.com/event4u-app/agent-config/commit/0ca2310b0007c15f66ed4f95e5e1260b9b6b83be))
1066
+ * **contracts:** draft injected-block authenticity model (P5, proposal only) ([0738dad](https://github.com/event4u-app/agent-config/commit/0738dad234ef545c40d0294fdc47b2b116f2c7aa))
1067
+ * **roadmap:** separate external blockers from human gates; risk-based autonomous recommendation ([dc049e1](https://github.com/event4u-app/agent-config/commit/dc049e1fe68612367c576db9fae693abf04b1cc5))
1068
+ * **roadmap:** autonomy-first authoring — human gates are the exception ([c007ac7](https://github.com/event4u-app/agent-config/commit/c007ac7db79184805d2815ff21da0c4ba7858402))
1069
+ * **memory:** name the separator-recall limit in the retrieval scope + ADR-116 ([0c8a6f8](https://github.com/event4u-app/agent-config/commit/0c8a6f8a065347e8a6a4df8b08b319ce23a6f5b5))
1070
+ * sync counts (+2 rules), CLAIMS/proof, archive completed roadmap ([101c801](https://github.com/event4u-app/agent-config/commit/101c8015532f258671af28934048bb4049e16ed4))
1071
+ * **roadmap:** mark B3 display-merge done — Phase 3 complete ([3fa451a](https://github.com/event4u-app/agent-config/commit/3fa451aff07a9d1309e594614cef5cd1868b6e15))
1072
+ * **roadmap:** mark B3 aggregator done (Phase 3 checkbox 1) ([43ba766](https://github.com/event4u-app/agent-config/commit/43ba76606659310d529cbb73b1ad1e1539f6e2fb))
1073
+ * **roadmap:** mark B2 activation done — Phase 2 complete ([89f6ae4](https://github.com/event4u-app/agent-config/commit/89f6ae448123e8a633e4e9f990ca0bae442f045c))
1074
+ * **memory:** record ADR-061 <-> FTS5 resolution for retrieval ranking (B2) ([0e54680](https://github.com/event4u-app/agent-config/commit/0e546807489e9e8c0c68e8db45fe661a8e3b1790))
1075
+ * **roadmap:** resolve retrieval-substrate design council pass; promote to ready ([9194898](https://github.com/event4u-app/agent-config/commit/9194898cfa0b80f2c1bd5f4b3783eaec7337c037))
1076
+ * **roadmap:** draft retrieval-substrate hardening (source-anonymous borrow) ([708ac89](https://github.com/event4u-app/agent-config/commit/708ac89d930301fbf9880e59908552d2e8b1d175))
1077
+ * **orchestration:** document dispatch_tokens + session_tier telemetry fields ([f59562a](https://github.com/event4u-app/agent-config/commit/f59562a598c610a42a16fd1ced4dfa769eab2f15))
1078
+ * **token-saving:** run the live thin-vs-eager judge — honest INCONCLUSIVE ([3ad161b](https://github.com/event4u-app/agent-config/commit/3ad161b104c1a037b22774738e9545f4b65cc0ca))
1079
+ * **claims:** repoint hidden-instruction claim to the release gate ([a41815d](https://github.com/event4u-app/agent-config/commit/a41815db830ba90e5daaa512f6b55b6ee8be4f81))
1080
+ * **orchestration:** wire the recorder into the emit procedure + delegation-policy ([69042ad](https://github.com/event4u-app/agent-config/commit/69042ad1568bd9e16a520e63c91744cd385567a1))
1081
+ * **proof:** regenerate proof page for the new hidden-instruction claim ([45f5a7a](https://github.com/event4u-app/agent-config/commit/45f5a7a106c4c5c5b3b003ed3c3fd8e6be4f8425))
1082
+ * **claims:** bind the hidden-instruction CI scan to the claims ledger ([55fe74e](https://github.com/event4u-app/agent-config/commit/55fe74ed2122959d465b9fcc4f2fc6daffd30445))
1083
+ * **second-brain:** publish the retrieval-precision result across the surfaces ([3ee930a](https://github.com/event4u-app/agent-config/commit/3ee930a4bc61e3f1c01c7a02b204099f96042e2a))
1084
+ * **frontier-quality:** Phase 0 metrics + provenance + contract + pilot proposal ([0e738fb](https://github.com/event4u-app/agent-config/commit/0e738fb32a4645f499055940e386295b265fdc8d))
1085
+ * **second-brain:** publish the measured recall lift + decline the export ([8fbaeaf](https://github.com/event4u-app/agent-config/commit/8fbaeaf0fa8a361d9b469dad4d8046d677b4c9a7))
1082
1086
 
1083
1087
  ### Refactoring
1084
1088
 
1085
- * **scripts:** retire py2ts parity rationale from all src/scripts comments ([4ec6f07](https://github.com/event4u-app/agent-config/commit/4ec6f07c5e36240c572426ff8e17ae857efc2ba4))
1086
- * **commands:** nest 19 flat commands into Phase-4 clusters ([fa918c2](https://github.com/event4u-app/agent-config/commit/fa918c23d99f1b1100210be6757906bbcc68153f))
1089
+ * **skill:** extract topology hints from subagent-orchestration to context ([4918ef2](https://github.com/event4u-app/agent-config/commit/4918ef2372d7cb2c6e24a71ba9e3307946426899))
1087
1090
 
1088
1091
  ### Tests
1089
1092
 
1090
- * **budget:** align fixtures with the re-anchored mcp_schemas cap ([fa3c93f](https://github.com/event4u-app/agent-config/commit/fa3c93f637e751dc31bd6cc2b3b71a740fca33f1))
1091
-
1092
- ### Chores
1093
-
1094
- * **counts:** re-sync prose counts after the main merge (172 commands) ([1042fad](https://github.com/event4u-app/agent-config/commit/1042fad691a0c2c3aa01079ef21654e816565863))
1095
- * **hygiene:** fix stale references, triage claims debt, revive Tests: footer ([2379d4b](https://github.com/event4u-app/agent-config/commit/2379d4bf1821c0cbcb11d1ca919677a65bce86bf))
1096
- * **roadmaps:** land the inbox-consolidation roadmap set (council 2026-07-08) ([f25b3bb](https://github.com/event4u-app/agent-config/commit/f25b3bb4a6fa68444e79e0cca80b2c3813bd3484))
1097
- * regenerate dist, projections, catalogs, and pack manifests ([fa45778](https://github.com/event4u-app/agent-config/commit/fa45778ada09381701222a12be064932bb572c7d))
1098
- * **bench:** re-anchor kernel-prefix snapshot after main's commit-policy edit ([98ee05a](https://github.com/event4u-app/agent-config/commit/98ee05a18736d016361d7dab88373b819ff1922e))
1099
- * **bench:** refresh token baseline after run_tests exec pilot ([140697e](https://github.com/event4u-app/agent-config/commit/140697e177672805319fe2425c7e641d266c0843))
1100
- * **budget:** re-anchor mcp_schemas.gpt cap after run_tests exec pilot ([0b49bd4](https://github.com/event4u-app/agent-config/commit/0b49bd4bd389ead796a59eb61c29b5fcc584d520))
1101
- * **kernel:** ADR-114 — commit-policy Iron-Law override ([edabc87](https://github.com/event4u-app/agent-config/commit/edabc8753c218ed1661ccd664a7ce513b7f0b34b))
1102
- * **matrix:** regenerate file-ownership matrix (new files from branch + main merge) ([8a88564](https://github.com/event4u-app/agent-config/commit/8a88564c7f01d2bfe5e35287e55ad0b1fca655f8))
1103
- * **roadmap:** allow-pragma for historical council output path ([67076a4](https://github.com/event4u-app/agent-config/commit/67076a46c3228752bea11a050fb193e695e5b04c))
1104
- * **docs:** add required stability frontmatter to surface-matrix contract ([e16a998](https://github.com/event4u-app/agent-config/commit/e16a998b499a8cdcdfc1a5f2f20d66c5031fe5b5))
1105
- * **tiers:** register mcp_exec cluster (lab) in surface-tiers.yml ([55c3eda](https://github.com/event4u-app/agent-config/commit/55c3eda9c3fd148bae3b620c7214cfaa69ec9eb3))
1106
- * **lint:** re-bump leakage allowlist lines after main's content sweep ([c2843ae](https://github.com/event4u-app/agent-config/commit/c2843ae9943305915ddf57ddad971f4e5aaf7799))
1107
- * **index:** regenerate agents/index.md + docs/catalog.md after main merge ([2b85d9c](https://github.com/event4u-app/agent-config/commit/2b85d9c9aeb53b84f1be5473c835dd54ba73bb16))
1108
- * **build:** regenerate install bundle (flat-command wrappers + packs lockfile) ([9952ae1](https://github.com/event4u-app/agent-config/commit/9952ae1512a1b4a0c76151b26fdf5a12632e1344))
1109
- * **roadmap:** add + archive road-to-setup-experience (all phases shipped) ([54f01e5](https://github.com/event4u-app/agent-config/commit/54f01e5ad8ae37e277103973f93abd38c46e476e))
1110
-
1111
- Tests: 6936
1112
-
1113
- ## [8.4.1](https://github.com/event4u-app/agent-config/compare/8.4.0...8.4.1) (2026-07-08)
1114
-
1115
- ### Bug Fixes
1116
-
1117
- * **package:** ship src/install + agent-src script trees; gate imports at prepack ([77d53bc](https://github.com/event4u-app/agent-config/commit/77d53bcb2e14da1cff308cd0a8dd5d11d8783d5b))
1118
-
1119
- ## [8.4.0](https://github.com/event4u-app/agent-config/compare/8.3.0...8.4.0) (2026-07-08)
1093
+ * **memory:** land the Phase 0-pre substrate-validation foundations ([474df9a](https://github.com/event4u-app/agent-config/commit/474df9af95f8edd2ba10d6ba7ff88465a534d12d))
1120
1094
 
1121
- ### Features
1122
-
1123
- * **hooks:** surface-probe SessionStart concern — runtime self-detection ([934f8ae](https://github.com/event4u-app/agent-config/commit/934f8aef6563c53f77937f8d942b5dfd2310cd6b))
1124
- * **converge:** consented duplicate-surface cleanup command ([9b35d00](https://github.com/event4u-app/agent-config/commit/9b35d00dd88b747503cb728502b8b5f288fb325a))
1125
- * **surface-matrix:** machine-checked per-tool canonical-surface inventory ([cf8e932](https://github.com/event4u-app/agent-config/commit/cf8e932a4ca42d1d83d87b585098e39157467955))
1126
- * **plugin:** strip Claude Code plugin to bootstrap shim ([4d1900b](https://github.com/event4u-app/agent-config/commit/4d1900b25bddcf8b0d67858ad7126c279c7522f5))
1127
-
1128
- ### Bug Fixes
1129
-
1130
- * **hooks:** surface-probe honors replay mode; fix spy typing in test ([e3900c9](https://github.com/event4u-app/agent-config/commit/e3900c99814cdc371ae5b99ddc9ead09fb2f31cc))
1131
-
1132
- ### Documentation
1133
-
1134
- * **context:** unbreak path literal in augment parity note (check-refs) ([d15e4b0](https://github.com/event4u-app/agent-config/commit/d15e4b08a4a5e76cfead11a02d76e4db680186c4))
1135
- * **roadmap:** archive install-path-convergence; spawn delist-checkpoint follow-up ([228b727](https://github.com/event4u-app/agent-config/commit/228b72758b938d3c4fdeaee3bbb42a278aa83e27))
1136
- * **context:** record Augment surface-parity evidence gate outcome ([9144fc1](https://github.com/event4u-app/agent-config/commit/9144fc18b0eaab9e513180a3cf7dba06984b58ca))
1137
-
1138
- ## [8.3.0](https://github.com/event4u-app/agent-config/compare/8.2.0...8.3.0) (2026-07-08)
1139
-
1140
- ### Features
1141
-
1142
- * **ci:** add release.yml — merge a `release`-labeled PR to cut a release ([742aa91](https://github.com/event4u-app/agent-config/commit/742aa91c8dc3686a1618291dd425efbc1a69ac13))
1143
- * **release:** add --ci mode to release.ts for the label-triggered CI path ([2fc9db6](https://github.com/event4u-app/agent-config/commit/2fc9db6b98fa998a03e68c0e2ce676c40d63c6e8))
1144
- * **mcp:** ship the run_tests shell-exec pilot under a compiled safety envelope ([598a8a4](https://github.com/event4u-app/agent-config/commit/598a8a49f05f5e9ebd4c0c531a5424f079eb16b6))
1145
- * **guardrails:** hook-matrix single source, golden smoke, doctor-last upgrade step (Phase 4) ([d3ddd37](https://github.com/event4u-app/agent-config/commit/d3ddd37aa9f72dd65cebd54985e121d05a8bc0e6))
1146
- * **mcp:** implement the 8 council-approved Phase 4 tools (17 implemented total) ([71f4074](https://github.com/event4u-app/agent-config/commit/71f4074b1b065dd455b361959322ae18c11e0d6d))
1147
- * **doctor+docs:** plugin retirement — duplicate-surface/hook-wiring checks, migration flow, docs sweep (Phase 3) ([3f6234d](https://github.com/event4u-app/agent-config/commit/3f6234d82730d0210d72c5712ca49a84fb160c0e))
1148
- * **upgrade:** register managed hooks on global deploy; decouple upgrade steps (Phase 2) ([9c06cdb](https://github.com/event4u-app/agent-config/commit/9c06cdba7622691ed8c6b175fbc0f32b975db311))
1149
- * **install:** managed Claude hook registration in settings.json (Phase 1) ([f1a7644](https://github.com/event4u-app/agent-config/commit/f1a7644b89a4da1e67b95cf8dc15eda778f4dc67))
1150
-
1151
- ### Bug Fixes
1152
-
1153
- * **scripts:** make upstream-remote wiring idempotent in mcp_registry_submit ([b1c5ee1](https://github.com/event4u-app/agent-config/commit/b1c5ee18105cc2845e66b3595743dfe673292f8c))
1154
- * **roadmap:** correct mcp-cloud-endpoints doc path in Phase 6 step text ([65ab1d6](https://github.com/event4u-app/agent-config/commit/65ab1d6611edd63242b3f334c4233087975d45b0))
1155
- * **ci:** static yaml import + createRequire banner; no unchecked step indexing ([98c71c0](https://github.com/event4u-app/agent-config/commit/98c71c0f88c5e696dd0b5d00ed0e6a38c48717a1))
1156
- * **mcp:** use process.stdout.write instead of console.log in glama drift lint ([80b53fe](https://github.com/event4u-app/agent-config/commit/80b53fea3f52f486395ebb9a7ede4ea583014b55))
1157
- * **mcp:** fix stale glama build docs and dead pycache artifacts ([ea1cece](https://github.com/event4u-app/agent-config/commit/ea1cece30c097846f3475ac51211a2854223cae8))
1158
- * **install:** accept --no-ui in the bash orchestrator (unblocks upgrade) ([a519b34](https://github.com/event4u-app/agent-config/commit/a519b34f9618c5c165d0bcc5c6ea04d7ce141361))
1159
- * **release:** era-split gate measures the post-release state the drift test sees ([572e6ce](https://github.com/event4u-app/agent-config/commit/572e6ce83b74d37112213cb790c3a07a1d4e0968))
1160
-
1161
- ### Documentation
1162
-
1163
- * **release:** document the dual release path; fix stale release.py refs ([9ae0aee](https://github.com/event4u-app/agent-config/commit/9ae0aeed403376581d656b2682c6009694e9d1b1))
1164
- * **adr:** ADR-113 — CI-native release, label trigger, bot-PR-approval finding ([7af715c](https://github.com/event4u-app/agent-config/commit/7af715cc0753fbb77facf904101c317f271863e1))
1165
- * **mcp:** Phase 6 — ADR-112 stdio-lite verdict, cloud-scope note, fresh counts ([c6fe3ed](https://github.com/event4u-app/agent-config/commit/c6fe3ed07689b82ea349beb377bd4cf97ceddaca))
1166
- * **context:** Phase 0 hook+agent parity findings — settings.json parity CONFIRMED ([b22bc38](https://github.com/event4u-app/agent-config/commit/b22bc38412d76315d4406f41fbd746a70952cdbb))
1167
- * **roadmap:** add road-to-claude-code-single-surface (council 2026-07-07, Option B projection-primary) ([cb283c3](https://github.com/event4u-app/agent-config/commit/cb283c3c0dbc52f66337a30a8edb94e084caeda6))
1168
- * **mcp:** resolve A0 amendment signoff, run council, record write/exec cut ([323def8](https://github.com/event4u-app/agent-config/commit/323def8c0692c26408791623374d28eee512686a))
1169
- * **readme:** add troubleshooting section for install/upgrade failure modes ([ba33679](https://github.com/event4u-app/agent-config/commit/ba336790f6c8f8eac662e72ae2a408338b03b971))
1170
-
1171
- ### Chores
1172
-
1173
- * **roadmap:** archive road-to-ci-native-release; spawn first-run follow-up ([1544c3c](https://github.com/event4u-app/agent-config/commit/1544c3c3773f1eded3e3037e4abf04f66d9e5900))
1174
- * **mcp:** record registry submission, fix submit-script PR head, park roadmap to later/ ([1f8f49f](https://github.com/event4u-app/agent-config/commit/1f8f49f97d0e443141d53736beea59ea45e780e7))
1175
-
1176
- ## [8.2.0](https://github.com/event4u-app/agent-config/compare/8.1.0...8.2.0) (2026-07-07)
1177
-
1178
- ### Features
1179
-
1180
- * **hooks:** session-start self-heal for the installed pre-commit gate ([5c5fc68](https://github.com/event4u-app/agent-config/commit/5c5fc68e7d79717746618cad61ee9acd29669515))
1181
- * **upgrade:** re-stamp our installed pre-commit hook; doctor: mcp-beta gates skip in consumers ([c736ae9](https://github.com/event4u-app/agent-config/commit/c736ae9dfd3837bc96c999f2eccb2bce096d629b))
1182
- * **dispatch:** add roadmap:archive — /create-pr § 1c instructed a command that did not exist ([0ec1af2](https://github.com/event4u-app/agent-config/commit/0ec1af20ed184e25513a0f79f804d2b62eab7b5c))
1183
- * **doctor:** claude-plugin staleness check ([82fc8ef](https://github.com/event4u-app/agent-config/commit/82fc8ef4868d1789ac7d0423b04a3f71a1966e20))
1184
- * **upgrade:** refresh optional Claude Code plugin and skip wizard ([f2c6cc5](https://github.com/event4u-app/agent-config/commit/f2c6cc5a9a11ff95011894aeb4197b0f46721704))
1185
- * **quality:** local_auto_run defaults to false — quality tools run on demand only ([1cecb58](https://github.com/event4u-app/agent-config/commit/1cecb583ed7bdca8d0b5edd49f731dad9b9cb250))
1186
- * **upgrade:** sync existing settings files against the new template after upgrade ([4b36117](https://github.com/event4u-app/agent-config/commit/4b361177c033f0dcac76f2a303f31ef70a22f1a3))
1187
- * **settings:** balanced preset fills discipline_profile=auto (lift only where measured) ([1d3d304](https://github.com/event4u-app/agent-config/commit/1d3d3042d7430505b30ab4a3f78106a136ba8449))
1188
- * **settings:** P2 verdict — vendor-granular unknown_defaults; gpt-5-mini measured null ([16544d5](https://github.com/event4u-app/agent-config/commit/16544d524f227eff35d679094ec91f7b8a09ca6f))
1189
-
1190
- ### Bug Fixes
1191
-
1192
- * **ci:** regenerate install bundle; trim work/implement-ticket descriptions under the 200-char cap ([1ca779b](https://github.com/event4u-app/agent-config/commit/1ca779b2521820da0cea0f114ec30b2473ad56f2))
1193
- * **content:** stale Python-era instructions swept off the agent surfaces ([4f7f4a8](https://github.com/event4u-app/agent-config/commit/4f7f4a86c30dc3bdad79e65184cf526a38203434))
1194
- * **scripts:** realpath-aware CLI entry guards — symlinked invocations silently no-op'd ([0fa2f03](https://github.com/event4u-app/agent-config/commit/0fa2f03e7c7faabd2faad3e39b44160a22b5dd76))
1195
- * **hooks:** prefer the package's own tsx over npx in twin-spawn resolution ([b1f8b7e](https://github.com/event4u-app/agent-config/commit/b1f8b7e9bbc71470c16881a195a329039175f640))
1196
- * **pack:** ship tests/fixtures/hooks — hooks:replay named payloads 404'd on installs ([a6db852](https://github.com/event4u-app/agent-config/commit/a6db852dc2873b30cd5613a56436f5269377f7bd))
1197
- * **roadmap:** fall back to the git toplevel when cwd has no agents/roadmaps ([a04505a](https://github.com/event4u-app/agent-config/commit/a04505a7e0b6a7b0e77cd940e1447eb9b6f12a44))
1198
- * **council:** anchor the prices file to the project root, not the installed package ([4ab8cc2](https://github.com/event4u-app/agent-config/commit/4ab8cc2d4bff5a06554b9fc8e260f49e6606a936))
1199
- * **templates:** consumer hooks + CI workflows off python3 — gates were silently dead since py2ts ([6c36d8d](https://github.com/event4u-app/agent-config/commit/6c36d8d83c40fc4065b1308985ad8fd6d0d1d021))
1200
- * **dispatch:** ship tsx as runtime dependency — consumer hooks and TS commands broke via npx fallback ([0119de6](https://github.com/event4u-app/agent-config/commit/0119de6cabafa10fa85b51d92ab6fcafe313745a))
1201
- * **install:** launch setup wizard detached and show version on completion ([f043ad7](https://github.com/event4u-app/agent-config/commit/f043ad752067d6770c3f7d36bb829995c46ff7e7))
1202
-
1203
- ### Documentation
1204
-
1205
- * **claude-code:** correct plugin install commands, frame plugin as optional ([1b89b2d](https://github.com/event4u-app/agent-config/commit/1b89b2d261ccc42d3205a705aa2239ded6b0bf79))
1206
- * **quality:** gate quality-pipeline runs behind local_auto_run across skills, rules, and commands ([ce9fefd](https://github.com/event4u-app/agent-config/commit/ce9fefd10a47cd9144e6bf0de29a22a4a974ce62))
1207
- * **benchmark:** pin the failed P2 replication; three-host evidence ledger ([a77c476](https://github.com/event4u-app/agent-config/commit/a77c4765f221005f59165a67e215ac6bdc03c9d8))
1208
-
1209
- ### Chores
1210
-
1211
- * **packs:** regenerate meta pack README after description trim ([96beffb](https://github.com/event4u-app/agent-config/commit/96beffb350d29503b8ab12a6de177c6c8137f332))
1212
- * **condense:** propagate the Python-reference sweep into the condensed projections ([b63bc0a](https://github.com/event4u-app/agent-config/commit/b63bc0a31fe2ad42ba37db701d6b4a935a555783))
1213
- * **deps:** regenerate lockfile — tsx now a runtime dependency ([68a383d](https://github.com/event4u-app/agent-config/commit/68a383da386095e6fd740b230ac4042e08a8a152))
1214
- * **condense:** mark 15 hash-stale command projections as done ([585939d](https://github.com/event4u-app/agent-config/commit/585939d956f5d999e97ab788bd509d642767d512))
1215
- * **changelog:** perform the era split the 8.1.0 release missed ([96b43ba](https://github.com/event4u-app/agent-config/commit/96b43baa81488084740d6c4ae479ee0d0d5e563a))
1216
- * **sync:** mirror the P2 resolver changes into the dist work-engine lib ([920158b](https://github.com/event4u-app/agent-config/commit/920158b6d619a43fdb3ba63a374a84e6da011440))
1217
-
1218
- ### Other
1219
-
1220
- * **install:** named ChildProcess type import (eslint consistent-type-imports) ([34ec4fc](https://github.com/event4u-app/agent-config/commit/34ec4fc6206e0018b4dc559a19375017d6a8a669))
1221
-
1222
- ## [8.1.0](https://github.com/event4u-app/agent-config/compare/8.0.0...8.1.0) (2026-07-07)
1223
-
1224
- ### Features
1095
+ ### CI
1225
1096
 
1226
- * **commit-policy:** one-shot authorization is not a standing license ([259bb1b](https://github.com/event4u-app/agent-config/commit/259bb1b249063e055774c3159be8c584a2db54d3))
1097
+ * **security:** fail-closed agent-security gate on the publish path ([f8934f7](https://github.com/event4u-app/agent-config/commit/f8934f739a4f27a11e3c0bd8df7c9943ddba519f))
1098
+ * **second-brain:** wire the retrieval-precision dry-run into ci + ci-strict ([da4ec36](https://github.com/event4u-app/agent-config/commit/da4ec36e7c84765203864cb9f8e99e62aaf85e53))
1099
+ * **security:** wire lint-agent-security into CI and scan dist/agent-src ([453095f](https://github.com/event4u-app/agent-config/commit/453095f28bcf9aaa9c9419872dc732571d9971e3))
1100
+ * **consistency:** trigger required check on any workflow change ([e629624](https://github.com/event4u-app/agent-config/commit/e629624644e33fa1926c763f8b1a05c730c0fcdc))
1227
1101
 
1228
1102
  ### Chores
1229
1103
 
1230
- * **changelog:** split era 7.0.x → pre-8.0.0 ([7aea9be](https://github.com/event4u-app/agent-config/commit/7aea9be499768f7fd76949d607a6503b3324f8c0))
1104
+ * **roadmap:** add + close road-to-simplicity-and-goal-discipline ([026bf11](https://github.com/event4u-app/agent-config/commit/026bf1159e9af14cee1f76ccfa240d7f7b7076f4))
1105
+ * **roadmap:** close + archive execution-discipline-harvest (kernel content landed) ([49134d4](https://github.com/event4u-app/agent-config/commit/49134d4cb4178a7baa1cad8dbd38265b9c0d457f))
1106
+ * **roadmap:** close + archive injection-and-authority-harvest (kernel content landed) ([810df58](https://github.com/event4u-app/agent-config/commit/810df58e7b7525b781f3cf5f93a1b651a85927fc))
1107
+ * **install:** regenerate install bundle ([f167954](https://github.com/event4u-app/agent-config/commit/f1679547063d9cf6c9354c1d25d026f740445169))
1108
+ * **condense:** refresh stale hash for commands/optimize/project.md ([fa9c0ec](https://github.com/event4u-app/agent-config/commit/fa9c0ecb57653a6157a1eacdc8eba2fd77a357c5))
1109
+ * **condense:** project phases-4-7 rule/command/context edits into dist/agent-src ([7d727db](https://github.com/event4u-app/agent-config/commit/7d727db49522669d2aba3ac8e87cdbf5c9410898))
1110
+ * **tasks:** unify task test to include the vitest suite ([e0ca766](https://github.com/event4u-app/agent-config/commit/e0ca766bc7a15ebf17347ac246257d57c04bf63f))
1111
+ * **roadmap:** retrieval-substrate-hardening Phase 0 B6 done ([671f8d5](https://github.com/event4u-app/agent-config/commit/671f8d519a885bd93302d9962b3fc5c78469715a))
1112
+ * **roadmap:** record the inconclusive live judge run on token-saving Phase 0 ([2356ec8](https://github.com/event4u-app/agent-config/commit/2356ec88527366fe6122fdaeb71e0ff1284f364c))
1113
+ * **sync:** regenerate pack manifests after through-line pack move ([adde3de](https://github.com/event4u-app/agent-config/commit/adde3de8e94a7f03a6ebdc31e7837c0696b47209))
1114
+ * **roadmap:** frontier-quality Phase 0 authored (proposal, checkpoint pending) ([0912362](https://github.com/event4u-app/agent-config/commit/0912362aedf6a90ae122ad1ea4f167e741c40dae))
1115
+ * **roadmap:** close + archive second-brain-delta-proof (PASS) ([ec0909d](https://github.com/event4u-app/agent-config/commit/ec0909d78264d33e7ba71e6387ae553bd3494354))
1116
+
1117
+ Tests: 7188 (+161 since 8.8.0)
1231
1118
 
1232
1119
  # Era: pre-4.0.0 — archived
1233
1120
 
package/CONTRIBUTING.md CHANGED
@@ -93,6 +93,25 @@ task lint-skills # ./scripts-run src/scripts/skill_linter --all
93
93
  - Open the PR against `main` with a short description of the change,
94
94
  motivation, and any notes for reviewers.
95
95
 
96
+ ## Reviewability and the self-imposed gate
97
+
98
+ This is a governance standard, so the maintainer holds themselves to the same
99
+ gate as any contributor — the point is that even a solo merge goes **through**
100
+ the review floor, not around it.
101
+
102
+ - [`.github/CODEOWNERS`](.github/CODEOWNERS) routes review on the sensitive
103
+ surfaces (kernel rules, router compiler, install, hooks, claims/proof
104
+ generators, release pipeline, schemas). Branch protection is configured to
105
+ require Code-Owner review on those paths (maintainer, in GitHub → Settings →
106
+ Rules; source of truth: [`docs/contracts/branch-protection-policy.md`](docs/contracts/branch-protection-policy.md)).
107
+ - **Honest bound:** an AI adversarial-review / security gate (when enabled)
108
+ raises the floor and catches regressions and claim-drift, but it is **not**
109
+ independent human review. The bus-factor is tracked truthfully in
110
+ [`docs/succession.md`](docs/succession.md) — a bus-factor of 1 stated plainly
111
+ beats one implied to be more.
112
+ - A realistic second-reviewer on-ramp starts small (docs/claims or a single
113
+ pack), never "co-maintain the kernel on day one".
114
+
96
115
  ## Adding or editing skills, rules, and commands
97
116
 
98
117
  - Skills and rules live in `src/skills/` and `src/rules/`; commands in
@@ -276,6 +295,12 @@ which never reach a consumer.
276
295
 
277
296
  ### Release process
278
297
 
298
+ > **Inheritable runbook:** the exact, reproducible steps a second maintainer
299
+ > can follow cold — both entry points, the manual approval checkpoint, and
300
+ > recovery — live in [`docs/release-runbook.md`](docs/release-runbook.md), with
301
+ > the secret/operator-gated dependencies in [`docs/succession.md`](docs/succession.md).
302
+ > The summary below is orientation; the runbook is the source of truth.
303
+
279
304
  Releases are driven by a single command that owns the entire pipeline from
280
305
  version bump to npm publish:
281
306
 
package/README.md CHANGED
@@ -4,19 +4,21 @@
4
4
 
5
5
  [![Smoke](https://github.com/event4u-app/agent-config/actions/workflows/smoke.yml/badge.svg)](https://github.com/event4u-app/agent-config/actions/workflows/smoke.yml) [![Public install smoke (3 OS × 2 Node)](https://github.com/event4u-app/agent-config/actions/workflows/smoke-public-install.yml/badge.svg)](https://github.com/event4u-app/agent-config/actions/workflows/smoke-public-install.yml) [![npm](https://img.shields.io/npm/v/@event4u/agent-config?style=flat-square&label=npm&color=orange)](https://www.npmjs.com/package/@event4u/agent-config) [![agent-config MCP server](https://glama.ai/mcp/servers/event4u-app/agent-config/badges/score.svg)](https://glama.ai/mcp/servers/event4u-app/agent-config)
6
6
 
7
- [![Skills](https://img.shields.io/badge/Skills-264-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-95-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-172-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-87-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-29-orange?style=flat-square)](dist/agent-src/personas/) [![Advisors](https://img.shields.io/badge/Advisors-5-orange?style=flat-square)](dist/agent-src/personas/advisors/)
7
+ [![Skills](https://img.shields.io/badge/Skills-267-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-102-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-172-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-90-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-29-orange?style=flat-square)](dist/agent-src/personas/) [![Advisors](https://img.shields.io/badge/Advisors-5-orange?style=flat-square)](dist/agent-src/personas/advisors/)
8
8
 
9
9
  > **Choose your experience — developer · founder · content · agency · finance · ops. Add packs. Get a focused command set, not a 500-artefact dump.** Bring your own AI provider.
10
10
 
11
+ **Try it in 30 seconds** — drop one read-only subagent into any repo and watch it gate "done": `@production-validator check this branch is actually done`. No wizard, no lock-in, nothing else installed — the [30-second wedge ↓](#quickstart) is the whole first step. Full docs: **[event4u-app.github.io/agent-config](https://event4u-app.github.io/agent-config)**.
12
+
11
13
  **Every public claim in this README is machine-checked — [verify it yourself](docs/proof.md).** In a market that runs on unbacked headline numbers, this one binds each claim to resolvable evidence or fails its own build.
12
14
 
13
- **264 skills, 172 commands, 95 governed rules** — plus a capability router that loads the right skill on intent, and multi-agent orchestration with consensus review. The whole layer is compiled into 7+ host agents (Claude Code, Cursor, Augment, Cline, Windsurf, Copilot, Gemini) with **zero runtime daemon**.<!-- claim:no-runtime-daemon --> Six role-shaped entry paths sit on top, so any host becomes a reliable team member — without locking you to a single model or vendor.
15
+ **267 skills, 172 commands, 102 governed rules** — plus a capability router that loads the right skill on intent, and multi-agent orchestration with consensus review. The whole layer is compiled into 7+ host agents (Claude Code, Cursor, Augment, Cline, Windsurf, Copilot, Gemini) with **zero runtime daemon**.<!-- claim:no-runtime-daemon --> Six role-shaped entry paths sit on top, so any host becomes a reliable team member — without locking you to a single model or vendor.
14
16
 
15
17
  ### What's different
16
18
 
17
19
  It is both deep **and** disciplined — and honest about what it deliberately is not:
18
20
 
19
- - **Depth that routes itself** — 264 skills + 172 commands, with a capability router that loads the right one on intent, not a 500-artefact context dump.
21
+ - **Depth that routes itself** — 267 skills + 172 commands, with a capability router that loads the right one on intent, not a 500-artefact context dump.
20
22
  - **Governance on every host** — rules compiled into each tool's native format at projection time; deterministic runtime hooks added on hook-capable hosts. This config-space, host-agnostic governance is the moat ([the governance advantage](docs/governance-advantage.md) · [enforcement by host](docs/enforcement-by-host.md)).
21
23
  - **Surgical uninstall** — removes only its own keys from a shared host config (matched by JSON-pointer + SHA-256), never a neighbour tool's entries.<!-- claim:surgical-uninstall -->
22
24
  - **Pack-scoped install** — writes the active pack only, not a 500-artefact dump.
@@ -118,7 +120,8 @@ is generated from source: a claim→evidence table (every public claim binds to
118
120
  resolvable pointer, or CI fails), honest-null benchmarks *including the runs where
119
121
  the package changed nothing*, and a "verify it yourself" block you run on a fresh
120
122
  checkout. The proof page fails CI if it drifts from its sources — reproducibility
121
- is the proof.
123
+ is the proof. Browse it on the deployed docs site:
124
+ [event4u-app.github.io/agent-config](https://event4u-app.github.io/agent-config).
122
125
 
123
126
  Audit-disciplined by construction — every memory consult, decision
124
127
  key, and hook concern lands in `agents/runtime/state/` so you can replay it.
@@ -47,12 +47,31 @@ Last commit: {hash} {message}
47
47
  Roadmap: {roadmap file if active, or "none"}
48
48
  ---
49
49
 
50
+ ## User instructions (VERBATIM — highest priority)
51
+ - {every standing constraint / exclusion / correction the user gave, quoted
52
+ word-for-word, NEVER summarized — a paraphrase silently drops requirements
53
+ and causes post-handoff drift}
54
+
50
55
  ## Done
51
56
  - {1-2 sentences summarizing what was accomplished}
52
57
 
53
58
  ## Open
54
59
  - {bullet list of remaining tasks or next steps}
55
60
 
61
+ ## Resume pointer
62
+ - {the exact next action: "continue with X"}
63
+
64
+ ## Repeatable workflow (only when the work is iterative)
65
+ - Atomic unit: {the one thing repeated per iteration}
66
+ - Per-iteration steps: {1, 2, 3}
67
+ - Decision criteria: {when to stop / branch}
68
+
69
+ ## Errors + fixes
70
+ - {what failed and the fix that worked — so the new chat does not re-hit it}
71
+
72
+ ## Feedback history
73
+ - {corrections/preferences the user gave, so they are not re-violated}
74
+
56
75
  ## Key decisions
57
76
  - {important decisions made during this conversation}
58
77
 
@@ -60,6 +79,11 @@ Roadmap: {roadmap file if active, or "none"}
60
79
  - {list of files that were edited or are important for context}
61
80
  ```
62
81
 
82
+ **Verbatim-first is the load-bearing rule:** the *User instructions* and
83
+ *Feedback history* sections are preserved word-for-word and never compressed —
84
+ lossy re-summarization of the user's own constraints is the exact failure this
85
+ template prevents. Everything else (Done / Key decisions) stays concise.
86
+
63
87
  ### 3. Present to user
64
88
 
65
89
  Show the handoff prompt in a fenced code block and say:
@@ -97,8 +121,14 @@ do not auto-execute.
97
121
 
98
122
  ## Rules
99
123
 
100
- - **Keep it concise** — the prompt should be <30 lines. More context = more input tokens in the new chat.
101
- - **Only include actionable info** — skip history, reasoning, and failed attempts.
124
+ - **Concise everywhere EXCEPT the verbatim sections.** Keep Done / Key
125
+ decisions tight, but never truncate *User instructions* or *Feedback history*
126
+ to hit a line target — losing a user constraint costs far more than the
127
+ tokens. The concise-<30-line default applies to the narrative, not the
128
+ verbatim record.
129
+ - **Keep errors + fixes, drop dead-end noise.** Record what failed AND the fix
130
+ that worked (so the new chat does not re-hit it); skip reasoning chatter and
131
+ abandoned attempts that led nowhere.
102
132
  - **Branch name is critical** — always include it.
103
133
  - **Open tasks are critical** — the new chat needs to know what's left.
104
134
  - **Decisions are important** — prevents the new chat from re-asking settled questions.
@@ -123,3 +153,10 @@ do not auto-execute.
123
153
  Prefer `/agent-handoff` for planned context switches across tools or
124
154
  machines; use `/chat-history import` after a crash or fresh-chat reopen
125
155
  on the same workspace to surface prior-session context verbatim.
156
+
157
+ Three distinct mechanisms — do not conflate them:
158
+
159
+ - **handoff** (this command) — a one-shot push summary for the *next* chat;
160
+ ephemeral, copy-paste, verbatim on the user's instructions.
161
+ - **[`chat-history import`](../chat-history/import/command.md)** — pull a prior *session's* logged context into the current chat.
162
+ - **durable memory** ([`memory-consolidation`](../../../skills/memory-consolidation/SKILL.md)) — cross-*run* curated facts; a handoff is not memory, and memory is not a transcript.
@@ -92,6 +92,14 @@ Read {fields_path} to get all field definitions.
92
92
  6. Fresh-lookup-class fields (current status, versions, prices, dates)
93
93
  require a cited live source per `asking-and-brevity-examples § Volatile-fact
94
94
  freshness` — never fill from model memory.
95
+ 7. **Per-part grounding + disconfirmation (pre-write gate).** Before writing a
96
+ field, check each part of the request against what was actually retrieved —
97
+ no part is written unless a retrieved source grounds it. And run at least
98
+ one search that actively tries to **falsify** the leading hypothesis (rule
99
+ alternatives in or out), not only searches that confirm it. Distinct from
100
+ [`source-discovery-gate`](../../../../src/rules/source-discovery-gate.md)
101
+ (structural evidence) and [`verify-before-complete`](../../../../src/rules/verify-before-complete.md)
102
+ (completion evidence) — this is *research* evidence.
95
103
 
96
104
  ## Output path
97
105
  {output_path}
@@ -57,6 +57,13 @@ candidate list. Allow multi-select (e.g., *"1, 3, 5"*) plus *"none"*.
57
57
 
58
58
  ### Step 4 — Render `report.md` directly
59
59
 
60
+ Before writing, apply the **per-part grounding + disconfirmation gate**: every
61
+ part of the request must be grounded in a retrieved source before it appears in
62
+ the report, and at least one search must have actively tried to falsify the
63
+ leading hypothesis (not only confirm it). Distinct from
64
+ [`source-discovery-gate`](../../../../src/rules/source-discovery-gate.md) and
65
+ [`verify-before-complete`](../../../../src/rules/verify-before-complete.md).
66
+
60
67
  The agent itself reads each JSON + `fields.yaml` + the user's TOC
61
68
  choices, then writes `{topic_slug}/report.md`. **No `generate_report.py`
62
69
  script, no Python runtime.**