@event4u/agent-config 9.17.0 → 9.18.0

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "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.",
-    "version": "9.17.0",
+    "version": "9.18.0",
     "keywords": [
       "agent-config",
       "skills",

package/CHANGELOG.md

@@ -255,212 +255,109 @@ Entry-shape contract: [`docs/contracts/CHANGELOG-conventions.md`](docs/contracts
 > keeps the active era under the 250-line drift cap enforced by
 > `tests/test_changelog_eras.py`.
 
-# Era: 9.15.x — current
+# Era: pre-9.18.0 — archived
 
-> Started at `9.15.0`. Full entries live inline below.
+> All entries before `9.18.0` live in
+> [`docs/archive/CHANGELOG-pre-9.18.0.md`](docs/archive/CHANGELOG-pre-9.18.0.md).
+> The archive is read-only; git tags remain the canonical
+> source for what shipped. Splitting them out of the main file
+> keeps the active era under the 250-line drift cap enforced by
+> `tests/test_changelog_eras.py`.
+
+# Era: 9.18.x — current
+
+> Started at `9.18.0`. Full entries live inline below.
 > The drift test caps this era at 250 lines of entry body; growth past
-> that forces a new era split (`# Era: 9.16.x`, etc.) — see
+> that forces a new era split (`# Era: 9.19.x`, etc.) — see
 > [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
 
-## [9.17.0](https://github.com/event4u-app/agent-config/compare/9.16.0...9.17.0) (2026-08-04)
+## [9.18.0](https://github.com/event4u-app/agent-config/compare/9.17.0...9.18.0) (2026-08-04)
 
 ### Release highlights
 
 <!-- Curated head: fill before merge, keep it under 10 lines, and leave `_none_` where it is genuinely the answer. The generated log below is unchanged. -->
-- **Behaviour changes:** `/optimize:deep` is now bounded — plan-only with a schema-backed limits block, a 5-loop ceiling, a pre-registered target metric, and hard exclusions for kernel rules and stable contracts (980b4f1).
-- **Default changes + migration:** `/optimize:deep` defaults to plan-only; push/PR/loop execution now requires an explicit `--mode=execute`. No data or config migration.
-- **Security and correctness:** symlink traversal is confined in the catalog/count walkers (514189a); `ip-address` and `fast-uri` bumped past high npm-audit advisories (be9fb0f, 22887ba).
-- **Honest nulls:** no new nulls in this span — the highlight-plausibility gate itself ships here, and the false-`_none_` 9.13.0/9.14.0 heads were backfilled retroactively (491f98b).
-- **Known limitations:** _none_
+- **Behaviour changes:** rule triggers were re-cut — the brand pair is merged into one rule and the `disclaimer`/`finance` plus `secret`/`security` trigger sets are disjoined, so a prompt that used to load two rules now loads one (71c3527); `existing-ui-audit` moved its required sections back into the skill body and `references/output-and-pitfalls.md` is removed (b3cc0ad); an unknown router `tier` value now fails compilation instead of silently downgrading to tier-2 (02960bf); a new trigger-collision disposition gate lands with a reproducible census (b71e36c).
+- **Default changes + migration:** the new `planning` settings section (Gate C/R1/R2) ships with defaults, so omitting it stays legal (4bd8813, 74afbf9) — no data or config migration.
+- **Security and correctness:** the `secret`/`security` trigger overlap was disjoined so a secret-shaped edit routes to exactly one floor (71c3527); round-2 review of the new gate scripts closed eight findings, two of which were fail-open — a missing `maxBuffer` switched R2 off on large PRs, and the documented `planning.completion_review: false` escape hatch was read by nobody (8a2bf76).
+- **Honest nulls:** the R2 review of the merge scope returned a binding honest-null (6c6fc15); the Stage-A metrics protocol is pre-registered but unmeasured, so no effectiveness claim ships with it (01323d1); an honest-null verdict no longer suppresses the risk-table checks it previously masked (65fe441).
+- **Known limitations:** R2 (completion review) has **no blocking path in this release** — every wired call site passes `--advisory`, which downgrades every violation kind including dead-scan-scope; the gate-coverage note that claimed a trippable floor was withdrawn, and teeth arrive when Stage B drops the flag (f2c6971).
 
 ### Features
 
-* **agent-handoff:** CLI-backed resume flow as the primary command surface ([0ca1ee9](https://github.com/event4u-app/agent-config/commit/0ca1ee9136263e03eff3a62aed83b4cc70aed36f))
-* **cli:** agent-config handoff — picker, launch adapters, print mode ([d88eea9](https://github.com/event4u-app/agent-config/commit/d88eea976c2752f67c6d342011904a664d9e4329))
-* **handoff:** session enumeration + deterministic handoff generator ([55d2459](https://github.com/event4u-app/agent-config/commit/55d24597150c1155379d22e37593d1c78fca3826))
-* **hooks:** one-shot handoff-context session_start concern ([9fa684d](https://github.com/event4u-app/agent-config/commit/9fa684d62800b21871b09582fb2c6f109ea03166))
-* **commands:** bound /optimize:deep — plan-only default, enforced limits ([980b4f1](https://github.com/event4u-app/agent-config/commit/980b4f18319db38b0a2c4d9bd2ab0783c17de672))
-* **release:** finding-disposition ledger with stable ids ([4428e57](https://github.com/event4u-app/agent-config/commit/4428e5788f5cc8ef6c98da1e05fd6879374f3fb8))
-* **release:** highlight plausibility gate + backfill the 9.13.0/9.14.0 heads ([491f98b](https://github.com/event4u-app/agent-config/commit/491f98b32767f5c84e0d46f5d2938fa298fb0f4b))
-* **release:** derive all four release surfaces from the changelog at head ([d947247](https://github.com/event4u-app/agent-config/commit/d9472472de75755583fd6220975e602804f46096))
-* **release:** drill — run the real step machinery against a simulated git/gh world ([a937e59](https://github.com/event4u-app/agent-config/commit/a937e5908edcf3953fc73a6a552de1a51fdc98cd))
+* **ci:** local mirror for the R2 manifest re-derivation (parity) ([3e014b2](https://github.com/event4u-app/agent-config/commit/3e014b2196a1caf8ebfc404dd492cb500acf5126))
+* **metrics:** pre-register Stage-A protocol; close + archive the roadmap ([01323d1](https://github.com/event4u-app/agent-config/commit/01323d17b03e01610c526cf34cd5134002899518))
+* **ci:** enforce R1 + advisory R2 at pre-push and CI, register gate coverage ([21810f2](https://github.com/event4u-app/agent-config/commit/21810f2bd443310591bbaa7c83d54133477ab902))
+* **gates:** wire C/R1/R2 into the authoring and delivery surfaces ([3622d09](https://github.com/event4u-app/agent-config/commit/3622d09d4154e97fb2736cf5f08dc8eb2f7e0ba1))
+* **gates:** R1/R2 validators, R2 reviewer dispatcher, R1 annotation helper ([37389c9](https://github.com/event4u-app/agent-config/commit/37389c9ef8ae7420eaaab98484b53f362d34168b))
+* **settings:** add planning gate keys (Gate C/R1/R2) to template + Zod schema ([74afbf9](https://github.com/event4u-app/agent-config/commit/74afbf973bd34d8572f63b8e47ae29ebeefc43b1))
+* **work-engine:** ui-fix intent — fix-lane enters the chain at apply ([f29cc7c](https://github.com/event4u-app/agent-config/commit/f29cc7cb33b6247da197348d6e0a8e74ef74617d))
+* **work-engine:** trivial-lane recall 0.60 -> 1.00 against the pre-registered corpus ([07a32d4](https://github.com/event4u-app/agent-config/commit/07a32d4985cd89cba46474d7ffabff52ccd1b497))
+* **eval:** pre-register the ui-triviality golden corpus (40 tasks, council-labelled) ([f71a41c](https://github.com/event4u-app/agent-config/commit/f71a41c821f81cd0bb78bc427e2eba47b0ac0fd4))
+* **lint:** trigger-collision disposition gate + reproducible census ([b71e36c](https://github.com/event4u-app/agent-config/commit/b71e36c317385701d3b8577770130075c1b08754))
+* **routing:** one shared trigger matcher + route:explain / route:audit CLI ([e3af5ca](https://github.com/event4u-app/agent-config/commit/e3af5cacc496228794acf5a86fe799785ddbe19d))
 
 ### Bug Fixes
 
-* **agent-handoff:** trim suggestion.trigger_context under the 240-char schema cap ([708f963](https://github.com/event4u-app/agent-config/commit/708f963e3bf674f9ec1449673608fbf413897641))
-* **deps:** bump ip-address past the SSRF advisory trio (npm audit high) ([be9fb0f](https://github.com/event4u-app/agent-config/commit/be9fb0f1f58c39570deb38ab317d159c657fc14b))
-* **deps:** bump fast-uri past GHSA-7p8r-x3mc-p8w7 (npm audit high) ([22887ba](https://github.com/event4u-app/agent-config/commit/22887badc0e18f7e3fb7301e9aa02465e02e90e5))
-* **ci:** gate the findings-artifact upload on the file, not hashFiles ([7779d55](https://github.com/event4u-app/agent-config/commit/7779d55efb79b98f7ee6dabd84ed1659db6b4ec6))
-* **security:** confine symlink traversal in the catalog/count walkers ([514189a](https://github.com/event4u-app/agent-config/commit/514189a18f44d55cd45cb6a2b5a7236365e4d0a3))
+* **gates:** stop claiming a blocking floor the advisory window does not have ([f2c6971](https://github.com/event4u-app/agent-config/commit/f2c6971913d19afe14523d460df996aa8d2adf82))
+* **metrics:** create the metrics dir before appending an outcome ([4931eda](https://github.com/event4u-app/agent-config/commit/4931eda2dd968e365b7666856353d63e14f61dfe))
+* **gates:** slug comes from git, not the CI branch env ([a8b04e1](https://github.com/event4u-app/agent-config/commit/a8b04e14dfdafdfffdd38f4966a6f04f60c175ac))
+* **settings:** planning section defaults, so omitting it is legal ([4bd8813](https://github.com/event4u-app/agent-config/commit/4bd881354fdce7f053ce4b1135a650d11ab71898))
+* **gates:** cwd decides, never an inherited GIT_DIR ([022f381](https://github.com/event4u-app/agent-config/commit/022f3819b17d3c80afbbad4b8aa30ce0f05dc5da))
+* **gates:** honest-null no longer suppresses the risk-table checks ([65fe441](https://github.com/event4u-app/agent-config/commit/65fe4418126751d2833156b5debfa17fba2d17b5))
+* **gates:** pin the diff bytes; malformed-row reporting; shared row split ([e023ac7](https://github.com/event4u-app/agent-config/commit/e023ac70df800380214dd7ade34ae266f842ae03))
+* **ci:** full history for the plan-governance gates ([323ab06](https://github.com/event4u-app/agent-config/commit/323ab068eb8f70348478127768b54273a582dc8c))
+* **metrics:** annotate helper exits on EOF instead of hanging ([6fd7fa9](https://github.com/event4u-app/agent-config/commit/6fd7fa9296b50e90d120ed7575c6cdd5c2a554f7))
+* **gates:** exclude the mandated metrics path from the review scope ([cc82999](https://github.com/event4u-app/agent-config/commit/cc82999ceb937ef58543415c9abe45b1eb073eb7))
+* **gates:** escape-aware markdown row split; scanned on every exit path ([05b4d44](https://github.com/event4u-app/agent-config/commit/05b4d44f4edffe90c305f1aa9f34ced8543c7002))
+* **gates:** close the eight script findings of round 2 — two were fail-open ([8a2bf76](https://github.com/event4u-app/agent-config/commit/8a2bf767be47c081a0f94bd5f2dd69b45cce2e28))
+* **ci,pr:** no-fetch base sha, in-script artefact selection, scope-hash re-use (R2 round-2 findings 1,3,5) ([f9102d7](https://github.com/event4u-app/agent-config/commit/f9102d7bea877822b1d82f8a1650083fab4919b0))
+* **gates:** contract §2.0/§2.6, dispatcher scope binding, precise dead-scope trigger ([cd52b53](https://github.com/event4u-app/agent-config/commit/cd52b53458d18ec9f3ad2e7e1f65067b118a2a5d))
+* **bundle,roadmaps:** drop worktree path leak; R1 adoption + corrected claims (R2 findings 3,6,7) ([54e60db](https://github.com/event4u-app/agent-config/commit/54e60dbf814614c27ce94232b8c63f0893816849))
+* **ci:** verify every review artefact, block on dead scope (R2 findings 2,8,9) ([962699d](https://github.com/event4u-app/agent-config/commit/962699d5108ca12219ecf18c1c9e19e068b210b9))
+* **gates:** bind R2 to a review-scope hash, not a head sha (R2 findings 1,2,4,5,10,11) ([8b4ec9f](https://github.com/event4u-app/agent-config/commit/8b4ec9f75b09eaac913271e6e8dd8bd365c72371))
+* **lint:** repoint the fe-design abstraction-threshold pin to its reference file ([428bbd2](https://github.com/event4u-app/agent-config/commit/428bbd2513afe15a59600752244edd72b30a74b8))
+* **lint:** escape the NUL key separator in lint_trigger_collisions ([e359256](https://github.com/event4u-app/agent-config/commit/e359256e2498719afc508625c3c46cd3f93ff155))
+* **skills:** keep required sections in existing-ui-audit's body ([b3cc0ad](https://github.com/event4u-app/agent-config/commit/b3cc0ada669c2011de9c64623680ca4664552123))
+* **config:** surgical schema + budget edits instead of whole-file JSON rewrites ([2e1b377](https://github.com/event4u-app/agent-config/commit/2e1b3776edd2c960d0c9170bee60648875acf055))
+* **router:** unknown tier value fails compilation instead of silent tier-2 downgrade ([02960bf](https://github.com/event4u-app/agent-config/commit/02960bf5e8fab4c11aafaad29b5f4b5cde52ccd2))
 
 ### Documentation
 
-* **roadmap:** close and archive road-to-package-renewal (central) ([01b7ff6](https://github.com/event4u-app/agent-config/commit/01b7ff66b7886dfed9362682fc1262b15145adaa))
-* **handoff:** regenerate index catalogs ([a12e89e](https://github.com/event4u-app/agent-config/commit/a12e89e4f56c2bac0877f6f87c79a7ebb7168210))
-* **handoff:** sync generated catalogs, contracts, and archive the roadmap ([3505bb5](https://github.com/event4u-app/agent-config/commit/3505bb522fc69d2fdc9c5c3f4abc4ab35c3727ca))
-* **roadmap:** close and archive road-to-release-truth ([e8c1200](https://github.com/event4u-app/agent-config/commit/e8c120005250cfa116194b2aad54e237a8e09d8e))
+* **review:** binding R2 honest-null for the merge scope ([6c6fc15](https://github.com/event4u-app/agent-config/commit/6c6fc15a983c8c685820c5e5eac2dd21ba0ab228))
+* **contracts:** label the terminal-before-rename rule enforced_by: none ([911505e](https://github.com/event4u-app/agent-config/commit/911505e0207ab5715894e931b45f87a065b22b8a))
+* **contracts:** name the superseded-round convention (§2.7) ([ba202e2](https://github.com/event4u-app/agent-config/commit/ba202e2dd261ea3d194799946a2dc1924024bef3))
+* **review:** close round-4 findings — 4 fixed, 0 open ([7bb24d8](https://github.com/event4u-app/agent-config/commit/7bb24d879ecc9f512f9429e3c78a88959c7b6c50))
+* **gates:** withdraw three claims that had no mechanism behind them ([2529f53](https://github.com/event4u-app/agent-config/commit/2529f53e91c68a670667ea2fa2971cc262241404))
+* **review:** close round-3 findings — 11 fixed, 1 accepted-risk ([9603e29](https://github.com/event4u-app/agent-config/commit/9603e29f610dc1566bf1931ea6daf784e9f31725))
+* **review:** R2 round-3 findings — 12 open ([7a88b1a](https://github.com/event4u-app/agent-config/commit/7a88b1af2d2283ae1b3c8866d689241a4af9dda3))
+* **review:** close round-2 findings — 11 fixed ([6f0934c](https://github.com/event4u-app/agent-config/commit/6f0934c561223a8dd4424fa109b4c8b5701d38a7))
+* **review:** close round-1 findings — 10 fixed, 1 accepted-risk ([6bc2a26](https://github.com/event4u-app/agent-config/commit/6bc2a2673daf568d39de86710625108a84a03e13))
+* **review:** R2 completion-review findings — fresh blind reviewer, 11 open ([e7d0dca](https://github.com/event4u-app/agent-config/commit/e7d0dca86111dfe52247539630f11ff21f4c3c67))
+* **contracts:** add plan-review-gates v1 — R1/R2 grammars, C-to-R1 handoff, exit codes ([aa69cdd](https://github.com/event4u-app/agent-config/commit/aa69cdd39adb4e7c12f95881a2243a785093c734))
+* **roadmap:** adjudicate advisory-gate blocker findings for plan-governance-gates ([b35b2aa](https://github.com/event4u-app/agent-config/commit/b35b2aa088e6d0236d9a28107f7726d76b9530f8))
+* **roadmap:** inline council trace per no-roadmap-references council clause ([c355c3b](https://github.com/event4u-app/agent-config/commit/c355c3b00b3a8ce031b7017bf12734908e1fd485))
+* **roadmap:** add plan-governance-gates roadmap (confidence gate + review gates) ([810caa7](https://github.com/event4u-app/agent-config/commit/810caa74529577049bc55778fe82eb5936ce79e1))
+* **evidence:** pre-register the UI-skill progressive-disclosure threshold ([0914f65](https://github.com/event4u-app/agent-config/commit/0914f65b24dd76f50ba073f375d6b0cb7d69ff2b))
+* **roadmap:** flip census + collision-lint checkboxes (landed in b71e36c31) ([f49df8b](https://github.com/event4u-app/agent-config/commit/f49df8bf766462e1a60dae3f41d2974a81bee814))
+* **roadmap:** routing-correctness — Phases 1, 2 and 4 landed ([010d733](https://github.com/event4u-app/agent-config/commit/010d73359ced4c9700ef4f40cc948216b0d6a070))
+* **commands:** routing-audit surface on /rule-compliance-audit ([61ade3f](https://github.com/event4u-app/agent-config/commit/61ade3f78f8f5956ec66413890b692055fef319d))
+
+### Refactoring
+
+* **skills:** compress the gate additions under the size threshold ([015ec87](https://github.com/event4u-app/agent-config/commit/015ec8752dc6b5bc4e0e5c9098fc34b044bc9c61))
+* **skills:** progressive disclosure for the four heavy UI reference skills ([709f010](https://github.com/event4u-app/agent-config/commit/709f0105a2b305f7c1b53ad561ceb964c5616157))
+* **rules:** merge brand pair, disjoin disclaimer/finance and secret/security triggers ([71c3527](https://github.com/event4u-app/agent-config/commit/71c35279a774a42557f91d9f769ad0bdcf2386ba))
 
 ### Tests
 
-* **release:** script the release-truth surface interactions in the drill ([6ce8025](https://github.com/event4u-app/agent-config/commit/6ce8025597c0502f25b4cd350f69d20424568d1c))
-
-### CI
-
-* **release:** wire surface-equality, highlight-plausibility, finding-dispositions ([86866ed](https://github.com/event4u-app/agent-config/commit/86866edc918f4fbe3f2b2a1f6047584e2bc78b44))
+* **gates:** cover the annotation helper and the R2 artifact parser ([72eabe0](https://github.com/event4u-app/agent-config/commit/72eabe01025f6a399ff0818b173d17c8546ed737))
 
 ### Chores
 
-* ignore worktrees ([1c97785](https://github.com/event4u-app/agent-config/commit/1c9778549a4ea2dcb5c9a63b1e1252e5584876ce))
-* **budgets:** cli_help_command_count 81 -> 82 for the handoff subcommand ([b27e14d](https://github.com/event4u-app/agent-config/commit/b27e14d2a71ec4e682fbae34eec4b710d0165022))
-
-Tests: 10692 (+104 since 9.16.0)
-
-## [9.16.0](https://github.com/event4u-app/agent-config/compare/9.15.0...9.16.0) (2026-08-03)
-
-### Release highlights
-
-<!-- Curated head: fill before merge, keep it under 10 lines, and leave `_none_` where it is genuinely the answer. The generated log below is unchanged. -->
-- **Behaviour changes:** _none_
-- **Default changes + migration:** _none_
-- **Security and correctness:** _none_
-- **Honest nulls:** _none_
-- **Known limitations:** _none_
-
-### Features
-
-* **gates:** fail the PR that moves the CLI registry without the evaluator budget ([84740f3](https://github.com/event4u-app/agent-config/commit/84740f3aba1cd7e9fd3e2fa6eb304a1ad106e149))
-
-### Chores
-
-* **deps:** bump the github-actions group across 1 directory with 5 updates ([5e272d8](https://github.com/event4u-app/agent-config/commit/5e272d89e6e9b5bcc1fff053e9448da294998221))
-
-Tests: 10588 (+8 since 9.15.0)
-
-## [9.15.0](https://github.com/event4u-app/agent-config/compare/9.14.0...9.15.0) (2026-08-03)
-
-### Release highlights
-
-<!-- Curated head: fill before merge, keep it under 10 lines, and leave `_none_` where it is genuinely the answer. The generated log below is unchanged. -->
-- **Behaviour changes:** _none_
-- **Default changes + migration:** _none_
-- **Security and correctness:** _none_
-- **Honest nulls:** _none_
-- **Known limitations:** _none_
-
-### Features
-
-* **routing:** budget-aware cheap-request delegation (budget_routing) ([c3e98dd](https://github.com/event4u-app/agent-config/commit/c3e98dda535413e6d5e40cc463f88628c8b2ff27))
-* **eval:** rules mode for the live trigger eval + weekly canary leg ([69fda7d](https://github.com/event4u-app/agent-config/commit/69fda7ddadbb60581f33ec3403609a34edaeed8b))
-* **routing:** word-boundary-anchored keyword matching ([1975323](https://github.com/event4u-app/agent-config/commit/197532342bbac44adfc1e5e486f8e485a95e1d6a))
-* **routing:** per-rule routing matrices for all 97 rules + derived coverage corpus ([f5ea58f](https://github.com/event4u-app/agent-config/commit/f5ea58f458865ad5ba60713e918acab301a76ffb))
-* **routing:** routing:doctor + composed session_start chain tests ([bc9d3a2](https://github.com/event4u-app/agent-config/commit/bc9d3a249649a4fd063d316fdc42f2f5404246e7))
-* **hooks:** daily throttle for session_start probes ([db1cdef](https://github.com/event4u-app/agent-config/commit/db1cdef2b45b7944dd056648768acb4194675d31))
-* **cli:** dispatch:hook fast path in the bin launcher ([048757d](https://github.com/event4u-app/agent-config/commit/048757dc0fc2c21cc1ea862c4690cc5cbeb03d3b))
-* **hooks:** claude hook command invokes the dispatcher bundle directly ([a8b2bdd](https://github.com/event4u-app/agent-config/commit/a8b2bddd916d6e129c4db255094a369a6b7b6972))
-* **bench:** measure the real hook invocation path and gate CI on it ([832480a](https://github.com/event4u-app/agent-config/commit/832480ac961f3c1c0815219d95653c398ff7059d))
-* **router:** reconcile the routes_to contract via an explicit self-contained class (ADR-210) ([4f24152](https://github.com/event4u-app/agent-config/commit/4f2415250e8b3f5a9e235c0f99ef2707a0df99ec))
-* **adr:** retrofit event-based review_trigger on 11 time-bound ADRs ([6dd0375](https://github.com/event4u-app/agent-config/commit/6dd03758a73a7a0682f8b4543fe45954a5cb6f56))
-* **adr:** projection-era corrections via ADR-209 — ADR-030 carve-out retired, ADR-089 superseded ([73b3fd8](https://github.com/event4u-app/agent-config/commit/73b3fd804a666e1bed5b58ca67b35b0669c49daf))
-* **adr:** decide the ADR-201 open question — dist/agent-src is kept forever ([693fc3d](https://github.com/event4u-app/agent-config/commit/693fc3d172e0e9a6286d161c59035e848715dfd5))
-* **adr:** drain the perma-proposed sweep — five accepts, one supersede ([3ab49ff](https://github.com/event4u-app/agent-config/commit/3ab49ff992a4bafd4bbe9b7bc2a625c45427f439))
-* **adr:** supersede ADR-085 with ADR-207 — stdio-lite restated on Node-only grounds ([3874e58](https://github.com/event4u-app/agent-config/commit/3874e58267f684a8a479130ae1db20f1ab5e5ad5))
-* **adr:** batch-disposition the drive-loop era via ADR-206 ([0052f65](https://github.com/event4u-app/agent-config/commit/0052f657238794fce1144bfbf9a8f2864b569f01))
-* **hooks:** add the block-config-weakening PreToolUse guard ([d158f2d](https://github.com/event4u-app/agent-config/commit/d158f2dcfd69f4a71d97dd5bd30e9774aa95162e))
-* **router:** ratchet short keyword triggers, and stop the contract lying about activation ([9f9e273](https://github.com/event4u-app/agent-config/commit/9f9e273d5d3d8736542723be5ca4df1b32627229))
-* **projection:** project the colon command form and drop the twinned wrappers ([002697c](https://github.com/event4u-app/agent-config/commit/002697c891a9fde2a7e05a9f6b895bc189eeb80e))
-* **projection:** derive the rule pack axis from the active-pack set ([37900a9](https://github.com/event4u-app/agent-config/commit/37900a92badba9dec34cd6e84918581154365b26))
-* **gates:** put the repaired scan roots under the coverage census ([df1e736](https://github.com/event4u-app/agent-config/commit/df1e736b9d775d7870a1a2d1d7fc467c47ded858))
-* **release:** name failing checks + mid-release-fix guidance at the failure point ([a3ce993](https://github.com/event4u-app/agent-config/commit/a3ce9939fa02a3510882ac5e85a40e070e1c313a))
-* **ci:** commit the measurement set and warn on main, fail on release ([6eebc02](https://github.com/event4u-app/agent-config/commit/6eebc021cd8ac43a32625fa939898054e94f238b))
-* **gates:** extend default-entry coverage and add the mutation canary ([fc05f30](https://github.com/event4u-app/agent-config/commit/fc05f30f080b799d781e401fa500ede4d8bb340e))
-* **gates:** generate the scan-scope census over the full gate population ([301116f](https://github.com/event4u-app/agent-config/commit/301116f6f53d08d82806914bd1bf719f22ad6412))
-* **gates:** add a violation ratchet for repaired scan roots ([190d53d](https://github.com/event4u-app/agent-config/commit/190d53deca65c3c01c9fff619aaf0e0e136e92c6))
-
-### Bug Fixes
-
-* **cli:** register routing:doctor in the CLI registry ([f02db54](https://github.com/event4u-app/agent-config/commit/f02db54c2cae449e730742f7396af5ac812bf0e8))
-* **ci:** waive pre-existing SC2016 in bench-drift comment renderer ([bb4c605](https://github.com/event4u-app/agent-config/commit/bb4c6058177ccbdcdd3157a26c9818f1bcd3cc94))
-* **deps-dev:** keep web-tree-sitter on the 0.24.7 ABI pin ([3e76cb2](https://github.com/event4u-app/agent-config/commit/3e76cb2515d6b4c183b7305b49dd7084b1cd59b4))
-* **deps:** settle the preact floor and adopt the group bumps into the baseline ([b9c9c14](https://github.com/event4u-app/agent-config/commit/b9c9c14d6c43b51ee857a422ec35a4c559cd3a2e))
-* **sweep:** keep the kernel rule language-and-tone out of the dead-tree sweep ([80c323a](https://github.com/event4u-app/agent-config/commit/80c323ac27c024f85426ee63a03c51a2e02ac964))
-* **tests:** use src/rules fixture paths in the self-contained carve-out tests ([c541100](https://github.com/event4u-app/agent-config/commit/c541100cb8e9ed836dc3cd7ba54414a0c6783d65))
-* **adr-index:** stop the index header naming the retired Python generator ([a26756e](https://github.com/event4u-app/agent-config/commit/a26756e9f9da1cdb79ab29deaed6dd3238def969))
-* **hooks:** resolve the session-canary name user-globally, not per project ([9c3b779](https://github.com/event4u-app/agent-config/commit/9c3b7791fad2fa2d987b279a0951e662ff3c3ab1))
-* **hooks:** rebuild stale tsc output after pull / branch-switch ([d2122e9](https://github.com/event4u-app/agent-config/commit/d2122e936033262a9dbe429dd21a2a6e7e23efe6))
-* **roadmap-management:** tighten the awaiting-evidence section to clear the overlap gate ([5b6f141](https://github.com/event4u-app/agent-config/commit/5b6f141a8be8da01f7f231608de3a7d374b88e03))
-* **worktree:** name the dependency tree by ecosystem peers, not one stack ([eafeced](https://github.com/event4u-app/agent-config/commit/eafecedebbd207c97c37f2f380e718c37512b34b))
-* **clusters:** enumerate the filesystem in check_cluster_patterns ([a1cb83e](https://github.com/event4u-app/agent-config/commit/a1cb83e86648774cbbce7bc089640438a99626b5))
-* **registries:** register the new command generator and its output root ([2e57080](https://github.com/event4u-app/agent-config/commit/2e570802e170ff7ccd97476902b4dcdff8aac570))
-* **mcp:** price tool schemas per transport and stop shipping stub schemas ([040c8be](https://github.com/event4u-app/agent-config/commit/040c8bee1d3a7a02ec1bde7409c98e2f38881d4a))
-* **deps:** bump the npm-production group with 4 updates ([2795154](https://github.com/event4u-app/agent-config/commit/27951548d89bb575b8d08bffc2269a55f6e9f414))
-* **gates:** stop a check_ script from mutating a tracked report on every run ([d478b7a](https://github.com/event4u-app/agent-config/commit/d478b7a0f45373e9dd7f49b6427f93e101c77bea))
-* **condense:** wire thin-mode instead of throwing on it ([092e535](https://github.com/event4u-app/agent-config/commit/092e5354440dbc114e059a008139168e29e8eb42))
-* **docs:** drop the roadmap path from the branch-protection contract ([6927770](https://github.com/event4u-app/agent-config/commit/69277700fd91cf538cfb243700efcd748054dec7))
-* **gates:** repair five gates that were scanning a deleted root ([e89c1b7](https://github.com/event4u-app/agent-config/commit/e89c1b733a61bd6cd722c86488ee7f727e1e64f1))
-* **ci:** make ci-strict a superset of ci by construction ([10908cf](https://github.com/event4u-app/agent-config/commit/10908cf31919e615bb727a86b892cdfbcc38ca58))
-* **ci:** reconcile the required-check matrix with what is actually enforced ([9b6b016](https://github.com/event4u-app/agent-config/commit/9b6b016343a63d80db8d549b194b93200ad55798))
-* **ci:** satisfy actionlint on the newly-linted workflow and explain the plumbing failure ([f1e3518](https://github.com/event4u-app/agent-config/commit/f1e351811ac6ff53c80692ea94eee56fa30e4434))
-* **gates:** repair the last dead scan root and pin the exit contract on a fixture ([683d493](https://github.com/event4u-app/agent-config/commit/683d493ec5bed63b1ac023064ed7b4da2016f066))
-* **gates:** close four first-match-wins collisions over the repo's own conventions ([7dcc6f0](https://github.com/event4u-app/agent-config/commit/7dcc6f0f1cfc3e3cd8ba3b57f549b910cee931b4))
-* **release:** ratchet existing legacy roots and stop the lockfile drift ([3bba94e](https://github.com/event4u-app/agent-config/commit/3bba94e2e479f93d8a8bf27e191b8a6accccaace))
-* **ci:** run the release-gated checks on the PR that causes them ([7d25422](https://github.com/event4u-app/agent-config/commit/7d2542289748c8a768258389718e1870dbe67df9))
-* **gates:** repair thirteen dead scan roots so the gates read real artefacts ([47bb0f0](https://github.com/event4u-app/agent-config/commit/47bb0f099c248d9ab1669c589158bb8908b275db))
-
-### Documentation
-
-* **roadmap:** road-to-tested-routing complete — 37/37, archived ([9a0fed9](https://github.com/event4u-app/agent-config/commit/9a0fed9c8809d68706ea0b16a0ba920414fcd087))
-* **adr:** ADR-212 — declarative routing with a quantified resolver reopen ([9c6fbff](https://github.com/event4u-app/agent-config/commit/9c6fbfff23f11a0df6d24b3a55a931350f0f7097))
-* **roadmap:** road-to-tested-routing — council-locked plan, phases 1/2/6 progress ([5a04b3a](https://github.com/event4u-app/agent-config/commit/5a04b3aa013d43f9e0105169bf20e5bcce366363))
-* **roadmap:** close and archive road-to-hook-latency-repair ([3c0af7e](https://github.com/event4u-app/agent-config/commit/3c0af7e384badd218a4712caf93a1279dc972022))
-* **claims:** hook-dispatch-latency claim pinned to the real path ([fc31783](https://github.com/event4u-app/agent-config/commit/fc31783d672e1599041ed3bfa789ba4cbb94c765))
-* **adr:** renumber the harvest-freeze record 206 -> 210 (numbers 206-209 landed on main via #1123) ([bce530d](https://github.com/event4u-app/agent-config/commit/bce530dd5685932bdbf319369eea1f050f1feeac))
-* **roadmap:** pull Codex into agent-handoff v2 scope ([eb15183](https://github.com/event4u-app/agent-config/commit/eb15183e249fec1ed51e07b52785d3f8614e56fd))
-* **roadmap:** re-audit the parked feedback-sweep items against ADR-206 ([6216751](https://github.com/event4u-app/agent-config/commit/6216751849726b6738c04c31c5af8c8759494e8f))
-* **adr:** canonicalize the harvest freeze as ADR-206 with amended resume conditions ([7ebbe0e](https://github.com/event4u-app/agent-config/commit/7ebbe0e414321b2c4d57b3e0c5b5b7480db4cae0))
-* **roadmap:** plan the agent-handoff v2 resume-style overhaul ([62895b1](https://github.com/event4u-app/agent-config/commit/62895b1bccd9fa65f24e3a78f40e91602b47070c))
-* **roadmap:** reword tier-value tokens so check_references stops reading them as rule names ([5bc8124](https://github.com/event4u-app/agent-config/commit/5bc81249c94dd39a0271311206d85546d64bd318))
-* **roadmap:** land the three feedback-sweep repair roadmaps + dashboard ([beb0560](https://github.com/event4u-app/agent-config/commit/beb0560e9b49760f696dbd127ccec6c259f57228))
-* **roadmap:** park the four freeze-gated feedback-sweep proposals in later/ ([e669f0f](https://github.com/event4u-app/agent-config/commit/e669f0f01424d921fa798ad69ad7c20763d040b2))
-* **roadmap:** close road-to-renewal-leverage with its findings ([bcc85d0](https://github.com/event4u-app/agent-config/commit/bcc85d0c593b46d83e9455139937b73061ca64b4))
-* **roadmap-management:** name the awaiting-evidence signal ([e008f19](https://github.com/event4u-app/agent-config/commit/e008f191ddc2eeaa18931259e11c852ec6e101c6))
-* **worktree:** encode the seeding allow/deny list in the creation flow ([6743690](https://github.com/event4u-app/agent-config/commit/6743690f226242a2fed6d4a45195202342fd2878))
-* **roadmap:** pre-register the resolver spike, park it, and archive Foundation ([0e49f83](https://github.com/event4u-app/agent-config/commit/0e49f83d013a242c94baf320b13249ac3f496942))
-* **roadmap:** record Phase 2 with both figures, and the two honest misses ([8de0e6c](https://github.com/event4u-app/agent-config/commit/8de0e6c088b9f6d7fde94815dc2fe235c211815a))
-* **roadmap:** record the umbrella-runner spike result — import-safety GO, timing LOSS ([0551a7c](https://github.com/event4u-app/agent-config/commit/0551a7cce2b312cf3d018967aa8e606f0f2ecda2))
-* **roadmap:** decline CI build-artifact sharing on measurement, record the Phase 2 token baseline ([fa244c1](https://github.com/event4u-app/agent-config/commit/fa244c1a8878696ab2398ca6279ad9544b1269b1))
-* **roadmap:** close Foundation P1 required-checks, ci-strict, dependabot and baseline steps ([cbc1217](https://github.com/event4u-app/agent-config/commit/cbc12170722ad3a5d5e091f290d263fff9adad96))
-* **roadmap:** close the phases of road-to-gates-that-can-fail ([a6af14f](https://github.com/event4u-app/agent-config/commit/a6af14ff088e5836bc20f769e67a820e267defc6))
-
-### Tests
-
-* **orchestration:** dispatch-decision matrices + council-path routing invariants ([8d48180](https://github.com/event4u-app/agent-config/commit/8d48180064458dd5a75559465a20ea5424f1264c))
-* **portability:** build fixtures under the live scan root ([e02dd0b](https://github.com/event4u-app/agent-config/commit/e02dd0bfaf0f2b8aaaaccec9d1a82409fa2bdb98))
-* **gates:** exercise the two happy-path-only gates through their real entry point ([365da5b](https://github.com/event4u-app/agent-config/commit/365da5b9fcc887864d344b94301836ce5cef928e))
-
-### Build
-
-* **install:** refresh the committed installer output for the rule-packs change ([8bcccc7](https://github.com/event4u-app/agent-config/commit/8bcccc7ef575420f9074307cee33721d80c6df7a))
-
-### Chores
+* **index:** regenerate artefact index, catalog and command flows ([71aacc6](https://github.com/event4u-app/agent-config/commit/71aacc6f675def21773d13f3fd927bcdc2519a99))
+* **tests:** drop unused import in the fix-lane test ([b18e77f](https://github.com/event4u-app/agent-config/commit/b18e77f78c426493ba3ff6a2ee8dc9c9ce068253))
 
-* **deps-dev:** bump @types/node from 20.19.41 to 26.1.2 ([fd0d6f6](https://github.com/event4u-app/agent-config/commit/fd0d6f6493f78b31454ebd202008f3fbd46a3da9))
-* **deps-dev:** bump @inquirer/prompts from 7.10.1 to 8.5.2 ([7dfea4b](https://github.com/event4u-app/agent-config/commit/7dfea4bbc26e8b04d2c73bc9cbe4d813dc64c724))
-* **deps-dev:** bump typescript in /deploy/telemetry-worker ([fdbff3f](https://github.com/event4u-app/agent-config/commit/fdbff3f293b3eaa6a6b1d8d5c7ba8e0769a2daab))
-* **deps:** bump marocchino/sticky-pull-request-comment from 2 to 3 ([7d4d9cb](https://github.com/event4u-app/agent-config/commit/7d4d9cb81bd95faf851cf16bb06c87d2df871d9b))
-* **deps-dev:** bump tsx from 4.22.3 to 4.23.1 in deploy/telemetry-worker ([ea561ea](https://github.com/event4u-app/agent-config/commit/ea561ea964fda776c02df3a280aaa1d9c188eac6))
-* **deps-dev:** bump the npm-development group across 1 directory with 7 updates ([fe05c7f](https://github.com/event4u-app/agent-config/commit/fe05c7fe02b2d9dca60887fe23b92b1d5fe3024e))
-* **deps:** bump actions/upload-artifact from 4 to 7 ([a2a2423](https://github.com/event4u-app/agent-config/commit/a2a2423776510471a17ebf0631fad2cba9cd50d1))
-* **roadmap:** close and archive road-to-renewal-adr-hygiene ([ab432b0](https://github.com/event4u-app/agent-config/commit/ab432b0247b21a21b6961de20ca1ef1584c96367))
-* **adr:** regenerate the index for the hygiene batch ([61dc94f](https://github.com/event4u-app/agent-config/commit/61dc94f98f48ef508986050728d04c47125c6718))
-* **docs:** sweep non-gate .agent-src.uncondensed references to the src/ truth ([9d987a0](https://github.com/event4u-app/agent-config/commit/9d987a086363b933505d6290fc111f9763f8810d))
-* **roadmap:** default dashboard_regen_cadence to every_5_steps ([d40f676](https://github.com/event4u-app/agent-config/commit/d40f676326f034affe8a0c15e4835bc4a6143fe2))
-* **deps:** bump the site group in /site with 3 updates ([ddb92d4](https://github.com/event4u-app/agent-config/commit/ddb92d4399ee35137b8c0a557345f6104b069915))
-* **deps:** bump actions/configure-pages from 5 to 6 ([c2fe6bc](https://github.com/event4u-app/agent-config/commit/c2fe6bc26f123bfd0eaf8a88d5ba2c9cb70cf6bc))
-* **deps:** bump actions/upload-pages-artifact from 3 to 5 ([6998b77](https://github.com/event4u-app/agent-config/commit/6998b77bbddfd85f8346c751f0a8679f13129dcc))
-* **deps:** schedule dependency updates via dependabot ([d9e4a8d](https://github.com/event4u-app/agent-config/commit/d9e4a8de95ef246311b85a85fd5189892ce21161))
-* **reports:** refresh the derived reports the consistency gate regenerates ([ee73e3f](https://github.com/event4u-app/agent-config/commit/ee73e3feab59cf2df2a1f6b1bc35ff6e1e032359))
-
-Tests: 10580 (+524 since 9.14.0)
+Tests: 10944 (+252 since 9.17.0)
 
 # Era: pre-4.0.0 — archived
 

package/dist/agent-src/commands/challenge-me/vision.md

@@ -438,6 +438,11 @@ If the user wants any other follow-up, they invoke it explicitly. The
   polishing).
 - [`ask-when-uncertain`](../../rules/ask-when-uncertain.md) — the
   one-question-per-turn Iron Law this command is built on.
+- [`plan-confidence-gate`](../../contexts/execution/plan-confidence-gate.md)
+  — Gate C: the plan-authoring surfaces (`/roadmap:create`,
+  `roadmap-writing`, `/feature:plan`, `/feature:roadmap`) auto-route into
+  this interview when their confidence check falls below 95%. Reverse
+  pointer only — nothing in this command changes when the gate fires.
 - Inspiration: `mattpocock/skills/skills/productivity/grill-me/SKILL.md`
   — same spirit (relentless decision-tree interview, one question at a
   time, recommended answer per question), restructured to our command

package/dist/agent-src/commands/evals/rule-compliance-audit.json

@@ -0,0 +1,46 @@
+{
+  "command": "rule-compliance-audit",
+  "intent": "Audit rule trigger quality and replay the router matcher over recent prompts (routing audit)",
+  "cases": [
+    {
+      "prompt": "audit my rules for weak triggers",
+      "expected": "rule-compliance-audit"
+    },
+    {
+      "prompt": "run a routing audit — which rules fired on my last prompts",
+      "expected": "rule-compliance-audit"
+    },
+    {
+      "prompt": "check whether the rule routing actually matches what I type",
+      "expected": "rule-compliance-audit"
+    },
+    {
+      "prompt": "why did no rule activate on my last message — audit the triggers",
+      "expected": "rule-compliance-audit"
+    },
+    {
+      "prompt": "find rules whose descriptions overlap or never activate",
+      "expected": "rule-compliance-audit"
+    },
+    {
+      "prompt": "fix the failing CI on this branch",
+      "expected": "fix"
+    },
+    {
+      "prompt": "review the changes on this branch before I push",
+      "expected": "review-changes"
+    },
+    {
+      "prompt": "run a full project health check",
+      "expected": "project-health"
+    },
+    {
+      "prompt": "estimate this ticket for me",
+      "expected": "estimate-ticket"
+    },
+    {
+      "prompt": "commit these changes in logical chunks",
+      "expected": "commit"
+    }
+  ]
+}

package/dist/agent-src/commands/feature/plan.md

@@ -21,6 +21,19 @@ packs:
 # /feature plan
 ## Instructions
 
+### 0. Confidence gate (Gate C)
+
+Before gathering, run the plan-confidence gate per
+[`plan-confidence-gate`](../../contexts/execution/plan-confidence-gate.md):
+read `planning.challenge_on_create` (missing = `true`), do the codebase
+lookup, and assess the four 95%-conditions — **seed = the provided
+description** (when none was provided, step 1's ask supplies it first).
+Confident → single marker line, continue with step 1. Uncertain → route
+into `/challenge-me vision` (inline degrade protocol without the command);
+the pitch feeds steps 5c–6, and the C→R1 handoff state is written so the
+risk-review step re-asks nothing. Explicit user bypass wins for the turn
+and is counted.
+
 ### 1. Gather the idea
 
 If the user provided a description, use it. Otherwise ask:
@@ -259,6 +272,13 @@ If picked **2** → continue.
 - Set the `Module` field in the feature doc accordingly.
 - Set status to `📋 Planned`.
 - If Jira tickets were provided, add them to the `Jira` field and reference them in the feature doc.
+- **Risk review (Gate R1)** — before saving, add a `## Risk Register`
+  section per [`plan-review-gates § 1`](../../../docs/contracts/plan-review-gates.md):
+  read the C→R1 handoff state from step 0 if present (resolved branches
+  seed the risks — never re-ask them), rank the highest product and
+  implementation risks descending, one mitigation per row, each row
+  anchored to a section of this document. No material risks → the exact
+  honest-null grammar. Self-review suffices.
 
 **Ask for the filename:**
 ```

package/dist/agent-src/commands/feature/roadmap.md

@@ -55,6 +55,15 @@ Stop.
 - Read the roadmap template at `.augment/templates/roadmaps.md` for the structure.
 - Research the codebase for affected areas mentioned in the feature.
 
+**Confidence gate (Gate C)** — after reading the feature plan, run
+[`plan-confidence-gate`](../../contexts/execution/plan-confidence-gate.md)
+with the **feature document as seed** (`planning.challenge_on_create`,
+missing = `true`). All four 95%-conditions hold → single marker line,
+continue. A gap that would change the phases or acceptance criteria →
+`/challenge-me vision` interview (or inline degrade protocol) **before**
+proposing roadmaps; the C→R1 handoff state is written so the risk-review
+step re-asks nothing. Explicit user bypass wins for the turn and is counted.
+
 Determine how many roadmaps are needed:
 
 - **Single roadmap:** Small/medium features that fit in one document.
@@ -143,6 +152,16 @@ If any planned name already exists anywhere under the namespace,
 Re-run the check after a rename. Never silently overwrite, never
 auto-suffix without the user's pick.
 
+**Risk review (Gate R1)** — every generated roadmap that is saved ready
+(non-draft) carries a `## Risk Register` per
+[`plan-review-gates § 1`](../../../docs/contracts/plan-review-gates.md):
+read the C→R1 handoff state from step 2 if present (resolved branches
+seed the risks — never re-ask them), rank the highest product and
+implementation risks descending, one mitigation per row, each row
+anchored to a phase/step of that roadmap. No material risks → the exact
+honest-null grammar. `lint_plan_risk_register` enforces this at
+pre-push + CI; drafts are exempt until flipped to ready.
+
 ### 5. Link roadmaps in the feature plan
 
 Update the feature file's `## Roadmaps` section:

package/dist/agent-src/commands/pr/create.md

@@ -139,6 +139,35 @@ completion is read from the checkbox counts.
   in the working tree.
 - **It reported nothing → proceed.** No completed roadmap in this branch.
 
+### 1d. Completion review (Gate R2) — after the sweep, before the PR
+
+Fixed sequence: (1) the § 1c archival sweep runs first, (2) the R2 review
+runs on the post-archival state (the findings artifact references
+post-archival paths), (3) the PR is created only with a valid findings
+artifact, honest-null, or skip declaration **for the current review-scope
+hash** per
+[`plan-review-gates § 2`](../../../docs/contracts/plan-review-gates.md).
+
+- A completion-review artifact from the roadmap-completion event
+  (`agents/evidence/reviews/<slug>.findings.md`) is re-used when its
+  `scope:` equals the current review-scope hash — one artifact covers
+  both triggers. **Never compare the `diff:` sha**: it is provenance only
+  (§ 2.1), and § 2.0 proves that comparison unsatisfiable — committing the
+  artifact moves HEAD, and CI checks out a synthetic merge commit.
+  Otherwise dispatch a fresh review via `dispatch_r2_reviewer` (fresh
+  subagent, no implementation context, findings BEFORE fixes; every
+  finding ends `fixed` / `accepted-risk` / `deferred`).
+- **Review last.** Any content commit after the review changes the scope
+  hash and invalidates the artifact — freeze the content, then review.
+  Artifacts from earlier rounds stay as audit trail under a name outside
+  the `*.findings.md` glob; the final round is the binding one.
+- Docs-only / plan-only diffs take the explicit skip declaration, never
+  a silent skip.
+- The agent-side check here is advisory; `check_completion_review` at
+  pre-push + CI is the enforcing layer (CI authoritative; advisory mode
+  during the Stage-A baseline window). `planning.completion_review:
+  false` is the settings escape hatch.
+
 ### 2. Generate PR content
 
 Run `/create-pr:description-only` Steps 1–4 to generate the PR title and body.

package/dist/agent-src/commands/roadmap/create.md

@@ -20,6 +20,22 @@ packs:
 # /roadmap create
 ## Instructions
 
+### 0. Confidence gate (Gate C)
+
+Before anything else, run the plan-confidence gate per
+[`plan-confidence-gate`](../../contexts/execution/plan-confidence-gate.md):
+read `planning.challenge_on_create` (missing = `true`), do the codebase
+lookup, and assess the four 95%-conditions against the seed.
+
+- **Confident** (all four hold) → emit the single marker line and continue
+  with step 1.
+- **Uncertain** → route into `/challenge-me vision` with the ask as seed
+  (inline degrade protocol when the command is unavailable); the resulting
+  pitch pre-fills steps 3–4, and the C→R1 handoff state is written per the
+  context doc so the risk-review step re-asks nothing.
+- **Explicit user bypass** ("just write it") → skip the gate for this turn;
+  count the bypass.
+
 ### 1. Determine location
 
 Ask the user (in their language) where the roadmap should be created:
@@ -99,6 +115,19 @@ Show the complete roadmap to the user and ask (in their language) if anything sh
 - If yes → apply changes, show again.
 - Repeat until the user says it's done.
 
+### 5b. Risk review (Gate R1) — after draft, before save
+
+Unless the roadmap will be saved as `status: draft`, add a
+`## Risk Register` per
+[`plan-review-gates § 1`](../../../docs/contracts/plan-review-gates.md):
+read the C→R1 handoff state from step 0 if present (resolved branches
+seed the risk list — never re-ask them), identify the highest product and
+implementation risks, rank descending, write a mitigation per row, and
+anchor every row to a phase/step of this roadmap. No material risks → the
+exact honest-null grammar from the contract. Self-review suffices.
+`lint_plan_risk_register` enforces this at pre-push + CI; drafts are
+exempt until flipped to ready.
+
 ### 6. Save the file
 
 - Generate a filename from the title: kebab-case, e.g. `optimize-webhook-jobs.md`.

package/dist/agent-src/commands/rule-compliance-audit.md

@@ -5,11 +5,11 @@ pack: meta
 tier: 2
 visibility: internal
 skills: [rule-compliance-audit]
-description: Audit rule trigger quality, simulate activation, detect overlaps, and find never-activating rules
+description: Audit rule trigger quality, simulate activation, detect overlaps, find never-activating rules, and replay the router matcher over recent prompts (route:audit)
 suggestion:
   eligible: true
-  trigger_description: "audit my rules, check rule trigger quality"
-  trigger_context: "maintainer working on .augment/rules/ files"
+  trigger_description: "audit my rules, check rule trigger quality, routing audit — which rules fired"
+  trigger_context: "maintainer working on .augment/rules/ files or questioning whether rules route"
 workspaces:
   - agent-config-maintainer
 packs:
@@ -121,7 +121,27 @@ ALWAYS-RULE HEALTH
   {name}: {line_count} lines — {✅ healthy | ⚠️ large (>100 lines) | ⚠️ could be auto}
 ```
 
-### 6. Summary and recommendations
+### 6. Session routing audit (deterministic; the `/routing-audit` surface)
+
+Replay the router's ONE shared matcher over the recent session — read-only,
+no LLM call, deterministic:
+
+```bash
+agent-config route:audit --last 10        # matched rules per recent user prompt
+agent-config route:explain "<prompt>"     # deep trace for one prompt
+agent-config route:audit --weekly         # rolling 7-day recorder render
+```
+
+Render the matched-vs-should-have-matched review: for each audited prompt,
+the tool prints the matched rules + triggers; flag prompts where a rule you
+would expect is absent (should-have-matched is YOUR judgment as reviewer —
+the tool never computes it). Every output opens with the measurement-level
+header: **trigger matching only — what the host actually invoked is NOT
+measured** (ADR-126). Recording (`--record`) is opt-in via
+`telemetry.routing_recorder.enabled` (default off) and stores prompt digests,
+never prompt text.
+
+### 7. Summary and recommendations
 
 ```
 ═══════════════════════════════════════════════
@@ -152,7 +172,10 @@ Wait for user to pick which recommendations to apply.
 ## Rules
 
 - **Do NOT modify any files** until the user approves recommendations.
-- **Do NOT run any scripts** — this is a pure analysis command.
+- **Do NOT run any scripts** — this is a pure analysis command. Sole
+  carve-out: the read-only routing CLI in step 6 (`route:explain` /
+  `route:audit`), which is deterministic and writes nothing (the opt-in
+  `--record` flag is the one gated exception).
 - **Be honest about uncertainty** — if a trigger might or might not match, say "might miss".
 - **Always-rules are expensive** — flag any that could safely be auto.
 - **Auto-rules that never activate are dead weight** — flag them clearly.