@event4u/agent-config 12.1.0 → 13.0.0

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": "12.1.0",
+    "version": "13.0.0",
     "keywords": [
       "agent-config",
       "skills",

package/CHANGELOG.md

@@ -357,6 +357,157 @@ Entry-shape contract: [`docs/contracts/CHANGELOG-conventions.md`](docs/contracts
 > that forces a new era split (`# Era: 12.1.x`, etc.) — see
 > [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
 
+## [13.0.0](https://github.com/event4u-app/agent-config/compare/12.1.0...13.0.0) (2026-08-17)
+
+### 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:** _auto-derived, rewrite before merge:_ rule/schema diffs, breaking commits or removed public surface in 395912e, 357fa52, f224177, 43d4e1b, 0cb9e5d, 3573525 +2 more.
+- **Default changes + migration:** _none_
+- **Security and correctness:** _auto-derived, rewrite before merge:_ security-scoped commits or fixes to executable surface in 184a3f1, 64e48f1, 498f174, e3ce6a5, 532c29b, d36c665 +15 more.
+- **Honest nulls:** _auto-derived, rewrite before merge:_ commits recording a null, waived or falsified result in e8e6447.
+- **Known limitations:** _none_
+
+### BREAKING CHANGES
+
+* **council:** archive the budget-routing decision layer and permit lifecycle ([43d4e1b](https://github.com/event4u-app/agent-config/commit/43d4e1b2a83c25611e8d90c3ed28b5de13f09e29))
+
+### Features
+
+* **bench:** report T5 as its own verdict in the stats layer ([538708f](https://github.com/event4u-app/agent-config/commit/538708fd063a33cc8c5fb05943335b1637a97966))
+* **bench:** score T5 search adherence at the pre-registered k=2 ([5d5575e](https://github.com/event4u-app/agent-config/commit/5d5575e49c91ff5eb3bdf01e0c90542f496a9372))
+* **bench:** preserve each trial's transcript beside its clone ([f487622](https://github.com/event4u-app/agent-config/commit/f487622a06ad7c2237cd2060d0135c967be65a63))
+* **bench:** score T4 offline against the preserved workspaces ([ee770eb](https://github.com/event4u-app/agent-config/commit/ee770ebc129c2464a8d3f585b05131b1b1a103d5))
+* **bench:** add the T4 safety tier to the v2 corpus ([6bb7561](https://github.com/event4u-app/agent-config/commit/6bb7561436ac569712c5cebfba73099998cbb37f))
+* **cost:** re-price rate_missing ledger rows against the observed shape ([50b3c5d](https://github.com/event4u-app/agent-config/commit/50b3c5d2c9511ff517d7a3d2dfa189d4da45be1f))
+* **bench:** offline re-scorer retro-fits the size pair onto finished sweeps ([0fd111e](https://github.com/event4u-app/agent-config/commit/0fd111ebf0b9075002e1a8d462da70fa20fe473d))
+* **bench:** refuse a size win on golfing or a safety regression ([ae52635](https://github.com/event4u-app/agent-config/commit/ae52635b227e9a43e37c41edad9580fda62e91d5))
+* **bench:** cognitive complexity per changed function (delta #11) ([5e6f177](https://github.com/event4u-app/agent-config/commit/5e6f177731c12be4f57efbaccf2584718cdb6201))
+* **design-fidelity:** URL / live-page handover extracts into files first ([0cb9e5d](https://github.com/event4u-app/agent-config/commit/0cb9e5d8e8db5ced9b236e29f061233dbff47fc4))
+* **gates:** adopt per-target completeness ledgers in four more gates ([6fc4458](https://github.com/event4u-app/agent-config/commit/6fc445804ca845778e6521a1ddec8964ed072435))
+* **contracts:** declare the eight rule pairs the audit left arbitrated by nobody ([0499a0f](https://github.com/event4u-app/agent-config/commit/0499a0fe411e045c8562b94b95e2089379e4a4d1))
+* **prompt-optimizer:** de-inflate a prompt before polishing it ([8e22d2b](https://github.com/event4u-app/agent-config/commit/8e22d2b4667b59232a0aa2b26de4882da27f6c74))
+* **ci:** keep the archive index from going stale in the PR that stales it ([89ad466](https://github.com/event4u-app/agent-config/commit/89ad466950d818b56348bd5f49819bd0000d8ebf))
+* **scripts:** index the roadmap archive, deterministically ([725e4b3](https://github.com/event4u-app/agent-config/commit/725e4b376fd5b58ef47d82da777aaa30313ee76d))
+* **gates:** ratchet the excess lines over a 1,500-line source ceiling ([7e051f9](https://github.com/event4u-app/agent-config/commit/7e051f94af00b1652eabeca0064b28ef760c75db))
+* **mcp:** recover what the host dropped — real ranker tool + a route to it ([866bd98](https://github.com/event4u-app/agent-config/commit/866bd9861b42db575da1869790290cf4062eadfd))
+* **skills:** give skill triggers a schema, a validator, and a first tranche ([1bf6a9a](https://github.com/event4u-app/agent-config/commit/1bf6a9ab9d15909fcbd6e6dbe7f5d7e925cca18a))
+* **hooks:** bind the deterministic skill ranker to user_prompt_submit ([0da18b4](https://github.com/event4u-app/agent-config/commit/0da18b48956b2374e64e88bf3159e88581403178))
+* **catalogue:** report projected skill counts per projection mode ([8a6d7df](https://github.com/event4u-app/agent-config/commit/8a6d7df4ff15213a54c01f52895f5cebace78ab9))
+* **routing:** bound inherit at high, cap the judge ladder, floor the split ([7863ebc](https://github.com/event4u-app/agent-config/commit/7863ebca390cfd353dabc46bebb505fabacfa435))
+
+### Bug Fixes
+
+* **release:** keep release.ts off the source-size ratchet ([184a3f1](https://github.com/event4u-app/agent-config/commit/184a3f107ba24467eaf363bbfac7d02fd80152ef))
+* **release:** recognise the stale-lease push rejection as a moved ref ([64e48f1](https://github.com/event4u-app/agent-config/commit/64e48f1894a6dcbbc8292207215e0145bf9bd9d5))
+* **bench:** drop the own-orphans the extraction left in the runner ([498f174](https://github.com/event4u-app/agent-config/commit/498f174359e18e59f9ea98cd329ccaca329a9fbf))
+* **roadmaps:** resolve the dangling risk anchor in road-to-context-fidelity ([19b653a](https://github.com/event4u-app/agent-config/commit/19b653a016f683f733ff23e4f9a2122a15dff08f))
+* **bench:** pay back the source-size ratchet by extraction ([e3ce6a5](https://github.com/event4u-app/agent-config/commit/e3ce6a5539c0e47fb439e5c43a14dca40b47b923))
+* **bench:** repair the nine findings the completion review raised ([532c29b](https://github.com/event4u-app/agent-config/commit/532c29b722a6b80da06c338d033100ef9894b327))
+* **schemas:** the requires_confirmation descriptions carried the same claim ([395912e](https://github.com/event4u-app/agent-config/commit/395912ed6c8ec313c3a3d8c4547768f7d711d938))
+* **rules:** stop certifying two hosts that never deny, and name four gap hosts ([357fa52](https://github.com/event4u-app/agent-config/commit/357fa52c740f93a26022a352dfb6a45bdac9d583))
+* **contracts:** model the fourth host state — bound, and ignored ([2a30650](https://github.com/event4u-app/agent-config/commit/2a3065070281fcb3185939b182f41423a4adeb46))
+* **hooks:** correct the same claim in the ui-route-nudge header ([d36c665](https://github.com/event4u-app/agent-config/commit/d36c665b5b5d6918d0200710d3df489b10084782))
+* **rules:** correct the pre_tool_use coverage reason, not the count ([f224177](https://github.com/event4u-app/agent-config/commit/f224177f523b15585149fbe3524fa5ac915bebbb))
+* **roadmaps:** make the feasibility-screen inputs true again ([e8e6447](https://github.com/event4u-app/agent-config/commit/e8e64471659bddd7510861d70e0bbe250a7d9ad3))
+* **build:** rebuild the install bundle without the worktree symlink ([441c2d8](https://github.com/event4u-app/agent-config/commit/441c2d8edf4ed6836a483cb4c3ab15da75c0cfb1))
+* **cost:** repair all seven completion-review findings ([f296b41](https://github.com/event4u-app/agent-config/commit/f296b41e477fa7c3a34bde0e03ddb7b558422d42))
+* **council,roadmap:** apply the R2 fix pass on the archival ([e11b9e1](https://github.com/event4u-app/agent-config/commit/e11b9e18c2ab37d400fd2ec7c799099b6928848d))
+* **ci:** green the source-size ratchet and the reference check ([b0de33a](https://github.com/event4u-app/agent-config/commit/b0de33a29a2ab4c2476545c3b44ee2ce8b91de87))
+* **bench:** repair the ten completion-review findings ([4eee75f](https://github.com/event4u-app/agent-config/commit/4eee75f9c959b0c9710e37229bc41ce36640965c))
+* **roadmap,council:** apply the R2 fix pass ([8d49432](https://github.com/event4u-app/agent-config/commit/8d49432a615fd5f3f67f9ef9be1f0885912739fd))
+* **roadmap:** record both (b) votes, and correct three claims the last PR left stale ([4da97c5](https://github.com/event4u-app/agent-config/commit/4da97c5804f8eaf3c5f333f31e471ecc27d89356))
+* **council:** correct a comment that claimed the spawn inherits the caller cwd ([f3c1509](https://github.com/event4u-app/agent-config/commit/f3c1509d1f51eb5973184313618222517a062bd7))
+* **docs:** regenerate proof.md after the claims edit ([722c123](https://github.com/event4u-app/agent-config/commit/722c123a1bbdc10034aef606e14d3b48aeae9d63))
+* **roadmap:** picktier-wire-or-archive is gated on infrastructure, not judgement ([4ad4701](https://github.com/event4u-app/agent-config/commit/4ad4701cb6a882bab2581c23e8c9608b13459b46))
+* **claims:** the budget-routing entry described a binding that was deleted ([6712475](https://github.com/event4u-app/agent-config/commit/671247590b2a0be54f46d0d59dbb4568ea5c1798))
+* **gates:** drop a bootstrap flag whose window has closed ([cfc27b4](https://github.com/event4u-app/agent-config/commit/cfc27b4303cf2cdc6c0c64b338473e7b1356f511))
+* **roadmap:** stop the disposition note from naming the token it scrubbed ([e2b0858](https://github.com/event4u-app/agent-config/commit/e2b0858a45589ea887ba020030b43805fa9ba54f))
+* **roadmaps:** make six held blockers decidable, and lower the ratchet to match ([9aff993](https://github.com/event4u-app/agent-config/commit/9aff993d64698754c4253f30ef98a913a7325c3b))
+* **gates:** exclude declarations and tests, emit real JSON, stop swallowing reads ([09c7a84](https://github.com/event4u-app/agent-config/commit/09c7a84d680437a17a3d24fb665f236a9827e8b3))
+* **roadmap:** terminate a blocker field on ANY labelled bullet, not eight names ([8216fab](https://github.com/event4u-app/agent-config/commit/8216fab38bea09dc5d3051cd454dac26ab359235))
+* **ci:** pin skill-route in the worker-drop set ([179fc09](https://github.com/event4u-app/agent-config/commit/179fc09e9f8734b335aac5dc222ef243da76cef9))
+* **ci:** re-point the trigger census and rebuild the install bundle ([ec7b34b](https://github.com/event4u-app/agent-config/commit/ec7b34b37649a238dca949c98bf4458c4ebca69e))
+* **review:** close all 13 R2 findings ([3573525](https://github.com/event4u-app/agent-config/commit/35735256cbefccea79455a61c323cd37685920c3))
+* **routing:** address all 7 R2 review findings ([aa57107](https://github.com/event4u-app/agent-config/commit/aa571070882084f8653a7cff13a0c930d7690bcf))
+* **routing-doctor:** report cool-down state as unavailable, not as false ([4fed9ec](https://github.com/event4u-app/agent-config/commit/4fed9ec7b91777e198d2596d58c2868246072ac9))
+
+### Documentation
+
+* **evidence:** re-bind the review after the own-orphan cleanup ([575258b](https://github.com/event4u-app/agent-config/commit/575258b6867db4670f7bbe0c0b50bb4dee664b7a))
+* **roadmaps:** add road-to-release-review-p0 and regenerate the dashboard ([7ac1bfb](https://github.com/event4u-app/agent-config/commit/7ac1bfba699b53f29e151570789f29801c6b20c1))
+* **roadmaps:** add road-to-metric-loop-and-review-integrity ([2bec54e](https://github.com/event4u-app/agent-config/commit/2bec54e62ddc5f4dd14d63bb749f2e1a3309d473))
+* **roadmaps:** add road-to-org-telemetry ([5a8f5fd](https://github.com/event4u-app/agent-config/commit/5a8f5fdd838fb0b5c83b24fedb0b6d8f8657da71))
+* **roadmaps:** add road-to-context-fidelity ([ca373a6](https://github.com/event4u-app/agent-config/commit/ca373a667f972aace506597d75667f66dba0ab70))
+* **roadmaps:** add road-to-user-out-of-the-loop ([53166c7](https://github.com/event4u-app/agent-config/commit/53166c720e1c0e0c31e54a5741ac4a742f34abd6))
+* **evidence:** re-bind the review after the CI repair ([71457e0](https://github.com/event4u-app/agent-config/commit/71457e0bb1fcb9ebf5eed1783f3ee87c2dde1d05))
+* **evidence:** close the nine findings and re-bind the review scope ([f54a02f](https://github.com/event4u-app/agent-config/commit/f54a02f4c71aae43a24815d021e30a81ed890e71))
+* **evidence:** record the R2 completion review before fixing anything ([02e7b69](https://github.com/event4u-app/agent-config/commit/02e7b697c2c3240fe1944e5625fd3bbf28f0fd4c))
+* **bench:** discharge PREREG precondition 3 and close step 3.4 ([06b8e2d](https://github.com/event4u-app/agent-config/commit/06b8e2d9e68444a7f66d1218664dcaa30a4240b0))
+* **evidence:** re-bind the findings after the six fixes ([81d611d](https://github.com/event4u-app/agent-config/commit/81d611d2716a0947aa74978d42300591e7410939))
+* **evidence:** record the R2 findings before the fixes ([18e62fa](https://github.com/event4u-app/agent-config/commit/18e62fa49e9aa2b53f1da2c8892d7d5eddf54f78))
+* **contracts:** tabulate which hosts carry pre_tool_use ([36211a9](https://github.com/event4u-app/agent-config/commit/36211a9652cabff813fc9851080a0497c14fbc7d))
+* **evidence:** declare the completion-review skip for the corrections ([75c8d89](https://github.com/event4u-app/agent-config/commit/75c8d898b9187b491f16f3d756c5668d3f80194c))
+* **evidence:** re-bind the completion review after the main merge ([3ce343d](https://github.com/event4u-app/agent-config/commit/3ce343dac8101e1e8d37a689296ce63820811b94))
+* **evidence:** re-bind the findings after the bundle rebuild ([35a178d](https://github.com/event4u-app/agent-config/commit/35a178d6e3ef7aca8f3c4c1da0c7775918491d37))
+* **evidence:** record the fix commit on each repaired finding row ([7cfc6ff](https://github.com/event4u-app/agent-config/commit/7cfc6ff2bdf274612f7ae0444229b5d6dbc6bb2c))
+* **evidence:** re-bind the completion review after the seven repairs ([b043aef](https://github.com/event4u-app/agent-config/commit/b043aef11a1eb9f02f1fd4ae8cd11be0ed6a78cc))
+* **evidence:** re-bind the R2 findings and record the dispositions ([80252df](https://github.com/event4u-app/agent-config/commit/80252df5e61ee215627da4a072b235126cfd336a))
+* **evidence:** completion review for the ledger-truth backfill, rows open ([f1dfe04](https://github.com/event4u-app/agent-config/commit/f1dfe0404e8e70745c4df67cbe26c669a0d67c19))
+* **evidence:** record the R2 findings on the archival before fixing ([f840dbc](https://github.com/event4u-app/agent-config/commit/f840dbc1ae0eca2a1e651277ca2f1e5c25821690))
+* **cost:** document the re-pricing pass in the cost report command ([d7021a5](https://github.com/event4u-app/agent-config/commit/d7021a57e299e83c5763943ffe5385a915789e3c))
+* **roadmap:** close ledger-truth 2.5, resolve its blocker, archive the roadmap ([8d6c8a2](https://github.com/event4u-app/agent-config/commit/8d6c8a2a6b43da0549965c4ace23e9ae7085147b))
+* **evidence:** record the observed rate_missing row, and why it waited three days ([d56147c](https://github.com/event4u-app/agent-config/commit/d56147c6869c35b29be061d791cf79767a1eff64))
+* **roadmap:** close 4.1 on the converged verdict ([01da09c](https://github.com/event4u-app/agent-config/commit/01da09ce167ef38af10bbe43b62e3c56c3d4f0ab))
+* **evidence:** re-bind the completion review after the CI repairs ([218b6eb](https://github.com/event4u-app/agent-config/commit/218b6eb8f5b202f9ff013673a387a86aba9fd01d))
+* **evidence:** re-bind the completion review, all ten rows fixed ([17a8ad0](https://github.com/event4u-app/agent-config/commit/17a8ad09c673150561ebdb72340d8e99fd382b20))
+* **evidence:** completion review for the Phase-3 metric pair, rows open ([df12c39](https://github.com/event4u-app/agent-config/commit/df12c39e18630757fd34da19dbea79a17a2809b0))
+* **evidence:** record the R2 findings before the fix pass ([1aae520](https://github.com/event4u-app/agent-config/commit/1aae5201e9e7b74238cf095ed026e33cf5fcd0a8))
+* **roadmap:** record delta #11 and repoint five stale blocked-by annotations ([d6f5d59](https://github.com/event4u-app/agent-config/commit/d6f5d5929596ce813a4920bc78dfc95525adba0d))
+* **evidence:** re-bind the completion-review skip after the main merge ([7594467](https://github.com/event4u-app/agent-config/commit/7594467ce4e38391537329c4d92696fbdf7f747b))
+* **evidence:** declare the docs-only skip for this completion ([7041aae](https://github.com/event4u-app/agent-config/commit/7041aae477d9b1b051796236440a6b99263496b2))
+* **evidence:** re-declare the skip after the forward-merge and index regen ([f2ffe38](https://github.com/event4u-app/agent-config/commit/f2ffe38e83d12da0a1255436f1596c33ad5b7328))
+* **evidence:** re-declare the docs-only skip at the post-split scope ([90409ae](https://github.com/event4u-app/agent-config/commit/90409ae8c915a70d0d64d466bbdebff3560a036c))
+* **roadmap:** close source-first Phase 4 Steps 1-2, correct a stale blocker claim ([314e3ea](https://github.com/event4u-app/agent-config/commit/314e3eaf9157ce87003c5ca5447118b756bf7e28))
+* **roadmap:** close F4.1 with the re-adjudication, and correct a header that was false ([0b96569](https://github.com/event4u-app/agent-config/commit/0b9656992832fe4f7a3f87e109af26c474c0c011))
+* **roadmap:** close and archive the prompt-deinflation roadmap ([a14f7be](https://github.com/event4u-app/agent-config/commit/a14f7be15d165df34bca2d3167084cb9dd84d4d7))
+* **roadmap:** publish the saving reading, route the authoring surface, archive ([ee3d0ef](https://github.com/event4u-app/agent-config/commit/ee3d0efcfd851e9b45017e433961b4450bbbe4df))
+* **review:** re-bind the completion review after the fix pass ([8941d59](https://github.com/event4u-app/agent-config/commit/8941d599f5351b167c93da8ecc97fd32bc10328b))
+* **review:** record the R2 completion-review findings for this branch ([1e4c3a2](https://github.com/event4u-app/agent-config/commit/1e4c3a27025166026b575aee4d6ebf162c633b32))
+* **review:** re-bind the findings after the originality refresh ([620613f](https://github.com/event4u-app/agent-config/commit/620613f3ba21b72f2aff1f38cc4658fe58c8ee9e))
+* **review:** re-bind the findings after the worker-drop pin ([a326d59](https://github.com/event4u-app/agent-config/commit/a326d59f0234dc366b3e53ee9a3a6bbb531a5fea))
+* **roadmap:** close R3 and R4, make both residual blockers decidable ([358c91d](https://github.com/event4u-app/agent-config/commit/358c91db0bd44aa0c65c9f8aad000f7e2c98f3ac))
+* **skills:** record the snapshot preference order for design-system capture ([bcbb0ca](https://github.com/event4u-app/agent-config/commit/bcbb0ca8f3b81e59368fab31e07fd8963b39e0c8))
+* **review:** re-bind the findings after the CI-fix commit ([cfe225c](https://github.com/event4u-app/agent-config/commit/cfe225cde464f5d67a0458b94ef3f9673c5f8155))
+* **review:** re-bind the findings after the main merge ([24b0916](https://github.com/event4u-app/agent-config/commit/24b0916629169c61d053592bd24694289feccb64))
+* **review:** re-bind the findings to the post-fix scope, 13/13 fixed ([871a96c](https://github.com/event4u-app/agent-config/commit/871a96c675f4de2693b6b97a520c19ff6bb9181d))
+* **review:** record the R2 completion review — 13 findings ([113b9ed](https://github.com/event4u-app/agent-config/commit/113b9edfc76ec796fa4ceea6dc36ea56c6818a0e))
+* **review:** re-bind the R2 findings after the fix pass ([80c994e](https://github.com/event4u-app/agent-config/commit/80c994e8c0ed491374c6bb77010a9ff845159dae))
+* **review:** R2 completion review for feat-top-band-model-economy ([2f25030](https://github.com/event4u-app/agent-config/commit/2f250301491a4d3c305be148159b7803ed4ff511))
+* **roadmap:** close runtime-skill-routing, 14 of 14 ([793a75e](https://github.com/event4u-app/agent-config/commit/793a75ea4af9c7ecfba08a31c3de4c1b2940b0b6))
+* **roadmap:** close Phase 3 and 4.2, open the pickTier decision as a blocker ([1c078db](https://github.com/event4u-app/agent-config/commit/1c078dbbdfcd65074434707fa8cb61fee53fe05b))
+* **evidence:** publish the downshift-versus-cache reading ([3a27719](https://github.com/event4u-app/agent-config/commit/3a27719964ada44c7d2744a3aa928e258f997047))
+
+### Refactoring
+
+* **design-fidelity:** split the handover section out under the depth ceiling ([ee113c3](https://github.com/event4u-app/agent-config/commit/ee113c3c65d86e44bae34314f22a1eaaeabb8639))
+
+### Chores
+
+* **roadmap:** regenerate dashboard after merging main ([308faf8](https://github.com/event4u-app/agent-config/commit/308faf8e960c2f9a94a345809c12e2e1698a3902))
+* **evaluator:** record the 19 -> 20 mcp_public_tool_count move ([5a8a77f](https://github.com/event4u-app/agent-config/commit/5a8a77fca840e5dc4d5c35abcf9c3cb27e78b684))
+* **roadmap:** regenerate the dashboard for the ledger-truth archival ([daa3d0d](https://github.com/event4u-app/agent-config/commit/daa3d0d0b633d7aba27126b7512aa9f7be520790))
+* **roadmap:** regenerate the dashboard after the main merge ([8b40272](https://github.com/event4u-app/agent-config/commit/8b402725818fed47424b788de20ef9de516233a5))
+* **roadmap:** regenerate the dashboard after merging main ([9d2ff18](https://github.com/event4u-app/agent-config/commit/9d2ff180612fcfec1531fe6ed7a118b0c1dbde63))
+* **index:** regenerate the artefact index for the new guideline ([ce19de0](https://github.com/event4u-app/agent-config/commit/ce19de0baf25ed9982f9cdce97dc2f92a4d104fd))
+* **provenance:** record the prompt-optimizer non-entry and ratchet the source ([be9b9e2](https://github.com/event4u-app/agent-config/commit/be9b9e2f68394a2cbcac2101049f0470d5a39d02))
+* **reports:** refresh the originality audit for the grown corpus ([43054b8](https://github.com/event4u-app/agent-config/commit/43054b8e663d771e29dd102a41bbc639dfe194a7))
+* **roadmaps:** archive the completed scheduled-deprecation roadmap ([f74cabe](https://github.com/event4u-app/agent-config/commit/f74cabe009a14e7410c70cd06a481c42be304808))
+* **docs:** routed-rule count 110 -> 111 for missing-skill-recovery ([6b8a9a6](https://github.com/event4u-app/agent-config/commit/6b8a9a6726a3234a20a435bf71be9ebb942ffe70))
+* **roadmaps:** archive two completed roadmaps ([5cbe55d](https://github.com/event4u-app/agent-config/commit/5cbe55d6d78d340d25752505784e945aedee15df))
+
+Tests: 14173 (+181 since 12.1.0)
+
 ## [12.1.0](https://github.com/event4u-app/agent-config/compare/12.0.0...12.1.0) (2026-08-16)
 
 ### Release highlights

package/README.md

@@ -4,7 +4,7 @@
 
 [![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) [![MCP Toplist](https://mcptoplist.com/badge/glama%2Fevent4u-app%2Fagent-config.svg)](https://mcptoplist.com/server/glama%2Fevent4u-app%2Fagent-config)
 
-[![Skills](https://img.shields.io/badge/Skills-289-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-116-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-200-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-105-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/)
+[![Skills](https://img.shields.io/badge/Skills-289-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-117-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-200-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-106-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/)
 
 **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. Start at the proof, not the catalog: **[event4u-app.github.io/agent-config/proof/](https://event4u-app.github.io/agent-config/proof/)**.
 

package/dist/agent-src/commands/cost/report.md

@@ -46,6 +46,28 @@ treated as pre-dedup.
 If `track.mjs` exits 2 with `no Claude Code project dir`, the user is not in
 a Claude Code session — surface that and stop.
 
+If the run warns `rate_missing`, the session contained a model with no price
+tier: those messages were costed at **$0** and the total is understated, not
+cheap. Token counts are kept, so the row can be re-priced later — see step 1b.
+
+### 1b. Re-price an unpriced row (only when `rate_missing` fired)
+
+```bash
+node scripts/cost/backfill_rates.mjs --rates rates.json          # dry run
+node scripts/cost/backfill_rates.mjs --rates rates.json --apply  # write
+```
+
+`rates.json` maps each unpriced model id to a **tier alias** (`"opus"`) or an
+explicit per-1M table (`input`, `output`, `cache_write_5m`, `cache_write_1h`,
+`cache_read`). The rate is the operator's to supply: the pass never guesses a
+price for an id the tracker did not recognise, and rejects an unknown alias or
+a missing key by name rather than defaulting one.
+
+Dry run is the default. Ask the user for the rate — **never invent one** — and
+surface both limits the pass reports: cache writes price at the 5m rate (the
+row does not retain the 5m/1h split), and `byBucket` costs are not repaired
+(the row carries no per-bucket-per-model tokens).
+
 ### 2. Check the budget
 
 ```bash
@@ -186,6 +208,7 @@ and there is no `agents/runtime/state/audit/` directory.
   (different scope: in-flight estimate, not historical actuals).
 - [`scripts/cost/track.mjs`](../../../scripts/cost/track.mjs) — tracker source.
 - [`scripts/cost/budget.mjs`](../../../scripts/cost/budget.mjs) — budget source.
+- [`scripts/cost/backfill_rates.mjs`](../../../scripts/cost/backfill_rates.mjs) — re-pricing pass for `rate_missing` rows.
 
 ## Attribution
 

package/dist/agent-src/contexts/execution/subagent-routing.md

@@ -8,8 +8,10 @@ provider's model or billing rule.
 
 ## Inputs
 
-- The sub-task's declared `model_tier` (`lite | medium | high | inherit`,
-  per [`model-recommendations`](../model-recommendations.md)).
+- The sub-task's declared `model_tier` (`lite | medium | high | frontier |
+  inherit`, per [`model-recommendations`](../model-recommendations.md)).
+  `frontier` (ADR-232) is declarable and opt-in; it is never the resolution of
+  `inherit` — see the top-band invariant below.
 - `subagents.downshift`, `subagents.quota_arbitrage`, `subagents.model_map`
   (see [`auto-orchestration-activation`](auto-orchestration-activation.md)).
 - The host-capability manifest's `separate_quota_pool`
@@ -27,43 +29,154 @@ THE SAME MINUS THE QUOTA WIN.
 1. **Downshift off** (`downshift: false`) → every sub-task runs on the session
    tier. No routing change.
 2. **Downshift on** → a sub-task runs on its declared tier; an `inherit` task
-   runs on the session tier. The tier resolves to a model alias via
-   `model_map`; an empty entry means "use the tier's runtime default" — never a
-   baked-in provider model name.
+   runs on the session tier, **bounded by the top-band invariant below**. The
+   tier resolves to a model alias via `model_map`; an empty entry means "use
+   the tier's runtime default" — never a baked-in provider model name.
 3. **Quota arbitrage** → prefer the **separate** quota pool for the sub-task
    **only when** `subagents.quota_arbitrage == true` **and**
    `manifest.separate_quota_pool == true`. Otherwise the shared pool is used and
    the tier/model choice is unchanged. This is the only place the
    "Sonnet-has-its-own-allowance" idea lives, and it lives as a runtime-detected
    flag, never as portable prose.
-4. **Budget routing** (design:
-   [`budget-routing` contract](../../../../docs/contracts/budget-routing.md)) →
-   AFTER the tier resolves per 1–3, the budget relation via `pickTier`
-   (`src/scripts/_lib/tier_budget_routing.ts`) would apply: cheapest
-   classifier-adequate tier WITH available budget; that tier exhausted or
-   cooling → next tier up with budget; all unavailable → session model +
-   surfaced one-line notice. Work is never blocked to save money. Before
-   the dispatch is created, acquire the atomic reserve
-   (`acquireBudgetPermit`; check state via `node src/scripts/cost/budget.mjs
-   tier <t>`); a 429/quota error trips `tripCooldown` for that tier and
-   falls back per the relation — never a retry loop.
-   `subagents.budget_routing` was removed as a settings key (always-on
-   orchestration, road-to-always-on-orchestration Phase 1: no per-layer
-   on/off switch survives) — `pickTier` has NO production caller today, so
-   this point documents the DESIGNED relation, not a currently wired one;
-   wiring it is a later phase of that roadmap (council-side
-   `cli_call_budget`/`cost_budget` are the caps that replace the settings
-   gate). Every budget-routed dispatch, once wired, would emit one
-   `orchestration_record` line (tier + provenance-tagged token delta) so
-   realized savings are measured, not asserted.
+4. **Budget routing — ARCHIVED 2026-08-16, there is no fourth step.** This
+   position used to describe a budget relation applied after the tier resolves
+   per 1–3: cheapest classifier-adequate tier WITH available budget, an atomic
+   pre-dispatch reserve, a cool-down on quota errors. None of it exists any
+   more. A converged AI-council verdict (anthropic + openai, 2 of 2) archived
+   `pickTier` and the permit lifecycle, because the `routing_switch` they
+   required lost its only source when `subagents.budget_routing` was deliberately
+   deleted by always-on orchestration — so wiring meant inventing a replacement
+   for a removed category — and because `session_tier` sits non-null in 0 of 327
+   records, leaving the saving unmeasurable in principle. Migration record and
+   the union revisit-if:
+   [`budget-routing` contract](../../../../docs/contracts/budget-routing.md).
+   **Tier resolution therefore ends at step 3.** What survives of the module is
+   `TIER_ORDER` and `readCooldowns`, read by `routing:doctor` as a diagnostic —
+   monitoring, not routing, and note that nothing writes the cool-down file any
+   more, which is why the doctor reports that state as *unavailable, no
+   producer* rather than as a measured "not cooling".
+
+### The top-band invariant (binding)
+
+```
+UNDER A TOP-BAND SESSION, `inherit` RESOLVES TO AT MOST `high`.
+A SLICE THAT GENUINELY NEEDS THE SESSION'S OWN BAND DECLARES IT.
+ONE TOP-BAND CONTEXT PER TASK — THE ORCHESTRATOR'S. NEVER A SECOND BY DEFAULT.
+```
+
+Read as one line: an undeclared slice under a top-band session runs at most
+`high`, never the session's own band.
+
+`inherit` means *model-agnostic*, not *whatever the session happens to cost*.
+Left unbounded it is the one declaration that silently buys the most expensive
+band available, for exactly the slices whose authors judged the model choice
+not to matter — the weakest possible reason to spend the most.
+
+**The clamp is `high`, not the top mapped tier, and the distinction is not
+cosmetic.** ADR-232 added `frontier` to the tier→model map, so the top *mapped*
+rung is now `frontier`; clamping there would clamp nothing. The bound is the
+top **generally-recommended** band, which is what
+[`model-recommendations`](../model-recommendations.md) already states from the
+other side — its `frontier` row reads *"Never the resolution of `inherit`"*.
+This clause is that same rule written where the resolution actually happens.
+
+Consequences, stated so the cost stays visible rather than removed:
+
+- A slice that needs `frontier` **declares `model_tier: frontier`** — a value
+  § Inputs above lists as declarable, precisely so this escape hatch is legal
+  rather than instructed-but-forbidden. The declaration is the whole point:
+  the spend becomes an authored decision with a name on it instead of a
+  default nobody chose.
+- The clamp changes only the **undeclared** case. Every explicit
+  `model_tier:` is honoured verbatim, upward included.
+- A session running *below* `high` is untouched — `inherit` still resolves to
+  the session tier. "At most" is a ceiling, never a floor, and this clause
+  never promotes a slice.
+- A **declared `frontier` implementer** keeps its band, and its judge is
+  governed by [`subagent-configuration`](../subagent-configuration.md)
+  § The judge cap — which handles that case explicitly rather than leaving
+  the reviewer weaker than the author.
+
+**Honest scope.** This is a policy clause in a context file, so it binds the
+agent that reads it and nothing else; no gate re-derives an `inherit`
+resolution at dispatch time. `enforced_by: none`, deliberately — the same
+boundary the safety-floor rules state for their own obligations.
+
+### The non-escalation floor (binding)
+
+```
+A SLICE WHOSE DISPATCH OVERHEAD EXCEEDS THE SAVING FROM DOWNSHIFTING
+STAYS IN-SESSION. SPLITTING WORK WHOSE OVERHEAD EATS ITS OWN SAVING
+IS THE ANTI-GOAL, NOT THE MECHANISM WORKING.
+```
+
+Every dispatch pays a fixed cost the in-session path does not: the slice's
+prompt is re-sent to a fresh context, the return is read back, and the
+orchestrator verifies it. Below some slice size that overhead exceeds
+whatever the cheaper tier saved, and the delegation is a net loss dressed as
+an optimisation.
+
+**The floor is a rule, not a number — and the reason is measured, not
+assumed.** The step that authored this clause expected the same-band spawn
+distribution to supply the number. It cannot, and the corpus says so
+precisely. Over the full 327-record `orchestration` corpus (2026-07 plus
+2026-08):
+
+| Field the saving model needs | Non-null records |
+|---|---:|
+| `dispatch_tokens` | 40 |
+| `tier_chosen` | 1 |
+| `session_tier` | **0** |
+
+The three must co-occur on one dispatch to model a reduction, so the usable
+intersection is **zero**. This is not a small sample — it is an empty one, and
+`orchestration_savings_report.ts` already prints exactly that conclusion
+(`MODELED cost reduction: n/a (needs dispatch_tokens + session_tier +
+tier_chosen on a dispatch)`). `token_delta` does not rescue it: the hook
+writes it as a constant `0` with provenance `estimated`, deliberately, because
+no in-session counterfactual exists on disk to difference against.
+
+So the floor binds as a judgement with a named direction rather than a
+threshold:
+
+- **Default to in-session** when the slice is small enough that stating it
+  costs about as much as doing it — a single-file edit, one grep, one
+  question with a known answer.
+- **Delegate** when the slice carries its own reading (a file set to sweep, an
+  independent verification, a search whose output you do not want in context)
+  — there the returned conclusion is the saving, and it is not in tokens.
+- **Never delegate to hit a target.** A dispatch count is not an outcome.
+
+*Revisit-if:* a single dispatch record carries `dispatch_tokens`,
+`session_tier` and `tier_chosen` together. At that point the floor is
+computable and this clause should be replaced by the number, not amended
+toward it. Filling `session_tier` is the blocking gap — it exists in the
+schema and on the manual `orchestration_record` CLI path (`--session-tier`),
+and the hook that produced all 327 records never sets it.
 
 **Cache trade-off (road-to-cache-economy Phase 4).** A tier downshift changes
-the sub-task's model, and the prompt cache is keyed by `(model, prefix)` — so
-a downshifted leg forfeits its model-scoped cache reads AND splits a cohort's
-shared prefix into two caches (downshifted legs vs. session-tier legs). The
-per-call model saving and the forfeited cache-read saving pull in opposite
-directions; which wins is a measured question, not a default this policy
-resolves — see
+the sub-task's model, and the prompt cache is keyed by `(model, prefix)`. The
+concern was that a downshifted leg forfeits its model-scoped cache reads AND
+splits a cohort's shared prefix into two caches (downshifted legs vs.
+session-tier legs).
+
+**Measured 2026-08-16 —
+[`downshift-vs-cache.md`](../../../../agents/evidence/analysis/downshift-vs-cache.md),
+611 subagent legs / 16,612 calls.** The first half does not hold: a subagent
+leg's **first call realizes 2.8 % cache read**, so it starts cold and does not
+inherit the session's cache — a downshift forfeits a cache the leg never had.
+The cache is not lost, it is created on the other model and then read for the
+rest of the leg (median 18 calls per leg, ~96.9 % read share). The second half
+is **not measured** — nothing sizes cohort prefix sharing — but it is bounded
+above: prefix splitting is a write-side cost, and writes are **3.1 %** of
+subagent billable input against a 96.9 % read surface. Even attributing every
+write to splitting, the two sit about an order of magnitude apart, in favour of
+the downshift, so the direction does not depend on the unmeasured fraction.
+
+This resolves the direction; it does not license downshifting as a target. The
+cold start is paid per leg regardless of tier, which is precisely what the
+non-escalation floor above bounds. Analogous downgrade/cache coupling on the
+council side: see
 [`docs/contracts/ai-council-config.md`](../../../../docs/contracts/ai-council-config.md)
 § `model_downgrade` for the analogous downgrade/cache coupling this suite
 already ships on the council side.
@@ -80,8 +193,10 @@ rule, or context asserts "model X is free".
 [`src/scripts/_lib/subagent_routing.ts`](../../../../src/scripts/_lib/subagent_routing.ts)
 (`resolveSubagentRouting`), covered by
 [`tests/scripts/_lib_subagent_routing.test.ts`](../../../../tests/scripts/_lib_subagent_routing.test.ts).
-Budget layer: [`src/scripts/_lib/tier_budget_routing.ts`](../../../../src/scripts/_lib/tier_budget_routing.ts)
-(`pickTier`, `acquireBudgetPermit`, cool-downs), covered by
+Tier vocabulary + cool-down state:
+[`src/scripts/_lib/tier_budget_routing.ts`](../../../../src/scripts/_lib/tier_budget_routing.ts)
+(`TIER_ORDER`, `readCooldowns` — the budget decision layer that used to live
+there is archived, see step 4), covered by
 [`tests/scripts/tier_budget_routing.test.ts`](../../../../tests/scripts/tier_budget_routing.test.ts);
 live state: `agent-config routing:doctor` (orchestration section).
 

package/dist/agent-src/contexts/subagent-configuration.md

@@ -15,21 +15,83 @@ Loaded by the `subagent-orchestration` skill and the `/do-and-judge`,
 ## Model tier ladder
 
 The "one tier up" fallback walks this ladder. Session model is the
-starting point; judge picks the tier above.
+starting point; judge picks the tier above. The ladder is written in
+**bands**, not vendor models — the package keeps exactly one tier→model
+mapping and it lives in
+[`model-recommendations`](model-recommendations.md) (ADR-035 § 3). A
+second per-vendor ladder here would be the two-clocks drift ADR-232 was
+careful not to create.
 
 ```
-haiku  →  sonnet  →  opus
+lite  →  medium  →  high
 ```
 
-If the session runs on **opus**, judge stays on opus (no higher tier
-available). If the session runs on **sonnet**, judge defaults to opus.
-If the session runs on **haiku**, judge defaults to sonnet.
+If the session runs at **`high`**, judge stays at `high`. If the session
+runs at **`medium`**, judge defaults to `high`. If the session runs at
+**`lite`**, judge defaults to `medium`.
+
+### The judge cap (binding)
+
+```
+THE ONE-TIER-UP ESCALATION STOPS AT `high` — IT NEVER CLIMBS INTO `frontier`.
+A JUDGE IS NEVER BELOW ITS OWN IMPLEMENTER: A DECLARED `frontier`
+IMPLEMENTER KEEPS A `frontier` JUDGE.
+A SATURATED LADDER ESCALATES CROSS-VENDOR VIA THE COUNCIL —
+NEVER INTO A SECOND SAME-VENDOR TOP-BAND AGENT.
+```
+
+Two clauses that are easy to collapse into one and must not be. The cap
+binds the **escalation**, not the floor:
+
+| Implementer band | Judge band | Why |
+|---|---|---|
+| `lite` | `medium` | one tier up |
+| `medium` | `high` | one tier up |
+| `high` | `high` | escalation capped — never climbs into `frontier` |
+| `frontier` | **`frontier`** | the floor wins: a judge is never below its author |
+
+`frontier` (ADR-232) sits above `high` in the vocabulary, so a naive
+"one tier up" would resolve a `high` implementer's judge to `frontier`
+and buy the most expensive band available for every verification pass.
+The cap forecloses that — `frontier` is opt-in by declaration only.
+
+**But the cap must not invert the ladder it protects.** Reading it as a
+flat ceiling would give a declared `frontier` implementer a `high`
+judge, i.e. a reviewer strictly *weaker* than the author — worse than
+the same-band case the one-tier-up rule exists to avoid, and a direct
+contradiction of "never downshifts its judge below what the verify
+contract requires" below. So `frontier` reaches the judge only where
+the implementer already declared it, never by escalation from `high`.
+
+**What to do when the ladder saturates.** At `high` and at `frontier`
+the judge is same-band — the reviewer is no stronger than the author,
+which is the condition the one-tier-up rule existed to avoid. The
+answer is *different vendor*, not *bigger model*:
+
+- Route the saturation case through
+  [`ai-council`](../skills/ai-council/SKILL.md), which polls models
+  outside the host session (Anthropic + OpenAI) and is therefore
+  genuinely independent of the implementer's framing.
+- This is the escalation **instead of** a second top-band context, not
+  in addition to one. Two same-vendor top-band agents on one task cost
+  twice and correlate their blind spots; a second vendor costs less and
+  disagrees for real reasons.
+- Cost boundary unchanged: the council is a network call and is
+  therefore never automatic. It is what the saturation case escalates
+  *to* when a second opinion is wanted, not a step every `high` task
+  takes ([`ai-council`](../skills/ai-council/SKILL.md) § Do NOT use).
+
+**Honest scope.** This is policy prose in a context file — it binds the
+agent that reads it and no gate re-derives a judge tier at dispatch
+time. `enforced_by: none`, stated rather than implied.
 
 **Downshift never touches the judge.** When cost-aware routing runs an
 implementer on a downshifted tier (per the category → tier defaults in
 [`model-recommendations § Subagent Category → Tier Defaults`](model-recommendations.md)),
-the judge still resolves one tier above the IMPLEMENTER's resolved tier —
-so a `lite` implementer gets at least a `medium` judge. Downshifting an
+the judge still resolves one tier above the IMPLEMENTER's resolved tier,
+**with the escalation capped at `high` per the judge cap above** — so a
+`lite` implementer gets at least a `medium` judge, and no *downshifted*
+implementer escalates its judge into `frontier`. Downshifting an
 implementer never downshifts its judge below what the verify contract
 requires, and a judge is never `lite`.
 

package/dist/agent-src/rules/autonomous-execution.md

@@ -67,7 +67,7 @@ ALLOWLIST > 20 ENTRIES IN ONE SESSION = THE LINTER IS WRONG.
 STOP. PROPOSE LINTER REDESIGN OR REMOVAL. DO NOT EXPAND THE ALLOWLIST FURTHER.
 ```
 
-Crossing 20 entries counts as the 3rd validation-target failure — fix the tool shape, not the list. Enforced at tool-call time by the `block-config-weakening` PreToolUse guard (`src/scripts/hooks/block_config_weakening.ts`) **on the three hosts that have a `pre_tool_use` slot at all** — augment, claude, cowork: it counts allowlist entries added per session, warns from 5, and blocks past 20. On cursor, cline, windsurf, gemini and copilot the guard has nowhere to bind, so there the cap is model-carried and "enforced at tool-call time" is not a claim this rule can make. Run `agent-config hooks:status` to see which slots are bound on the host you are actually on — the sibling rules `git-history-discipline` and `evaluator-independence` qualify the identical slot, and an unqualified claim here would read as a guarantee the manifest does not give. Baselines and budget thresholds warn only — a rising count there may be a legitimate ratchet reset, which the edit alone cannot distinguish. Verify with the narrowest tool that proves the target green (a single `curl` / Playwright spec for HTTP/UI, the test runner with a `--filter`, an `xdebug` step-through) — never a meta-pipeline as per-iteration probe. Failed-attempt detail, suppression-sweep equivalents, probe-efficiency detail, and adaptive effort & stop (RDP): [`autonomy-mechanics § Validation-loop budget`](../contexts/execution/autonomy-mechanics.md).
+Crossing 20 entries counts as the 3rd validation-target failure — fix the tool shape, not the list. Enforced at tool-call time by the `block-config-weakening` PreToolUse guard (`src/scripts/hooks/block_config_weakening.ts`) **on `claude`, the one host that both binds `pre_tool_use` and honours a deny**: it counts allowlist entries added per session, warns from 5, and blocks past 20. It is *bound* on augment and cowork as well, and ignored there — `host_semantics.ts` verifies claude alone, and both trampolines discard dispatcher output and `exit 0` unconditionally. Everywhere else the cap is model-carried and "enforced at tool-call time" is not a claim this rule can make. **Corrected 2026-08-17 in both directions:** this sentence used to certify augment, claude and cowork as the enforcing set (an over-claim of two hosts) and to explain the rest with "the guard has nowhere to bind" (false for cursor, cline and gemini, whose native pre-tool events `native_event_aliases` already maps onto `pre_tool_use` — unbound, not unbindable; only windsurf and copilot have no pre-tool surface). The four states are tabulated once in [`hook-architecture-v1 § Which hosts carry pre_tool_use`](../docs/contracts/hook-architecture-v1.md). Run `agent-config hooks:status` to see which slots are bound on the host you are actually on — the sibling rules `git-history-discipline` and `evaluator-independence` qualify the identical slot, and an unqualified claim here would read as a guarantee the manifest does not give. Baselines and budget thresholds warn only — a rising count there may be a legitimate ratchet reset, which the edit alone cannot distinguish. Verify with the narrowest tool that proves the target green (a single `curl` / Playwright spec for HTTP/UI, the test runner with a `--filter`, an `xdebug` step-through) — never a meta-pipeline as per-iteration probe. Failed-attempt detail, suppression-sweep equivalents, probe-efficiency detail, and adaptive effort & stop (RDP): [`autonomy-mechanics § Validation-loop budget`](../contexts/execution/autonomy-mechanics.md).
 
 Body migrated to `contexts/execution/autonomy-mechanics.md` (per P4 of `road-to-kernel-and-router.md`) — opt-in detection summary, task-scope shapes table, N=3 mechanics, allowlist-antipattern detail, probe efficiency, adaptive effort (RDP).
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).

package/dist/agent-src/rules/design-fidelity.md

@@ -171,7 +171,7 @@ introduced. The row that would have caught it is
 and it exists only because a review asked for it after the trigger had already
 shipped. Write that row first next time; it is the cheap half.
 
-Body migrated to [`guideline:design-fidelity-mechanics`](../docs/guidelines/design-fidelity-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — surgical visual edits (targeted-edit vs redesign-trigger discipline, stable anchors), asset & imagery discipline (owned-asset path, third-party delivery is self-hosted by default, real-imagery-as-proof, iconography floor, no unrequested filler), deviation-surfacing shape, failure-mode catalog, `daf-*` fixtures.
+Body migrated to [`guideline:design-fidelity-mechanics`](../docs/guidelines/design-fidelity-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — URL / live-page handover (extraction into the `design-system.json` contract before the first UI write, the retrieval order, the lock boundary), surgical visual edits (targeted-edit vs redesign-trigger discipline, stable anchors), asset & imagery discipline (owned-asset path, third-party delivery is self-hosted by default, real-imagery-as-proof, iconography floor, no unrequested filler), deviation-surfacing shape, failure-mode catalog, `daf-*` fixtures.
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 
 ## See also

package/dist/agent-src/rules/design-review-after-ui-write.md

@@ -114,11 +114,16 @@ still have no runtime consumer. A test — not a code path — keeps the two fro
 drifting: `ui_rule_triggers.test.ts` asserts every `file_pattern` declared here
 is accepted by that predicate.
 
-Warn-only, capped at two nudges per session, default-OFF, bound only on hosts
-carrying a `pre_tool_use` slot. A nudge that can be ignored is not enforcement,
-so `enforced_by:` stays `none` — it moves the day a mechanism can refuse, not
-the day a reminder appears. `agent-config hooks:status` answers whether the
-concern is bound on the host you are actually on.
+Warn-only, capped at two nudges per session, default-OFF, and bound only in the
+three `platforms:` rows that carry a `pre_tool_use` key — augment, claude,
+cowork (**clarified 2026-08-17**: "hosts carrying a slot" read as a host
+property and is a manifest one; three further hosts alias a native pre-tool
+event with no binding, and only claude honours a deny — see
+[`hook-architecture-v1 § Which hosts carry pre_tool_use`](../docs/contracts/hook-architecture-v1.md)).
+The verdict is unchanged either way: a nudge that can be ignored is not
+enforcement, so `enforced_by:` stays `none` — it moves the day a mechanism can
+refuse, not the day a reminder appears. `agent-config hooks:status` answers
+whether the concern is bound on the host you are actually on.
 
 What that leaves, and it is the useful part: the write side now has a named
 obligation and a route to the skill that discharges it, where before it had