@event4u/agent-config 1.15.0 → 1.17.0

package/AGENTS.md

@@ -14,8 +14,9 @@ when they install the package.
 
 ## What this repo is
 
-- A distribution package, not an application.
-- `type: library` in `composer.json`; no `app/` directory, no Laravel runtime.
+- A distribution package, not an application of any framework.
+- `type: library` in `composer.json`; no `app/` directory, no application
+  runtime (no Laravel, Symfony, Next.js, or other framework app code).
 - Published to Composer and npm as `event4u/agent-config` / `@event4u/agent-config`.
 - Installed into consumer projects via `scripts/install.sh` (Bash) and
   `scripts/install.py` (Python bridge).
@@ -43,8 +44,9 @@ and run `task sync` (or `task ci`) to compress + regenerate the tool directories
 - **Taskfile** — developer entrypoints (`task ci`, `task sync`, `task test`)
 - **GitHub Actions** — CI workflow under `.github/workflows/`
 
-No PHP, no Laravel, no JavaScript runtime dependencies. The `composer.json` /
-`package.json` are thin distribution manifests.
+No application code or framework runtime (no Laravel / Symfony / Next.js /
+Express). The `composer.json` / `package.json` are thin distribution
+manifests.
 
 ## Working on this repo
 
@@ -78,7 +80,7 @@ When a user's free-form prompt matches a command's purpose, the agent
 surfaces matches as a numbered-options block with an always-present
 "run the prompt as-is" escape. **Nothing auto-executes** — the user
 picks every time. Engine: `scripts/command_suggester/`. Rule:
-[`.agent-src/rules/command-suggestion.md`](.agent-src/rules/command-suggestion.md).
+[`.agent-src/rules/command-suggestion-policy.md`](.agent-src/rules/command-suggestion-policy.md).
 Locked eligibility table, scoring contract, and hardening list:
 [`docs/contracts/adr-command-suggestion.md`](docs/contracts/adr-command-suggestion.md)
 and
@@ -100,14 +102,14 @@ and
 
 ```
 .agent-src.uncompressed/      ← edit here
-  skills/       (128 skills)
-  rules/        (55 rules)
-  commands/     (77 commands)
-  guidelines/   (46 guidelines)
+  skills/       (129 skills)
+  rules/        (58 rules)
+  commands/     (95 commands)
   personas/     (7 personas)
   templates/    (AGENTS.md, copilot-instructions.md, skill.md, …)
   contexts/
 
+docs/guidelines/            (47 guidelines — reference material, not packaged)
 .agent-src/                 ← compressed output shipped in the package
 .augment/                   ← local projection for Augment Code (gitignored)
 scripts/                    ← install.sh, install.py, compress.py, linters

package/CHANGELOG.md

@@ -126,7 +126,7 @@ baselines pin the R3 contract.
   `directives/mixed/` (`contract → ui → stitch`). Dispatched at the
   engine boundary on `state.directive_set`; the audit gate is enforced
   at the dispatcher AND at always-on rule level
-  ([`ui-audit-before-build`](.agent-src/rules/ui-audit-before-build.md))
+  ([`ui-audit-gate`](.agent-src/rules/ui-audit-gate.md))
   so cloud surfaces and free-form edits cannot bypass it.
 * **stack detection:** `scripts/work_engine/stack/detect.py` reads
   `composer.json` + `package.json` and labels the frontend as
@@ -318,6 +318,217 @@ our recommendation order, not its support status.
   users" tension without removing any path that an existing user
   might rely on.
 
+## [1.17.0](https://github.com/event4u-app/agent-config/compare/1.16.0...1.17.0) (2026-05-04)
+
+### Features
+
+* **commands:** nest commit/create-pr/feature sub-commands under colon namespace ([ceef48b](https://github.com/event4u-app/agent-config/commit/ceef48bd5b5ff550bc560e722516037a4f45e895))
+* **rules:** add no-roadmap-references rule + CI linter ([a2882a8](https://github.com/event4u-app/agent-config/commit/a2882a8a424b6bee8829426f19e531931e9c77c2))
+* **hooks:** add roadmap-progress-sync pilot hook ([48484f2](https://github.com/event4u-app/agent-config/commit/48484f28cf1ca8857c54d65e7965f62aed552ea2))
+* **budget:** add concentration gate + trend logging ([06f3855](https://github.com/event4u-app/agent-config/commit/06f385518e8326bc4528a7bf7ebfc0c639ddd89a))
+* **council:** add /council cluster dispatcher ([e7aa0c6](https://github.com/event4u-app/agent-config/commit/e7aa0c6970db634b484046f5899165e8fd3ac8a2))
+* **rules:** slim 12 auto-rules — extract mechanics to load_context (Phase 2B) ([9d211c6](https://github.com/event4u-app/agent-config/commit/9d211c68824dde0e7c21592a3079f76deae8cd96))
+* **commands:** Phase 1 — command cluster Phase 2 dispatchers + shims ([2e9d8e0](https://github.com/event4u-app/agent-config/commit/2e9d8e0fcb85f1b34d528a3f3e991e6cd5ba1388))
+* **followups:** land Phase 1 — load_context: rollout regression test + 1.15 archive verification (F2, F12) ([4ce552a](https://github.com/event4u-app/agent-config/commit/4ce552a8181668ee4c7ac20d669ce179dbdd4ab6))
+* **followups:** land Phase 0b.2 budget headroom recovery (F10) ([62838b3](https://github.com/event4u-app/agent-config/commit/62838b3df6fe7493876594ed84c908241cc286c7))
+* **structural:** lock Phase 0.4 2A.4 contract after council acceptance ([70a13d3](https://github.com/event4u-app/agent-config/commit/70a13d3a17bbea11a7b55af3bd8c16f130d954f2))
+* **structural:** land Phase 0.5 3a-spike scoring protocol + persona-voice rubric ([0fac3eb](https://github.com/event4u-app/agent-config/commit/0fac3ebafa00855d69dc9ca4cbade1a8b3797244))
+* **structural:** land Phase 0.4 2A.4 worked example ([e1412d3](https://github.com/event4u-app/agent-config/commit/e1412d345eb5432e4443b3e077bc1693d2cf3855))
+* **structural:** land Phase 0.3 Phase 6 -> 2B decoupling proof ([67b1024](https://github.com/event4u-app/agent-config/commit/67b1024560552547d79019c3566c1dec0299a948))
+* **structural:** land Phase 0.2 load_context: budget accounting model ([32cfcd4](https://github.com/event4u-app/agent-config/commit/32cfcd41d23998a705128c78f2c0a2bcdf341c87))
+* **structural:** land Phase 0.1 file-ownership matrix schema + generator ([d1dfb02](https://github.com/event4u-app/agent-config/commit/d1dfb024d4ef31aab88bfd749a6e5e5167ac5d75))
+* **structural:** land Phase 0.6 context-file path conventions ([e9c72f4](https://github.com/event4u-app/agent-config/commit/e9c72f4bde948c38bde6e5e740852c29582df91c))
+
+### Bug Fixes
+
+* **refs:** repair 4 broken cross-references ([7b0f014](https://github.com/event4u-app/agent-config/commit/7b0f014db19af0e9d68979a3ff9d12555f1ee6f5))
+* **sync:** prevent recursive _user prefixing and heal legacy corruption ([0cb0845](https://github.com/event4u-app/agent-config/commit/0cb0845320e14584348505fa0540315091ba7ef9))
+* **ci:** install pyyaml in consistency workflow ([bbad5d0](https://github.com/event4u-app/agent-config/commit/bbad5d06009a3f204051ca3b01102827162fe2f3))
+* **check-refs:** skip references into SKIP_DIRS (gitignored audit trails) ([cd6fcce](https://github.com/event4u-app/agent-config/commit/cd6fcce5411c35baaf228dc3fe0a4202acab6eca))
+* **roadmaps:** mark example/spike/coupling docs as status: draft ([d84dcf4](https://github.com/event4u-app/agent-config/commit/d84dcf44a9f777d87ef273b700ef66389216157d))
+* **compress:** carry load_context into compressed slash-command-routing-policy ([8332fb0](https://github.com/event4u-app/agent-config/commit/8332fb06a4c61ec65e9e21a6a123ea10484477de))
+
+### Documentation
+
+* repoint cross-references to nested command paths ([fbfb048](https://github.com/event4u-app/agent-config/commit/fbfb0481113aa065779ace75cbd0914eaf002d7c))
+* **roadmap:** add Phase 0a closeout hygiene to rule-hardening ([d68c4f2](https://github.com/event4u-app/agent-config/commit/d68c4f22d09ed9c3b567e996834c0148ffd17492))
+* sync command-count messaging in README/AGENTS/getting-started ([c683e9a](https://github.com/event4u-app/agent-config/commit/c683e9a4bc93294940a8f07402f88510796d91d8))
+* **roadmap:** rule-hardening v2 — council-reviewed revisions ([4d9e225](https://github.com/event4u-app/agent-config/commit/4d9e225108b9c647157eb1f6df9b55c13665588e))
+* **roadmaps:** add context-layer-maturity v2 and rule-hardening ([620961b](https://github.com/event4u-app/agent-config/commit/620961b3f469ddf0ac40ee491c3b65cab0e1000a))
+* **phase6:** chat-history-* trigger overlap audit — Path B (orthogonal) ([62ffad2](https://github.com/event4u-app/agent-config/commit/62ffad234c50ab9930115813e6801a2a8e976199))
+* **phase3:** consolidation audit — DO NOT CONSOLIDATE verdict ([03dc6aa](https://github.com/event4u-app/agent-config/commit/03dc6aad88aee2ebd85bd1d95f402742fcce05d1))
+* **readme:** trim Requirements section to clear lint-readme overload threshold ([30bf18d](https://github.com/event4u-app/agent-config/commit/30bf18da26ce69fe8bf1d688309ad375a082de6b))
+* **counts:** sync command-count messaging after Phase 1 clusters ([8902f49](https://github.com/event4u-app/agent-config/commit/8902f49f3239274828d13ce61a2b28a415dda3f5))
+* **roadmap:** drop slow-rollout protocol; lock single-PR execution (v3.2) ([35885b0](https://github.com/event4u-app/agent-config/commit/35885b01ee3c1510b2e30ad9a3bd40b686efefdf))
+* **followups:** land Phase 2 — README onboarding anchor + host-agent terminology (F1, F3, F4) ([cd12f97](https://github.com/event4u-app/agent-config/commit/cd12f9717c6b6e34efa01e55046d9f0ba0276286))
+* **roadmap:** close out 1.16 followups Phase 0a (F9 + F14 = no-op) ([6171f80](https://github.com/event4u-app/agent-config/commit/6171f805729d45084fee80704be9ec6908f1c84e))
+* **ai-council:** add experimental banner per F11 ([17308e1](https://github.com/event4u-app/agent-config/commit/17308e124fa436fac47f42649a5d1abcdb20f503))
+* **roadmap:** add 1.16.0 follow-ups roadmap v1.1 ([e402e1d](https://github.com/event4u-app/agent-config/commit/e402e1d599d1797a04a70b9fb538fa0bae913645))
+* **roadmap:** add structural-optimization roadmap v3.1 ([547f802](https://github.com/event4u-app/agent-config/commit/547f8024671e1f79570b2a5d69218f93ef1a346c))
+
+### Refactoring
+
+* **commands:** nest cluster commands into subdirectories ([5fd0df3](https://github.com/event4u-app/agent-config/commit/5fd0df387f0f2182e029fc3f40e5bce3fc4ed598))
+* **refs:** purge roadmap-file links from stable artifacts ([b5a1429](https://github.com/event4u-app/agent-config/commit/b5a1429e3f6a7fa754e816d9ddb1c4b0a6034735))
+* **rules:** amortize shared brevity examples to guideline ([ee581f6](https://github.com/event4u-app/agent-config/commit/ee581f69cc1106ec485dfb7f3ac07ffc2e2886cb))
+
+### Tests
+
+* **followups:** land Phase 0b.1 failure-mode coverage (F13) ([9560667](https://github.com/event4u-app/agent-config/commit/9560667a328f746316828ab44f0a7ba1fe8c254c))
+
+### Chores
+
+* **generated:** regenerate compressed dispatchers + hash registry ([552ddfe](https://github.com/event4u-app/agent-config/commit/552ddfeef4837b9681fc3ee72a1a01cf6c230d1a))
+* **commands:** drop ## Migration sections from cluster dispatchers ([02a03e7](https://github.com/event4u-app/agent-config/commit/02a03e7b7fbcc62c1203b7fedef38f0685e85321))
+* **generated:** regenerate compressed sources, tool projections, marketplace, ownership matrix ([f1dddd2](https://github.com/event4u-app/agent-config/commit/f1dddd2499625382b7f7902268bdd468426ce515))
+* **test:** align command-suggester golden + count gate to colon naming ([e1aad41](https://github.com/event4u-app/agent-config/commit/e1aad41624b877e4cb066d6e5075326de79f3693))
+* **generated:** regenerate file-ownership-matrix after command nesting ([12dc0f3](https://github.com/event4u-app/agent-config/commit/12dc0f3b266d6cdec6a53c918fc86098103d0373))
+* **generated:** regenerate compressed sources, tool projections,                    marketplace, and ownership matrix ([6724878](https://github.com/event4u-app/agent-config/commit/67248786c7589a63c2dabc80b683ace602611ddf))
+* **tooling:** teach scripts to walk nested command directories ([fe5913e](https://github.com/event4u-app/agent-config/commit/fe5913ef2ab6766a042d5e9470e0871d80804ddd))
+* **generated:** regenerate counts, hashes, windsurfrules ([5613b48](https://github.com/event4u-app/agent-config/commit/5613b4858da531a23aa27e23a2bda561152d3809))
+* **roadmaps:** archive 4 closed phase-evidence reports ([d5995c3](https://github.com/event4u-app/agent-config/commit/d5995c31febb3dad31df95d72970de1e1bcf3181))
+* **generated:** regenerate file-ownership-matrix ([75ff69f](https://github.com/event4u-app/agent-config/commit/75ff69fdb45952e00320918d597ea2db239a7f0b))
+* **generated:** regenerate windsurfrules + counts + claude council-default ([02ad3e1](https://github.com/event4u-app/agent-config/commit/02ad3e1079f797f8a72c33f800f1d395499b951e))
+* add ai council scripts ([4cf513c](https://github.com/event4u-app/agent-config/commit/4cf513c90649292324579444f586becd78cfad96))
+* **roadmap:** close & archive road-to-structural-optimization ([3bfef51](https://github.com/event4u-app/agent-config/commit/3bfef5118cdb66db5809fddb3688bb22d3aa8aff))
+* **compression:** refresh compression hashes ([20717d7](https://github.com/event4u-app/agent-config/commit/20717d798c86dd99f17d4c851ea0a8754e249333))
+* regenerate ownership matrix after Phase 2B rule slimming ([17ac19c](https://github.com/event4u-app/agent-config/commit/17ac19cf1938c7fca945b4500c6232cfa4549f2c))
+* **structural:** regenerate file-ownership-matrix after Phase 1 clusters ([29aabb1](https://github.com/event4u-app/agent-config/commit/29aabb11351f9fe648644b508eb6d24a5870b160))
+* **sync:** regenerate agents/index.md + docs/catalog.md after Phase 1 clusters ([f07987a](https://github.com/event4u-app/agent-config/commit/f07987ac12aaa77cbc4c7584ac00607e5a438318))
+* **sync:** regenerate compressed outputs + tool projections for Phase 1 clusters ([99466c0](https://github.com/event4u-app/agent-config/commit/99466c0a77116c7ed70db38fd957d061ad18e307))
+* **sync:** compress contexts/judges/persona-voice-rubric.md into .agent-src/ ([4060d01](https://github.com/event4u-app/agent-config/commit/4060d01af0680c2a913295166b978b605b1453db))
+* **roadmap:** archive road-to-1-16-followups (100% done) + regen dashboard ([f78a9ad](https://github.com/event4u-app/agent-config/commit/f78a9ada649c01c03aa4e866e20bb32b547cd9d0))
+* **roadmap:** regenerate progress dashboard after 1.16 followups Phase 1+2 ([780db39](https://github.com/event4u-app/agent-config/commit/780db39b68230b68c51f158d8cc8b78e7937a40c))
+* **ai-council:** add multi-provider council scripts and openai sdk ([3c2360d](https://github.com/event4u-app/agent-config/commit/3c2360d137069287b7e2547a6132d36ebed09978))
+* add task command, to install chatgpt key ([1acea8b](https://github.com/event4u-app/agent-config/commit/1acea8b6dc329c70079cec42d5a98886c913acfd))
+
+### Other
+
+* **commands:** update cross-references to colon-namespaced sub-commands ([13caa6d](https://github.com/event4u-app/agent-config/commit/13caa6d9c116012f726947fa50a281ca34ce16c2))
+* fix_: thinking drift ([1d2d158](https://github.com/event4u-app/agent-config/commit/1d2d15833e6b9764e7c734e66b25cecdf1dc12ab))
+
+## [1.16.0](https://github.com/event4u-app/agent-config/compare/1.15.0...1.16.0) (2026-05-03)
+
+### Features
+
+* add no-cheap-questions always-rule with pre-send self-check ([2916210](https://github.com/event4u-app/agent-config/commit/2916210887f5ba9fc103d80585f0a8a0e2809686))
+* **lint:** load_context frontmatter convention + linter (Phase 2) ([f7c9c51](https://github.com/event4u-app/agent-config/commit/f7c9c5186e4264baee2a4cc299990ed9f87ded54))
+* **council:** B1–B4 host integration hooks ([f5ec711](https://github.com/event4u-app/agent-config/commit/f5ec71174f21f1f096fb4d8cff94feac2410835f))
+* **council:** specialised modes — /council-pr, /council-design, /council-optimize ([00ec7df](https://github.com/event4u-app/agent-config/commit/00ec7df94397addd4a09365b8e48f54441a3a496))
+* **council:** session persistence (D2) + daily budget guard (D3) ([b2395e9](https://github.com/event4u-app/agent-config/commit/b2395e9d325fb339fb45ada7f4e4297ee8e0811b))
+* **council:** multi-round debate (D1) + smart diff context (D4) ([3a06d8f](https://github.com/event4u-app/agent-config/commit/3a06d8f7b95ddb2db7b4d6d965f6b66abcda78a5))
+* **telemetry:** outcome-aware engagement events (P2 #9) ([bb8a7c3](https://github.com/event4u-app/agent-config/commit/bb8a7c39b9ecb36219eeb4d639706026f0e7db7b))
+* **rules:** expand rule-interaction matrix to 13 pairs across 9 rules ([0ce5891](https://github.com/event4u-app/agent-config/commit/0ce589148ea1a4b56a7fd782bc3492682850024e))
+* **ci:** add check-roadmap-trackable linter ([980e242](https://github.com/event4u-app/agent-config/commit/980e242189129271fb603222589eeb59864d3de6))
+* **check-portability:** F1.5 add identity-framing detector (Layer 5) ([9245f3b](https://github.com/event4u-app/agent-config/commit/9245f3b29cb3719df40c321b0e5c3f7ed50f19dc))
+* **ai-council:** Phase 2b — Manual mode + non-billable orchestrator path ([4cbe5ef](https://github.com/event4u-app/agent-config/commit/4cbe5ef6ff6959c42ebcb40df96f9e6a853d1d03))
+* **ai-council:** Phase 2a — neutral project-context handoff ([25b64dc](https://github.com/event4u-app/agent-config/commit/25b64dc55e0eeba66141d128a8963042735b05dd))
+* **ai-council:** pricing layer + per-member estimate gate + sequential overrun callback ([c6e0203](https://github.com/event4u-app/agent-config/commit/c6e0203acc8e50315e83ee56b156b95b00578fdc))
+* **installer:** add keys:install-* CLI commands and gitignore .agent-prices.md ([c4c29a6](https://github.com/event4u-app/agent-config/commit/c4c29a64bf9335cfb2ae764b7c49a4a3f1ff5ba6))
+* **ai-council:** add /council command + ai-council skill ([68e28e6](https://github.com/event4u-app/agent-config/commit/68e28e6992cd18b8808245b42e348d57f827359c))
+* **ai-council:** implement core orchestrator, bundler, clients, prompts ([d16ef04](https://github.com/event4u-app/agent-config/commit/d16ef04d2d734f527127e3ef884d6a975347d0bd))
+* **roadmap:** plan AI Council — external second-opinion workflow ([f973c38](https://github.com/event4u-app/agent-config/commit/f973c386fafa603bfc3d5935d8c1379d576e6236))
+* **governance:** F7 — universal identity reframe + archive completed roadmap ([8a259f0](https://github.com/event4u-app/agent-config/commit/8a259f0b41cbba8c70961f6e83f1c8dd08e02094))
+* **governance:** F6 — description-budget cap + augmentignore advisory ([5ac837d](https://github.com/event4u-app/agent-config/commit/5ac837d28971e4c8d679f5f3a1f25a0a4b6e50f7))
+* **governance:** F5 — index generator for internal + public catalogs ([bae4e19](https://github.com/event4u-app/agent-config/commit/bae4e198356a7994644f3c19c8da552d5d61560b))
+* **commands:** F2 — collapse fix/optimize/feature clusters into orchestrators ([5db2d1a](https://github.com/event4u-app/agent-config/commit/5db2d1a55533805c77195e35c800a89acdfe0bf3))
+* **rules:** F1.2-F1.5 — close always-rule budget breach (37,879/49,000) ([b9eb922](https://github.com/event4u-app/agent-config/commit/b9eb92232b6ec72209e60ee7d43f167489124690))
+* **rules:** add agent-authority Priority-Index router (F1.1) ([410653f](https://github.com/event4u-app/agent-config/commit/410653f1887bce755f314a97c542100e9dc4696e))
+
+### Bug Fixes
+
+* **rules:** trim no-cheap-questions to satisfy top-5 always-rule cap ([41e575b](https://github.com/event4u-app/agent-config/commit/41e575b8439f7f654f0c65284626dbe2c06b9e39))
+* **schema:** allow load_context in rule frontmatter ([342496e](https://github.com/event4u-app/agent-config/commit/342496e12adb7299bf6a20b5d7949aa657b0e6d4))
+* **scripts:** exempt README hero/blurb from update_counts ([6c6822a](https://github.com/event4u-app/agent-config/commit/6c6822aa055698c5d008d6487ab1a65ab5d65fd3))
+* **catalog:** point public catalog at shipped surface, add regression gate ([58ec2e9](https://github.com/event4u-app/agent-config/commit/58ec2e98b19aebe28ab2b718f2199adc2b6c6e82))
+* **rules:** trim language-and-tone.md to satisfy always-rule budget cap ([d20c99a](https://github.com/event4u-app/agent-config/commit/d20c99a36fba5e6c76f21f0be8f3435d699e8d2c))
+* **roadmap-progress:** support digit+letter phase ids (Phase 2a) ([968f7c6](https://github.com/event4u-app/agent-config/commit/968f7c64d39dfea043980cd5bc81af3970202966))
+* **rules:** add 'fenced step' clause to scope-control ([be337d8](https://github.com/event4u-app/agent-config/commit/be337d856b503fc4e15d9d4dfcad5b34f05b2597))
+
+### Documentation
+
+* **roadmap:** close + archive road-to-pr-34-followups ([4bb8d36](https://github.com/event4u-app/agent-config/commit/4bb8d3635eb4a8a386f8111ad2dd0a31ca4578fd))
+* **contracts:** Phase 7.2 — publish always-rule budget contract ([ff65861](https://github.com/event4u-app/agent-config/commit/ff65861db977688d9c0fb266c256aab710ba1d6e))
+* **roadmap:** close Phase 6 of road-to-pr-34-followups; mark 7.3 done ([0380083](https://github.com/event4u-app/agent-config/commit/0380083304a6ff22f0989acb3ff06259c58fe8b5))
+* **contracts:** Phase 6.1 — subdirectory conventions for contexts/ ([befdd92](https://github.com/event4u-app/agent-config/commit/befdd92d6cec1b6104316c0270d9dc124f9a2dce))
+* **roadmap:** close Phase 5 of road-to-pr-34-followups ([298b61f](https://github.com/event4u-app/agent-config/commit/298b61fac68efea9020d2a3e56327179116a29d1))
+* **roadmap:** insert Phase 5 CI drift hygiene; renumber 5/6 → 6/7 ([0e708a5](https://github.com/event4u-app/agent-config/commit/0e708a57b40688fe3aeb29ece85873abc6cbc270))
+* **roadmap:** narrow Phase 4.2 to existing engine vocabulary ([1905918](https://github.com/event4u-app/agent-config/commit/1905918cdfd1743680edc4ed1e22e9422424ed3c))
+* **roadmap:** reframe Phase 4 — engine halt tests, not LLM eval ([3eb2017](https://github.com/event4u-app/agent-config/commit/3eb2017a062c7c082d651a03ffe8521e804ae940))
+* **load-context:** close Phase 3 — first consumer documented + verified ([9b09833](https://github.com/event4u-app/agent-config/commit/9b098335e691ecf9c2808ceeabc318314379b367))
+* **reports:** verify autonomous-execution obligation surface (Phase 2.5) ([2e66d8c](https://github.com/event4u-app/agent-config/commit/2e66d8c416c6589203ce61969ebaa3ef347dd299))
+* **contexts:** extract autonomy EXAMPLES (Phase 2.3) ([4d56143](https://github.com/event4u-app/agent-config/commit/4d561437617c1cd74b1664bfab2154381f2352ae))
+* **contexts:** extract autonomy LOGIC + MECHANICS (Phase 2.2) ([1875f9a](https://github.com/event4u-app/agent-config/commit/1875f9a0ea5ac9fa2ef1f3074d98622d0ad2787e))
+* **roadmap:** pin Phase 2 to existing load_context: roots ([e2773f0](https://github.com/event4u-app/agent-config/commit/e2773f0635816d55f696d25be0aeb6107412949e))
+* **roadmap:** inventory autonomous-execution.md (Phase 2.1) ([2bead66](https://github.com/event4u-app/agent-config/commit/2bead66ae89c6f3f54e324e4c4ba7354a939032d))
+* **readme:** honest command count + governance-aligned hero wording ([1053d56](https://github.com/event4u-app/agent-config/commit/1053d56b3e52fd945a9c09555634abb74bfb2e81))
+* **roadmaps:** add road-to-pr-34-followups (round-6 review + round-7 hardening) ([7375759](https://github.com/event4u-app/agent-config/commit/737575907570dc22f83e6e0325ec3a6a85aaf2d7))
+* **roadmaps:** mark road-to-rebalancing complete + archive ([4c83f8e](https://github.com/event4u-app/agent-config/commit/4c83f8e752f83616209b79ae4fade551e932ef96))
+* **contracts:** add rule-priority-hierarchy.md (Phase 5) ([949c7a9](https://github.com/event4u-app/agent-config/commit/949c7a95689b273302dee3f3d1b9f8694425a213))
+* **rules:** point language-and-tone at the relocated examples doc ([45cc06c](https://github.com/event4u-app/agent-config/commit/45cc06c828d4535a013274952c3a3b627552d528))
+* **guidelines:** relocate language-and-tone-examples into agent-infra/ (Phase 3) ([579e162](https://github.com/event4u-app/agent-config/commit/579e162e960e4dd024888efcbab9ac98c5eb3601))
+* **roadmaps:** archive road-to-ai-council, mark council-modes Phase 2a/2b done ([9caba6d](https://github.com/event4u-app/agent-config/commit/9caba6d26a574591bafdc0e7c0a7f5434adbd717))
+* add end-to-end walkthroughs + complete road-to-1-15-followups (P1 #7) ([fa29fc4](https://github.com/event4u-app/agent-config/commit/fa29fc4279c020579e9cfdb6b79ded37268bc012))
+* **roadmaps:** mark P2 #9 shipped + regen dashboard ([821bcb1](https://github.com/event4u-app/agent-config/commit/821bcb16bd29cf2e06b260e341d6931d2a99677f))
+* **roadmap:** mark P0 #2/#3 + P1 #5/#6 verified shipped ([caccf12](https://github.com/event4u-app/agent-config/commit/caccf129e27ac81994bf549741704989b22e53fc))
+* **roadmaps:** canonicalize headings + tag drafts to satisfy linter ([a5e64b8](https://github.com/event4u-app/agent-config/commit/a5e64b8c8c051f79d3a3a1384f91136999a99150))
+* **rules:** harden roadmap-progress-sync with trackability Iron Law ([ef426cd](https://github.com/event4u-app/agent-config/commit/ef426cdfc7463f4ac44e0e323c7904b82f71a745))
+* **readme:** P0 #4 fix Token overhead wording in cost-profiles table ([1bcdb26](https://github.com/event4u-app/agent-config/commit/1bcdb26644875c5aee297957b0845bbab7240bc3))
+* **agents,copilot:** F1.4 generalize Laravel framing in AGENTS + copilot ([c282ae3](https://github.com/event4u-app/agent-config/commit/c282ae3a2ae93658de69dc92082399df552cb317))
+* **readme:** F1.3 reframe § Who this is for — Laravel as value, not headline ([2fa8022](https://github.com/event4u-app/agent-config/commit/2fa802269b2b936d621344dda0a995bd81bf9737))
+* **readme:** F1.2 neutralize opener stack-naming (Laravel ≠ headline) ([d26bf68](https://github.com/event4u-app/agent-config/commit/d26bf68a94ab0471a7270dea95b5cb35190ca581))
+* **roadmap:** F1.1 audit — Laravel-coloured identity language inventory ([2a42fad](https://github.com/event4u-app/agent-config/commit/2a42fad8b3f659d0c9c704942a3581cb7401057a))
+* **roadmap:** rewrite rebalancing roadmap around layered architecture ([5786d9c](https://github.com/event4u-app/agent-config/commit/5786d9c3f7ba8a668f4cf72478d72dfa463aef29))
+* **roadmap:** capture rebalancing roadmap from PR #34 review feedback ([55977d4](https://github.com/event4u-app/agent-config/commit/55977d4f60f4d665d26ea0f362fa2c581e7ebde5))
+* **ai-council:** Phase 2a/2b skill + command + roadmap updates ([c6b284f](https://github.com/event4u-app/agent-config/commit/c6b284fe8fd361636b2c52c75e03d679981bd231))
+* **roadmap:** capture 1.15.0 review followups -- identity rewrite as P0 #1 ([2abd676](https://github.com/event4u-app/agent-config/commit/2abd676aba025f5bc8efcd2ac2b5e27124f25a13))
+* **roadmap:** plan AI Council Phase 2 -- context-handoff, manual + playwright modes ([b578d6d](https://github.com/event4u-app/agent-config/commit/b578d6da916f98eed2baa57a00089b8815033f9f))
+* **ai-council:** document settings, install flow, and skill xref ([3b8a528](https://github.com/event4u-app/agent-config/commit/3b8a52875842fe4c939b2ae1049d347c0b7d443d))
+* **roadmap:** F3.1 close-out — 5 of 6 renames done, row 4 N/A ([713ff59](https://github.com/event4u-app/agent-config/commit/713ff5900fa1ba6e494286f8fa7403c6e26e3966))
+
+### Refactoring
+
+* **rules:** Phase 7.4 — slim non-destructive-by-default under 6k cap ([62d39ea](https://github.com/event4u-app/agent-config/commit/62d39ea296c0afe5822514d7c0c707ee91be7ce1))
+* **rules:** Phase 6.2 — migrate 3 rules to load_context ([0b93832](https://github.com/event4u-app/agent-config/commit/0b9383244ff90a0e0fbaa2b387c55f3d65672096))
+* **rules:** slim autonomous-execution + wire load_context: (Phase 2.4) ([94edd24](https://github.com/event4u-app/agent-config/commit/94edd24dd52e9d7ada2ecea4c90f23607686eda2))
+* **commands:** F2 — convert 15 atomic commands to deprecation shims ([84283cb](https://github.com/event4u-app/agent-config/commit/84283cbb98192f6f25e567c902aec246eb55e49a))
+* **governance:** F4 — update scripts, docs, and counts for relocated guidelines ([8234649](https://github.com/event4u-app/agent-config/commit/82346494df9efbca1392e55a858a993bec8b05c5))
+* **governance:** F4 — relocate guidelines to docs/guidelines/ ([6a82c0c](https://github.com/event4u-app/agent-config/commit/6a82c0c8e51fffb9ad0278a8f69fa03dcc2ab808))
+* **skills:** F3 — rename verify-before-complete (skill) → verify-completion-evidence ([1bada56](https://github.com/event4u-app/agent-config/commit/1bada563724a6a74c6e26dac988bde5c73d4246d))
+* **rules:** F3 — rename command-suggestion → command-suggestion-policy ([2338aef](https://github.com/event4u-app/agent-config/commit/2338aeff2f81fc28beae1ae79e1e5584237bf7d2))
+* **rules:** F3 — rename slash-commands → slash-command-routing-policy ([347caf8](https://github.com/event4u-app/agent-config/commit/347caf87cd2dbaeb90761f42865276789a0d89b7))
+* **rules:** F3.2 — rename ui-audit-before-build → ui-audit-gate ([dcab51a](https://github.com/event4u-app/agent-config/commit/dcab51ae1535d10b56ff0afaa3164cd595a1b0d3))
+
+### Tests
+
+* **golden:** lock governance anti-pattern baselines ([360f259](https://github.com/event4u-app/agent-config/commit/360f259b72e6d3ab69b4afc344aacf17beabf980))
+* **golden:** add governance anti-pattern recipes ([960c0ec](https://github.com/event4u-app/agent-config/commit/960c0ecf1c106c09a81930a53da10a88e4420f4e))
+* **ai-council:** contract tests for install_{openai,anthropic}_key.sh ([0e193bc](https://github.com/event4u-app/agent-config/commit/0e193bc588394dc41ae4f51cd65021c3c7c13521))
+* **naming:** F3.2 — guard policy-verb vs tool-noun naming split ([efbe2db](https://github.com/event4u-app/agent-config/commit/efbe2dbf04a25fc873e78f5522996ed57bfcc176))
+
+### CI
+
+* **budget:** Phase 7.4 — enforce per-rule 6k cap and top-3 ≤ 50% in CI + tests ([9e8b079](https://github.com/event4u-app/agent-config/commit/9e8b079fc8f11b274ff542d91469dd50381e5ae4))
+* **budget:** Phase 7.1 — always-rule budget gate (warn 80% / fail 90%) ([b3af9ad](https://github.com/event4u-app/agent-config/commit/b3af9ad04334d678bf0d49a60c13808ba17a4450))
+* **tests:** allow manual workflow_dispatch trigger on tests.yml ([e230e2b](https://github.com/event4u-app/agent-config/commit/e230e2bcb9e973a4450170cd4f09aba96116cb05))
+
+### Chores
+
+* finish council modes ([c1496e4](https://github.com/event4u-app/agent-config/commit/c1496e4a240be4210c7624b41cb389065bdf3aee))
+* update gitignore ([184c27f](https://github.com/event4u-app/agent-config/commit/184c27f6a8d9e7549432b9190f6c929ec1be63af))
+* **index:** regenerate index/catalog for no-cheap-questions ([7c45498](https://github.com/event4u-app/agent-config/commit/7c454983735680ebe1b9efb72ad0e4533997e9b6))
+* **tools:** regenerate .windsurfrules and rule symlinks ([8621e23](https://github.com/event4u-app/agent-config/commit/8621e23578c5200ce58888d1be3dc14a5705eb0e))
+* **check-refs:** skip agents/council-sessions/ ([53ff5a6](https://github.com/event4u-app/agent-config/commit/53ff5a6ba28508bcee257d90302073d17c822e49))
+* **index:** regen agents/index.md + docs/catalog.md for council-* commands ([c9d01e5](https://github.com/event4u-app/agent-config/commit/c9d01e5cb819042a4eecf47aec02ac9a8c96325b))
+* **rules:** mark roadmap-progress-sync cloud_safe degrade and trim under 200-line cap ([c740054](https://github.com/event4u-app/agent-config/commit/c74005487a3898ae416b704ad2fbeea4c4c8daf4))
+* **roadmap:** archive open-questions-3.md (all 13 closed) ([18ba9ba](https://github.com/event4u-app/agent-config/commit/18ba9ba789a9974e51258c2242c1bbb2dfbc5a52))
+* **roadmap:** regenerate progress dashboard after Q43 closure ([f027c55](https://github.com/event4u-app/agent-config/commit/f027c550c6a7fe66eb189440ce22a46990977c45))
+* **tools:** regenerate .windsurfrules after language-and-tone trim ([d9a6cf4](https://github.com/event4u-app/agent-config/commit/d9a6cf4921ca29787b4aaa46341eacd86493a8e8))
+* **ai-council:** recompress council.md (Q43) + refresh stale hash ([005ba1b](https://github.com/event4u-app/agent-config/commit/005ba1bcebcdf945df4023d720fe924471448d3d))
+* **ai-council:** post-install enable hint + close Phase-1 decisions ([595d475](https://github.com/event4u-app/agent-config/commit/595d475911f1621c84d846a2e10452611b7558f1))
+* **readme:** trim 'Who this is for' below 500-line linter budget ([e06237d](https://github.com/event4u-app/agent-config/commit/e06237dec5ae61f26cf9456c7584e500f4a36f0f))
+* **roadmap:** regenerate roadmaps-progress dashboard after F6 ([024916b](https://github.com/event4u-app/agent-config/commit/024916b2fe47deb4d77bc561ca9c8f82833c2da6))
+
 ## [1.15.0](https://github.com/event4u-app/agent-config/compare/1.14.0...1.15.0) (2026-05-02)
 
 ### Features
@@ -430,7 +641,7 @@ our recommendation order, not its support status.
 * **linear:** Phase 3 — Linear AI rules digest builder + three-layer split ([3dcbf0a](https://github.com/event4u-app/agent-config/commit/3dcbf0af3c2dca70ef70f18af70a3568516f0147))
 * **rules:** add commit-policy as canonical no-commit-no-ask rule ([fd208ea](https://github.com/event4u-app/agent-config/commit/fd208ea1c0f95aaa58d930c99ff0e51dd27600ed))
 * **rules:** add autonomous-execution rule with intent-based opt-in ([fbff529](https://github.com/event4u-app/agent-config/commit/fbff5299b32606b7f13f06c856a4d4556c908fcb))
-* **commands:** add /commit-in-chunks for autonomous commit splitting ([b53fa7b](https://github.com/event4u-app/agent-config/commit/b53fa7b277a107af8acc6076baf8c985f0fbb901))
+* **commands:** add /commit:in-chunks for autonomous commit splitting ([b53fa7b](https://github.com/event4u-app/agent-config/commit/b53fa7b277a107af8acc6076baf8c985f0fbb901))
 * **cloud:** mark T3-H artifacts cloud-safe (4 noop + 4 degrade) ([0eb7eb3](https://github.com/event4u-app/agent-config/commit/0eb7eb3cdbf590e3ef87f372c3fd09d85aa5cfd5))
 * **cloud:** cloud-safe marker detection + variant rendering ([67bf28b](https://github.com/event4u-app/agent-config/commit/67bf28b8f85384333f5d26807ad92e6d0b456288))
 * **cloud:** cloud-bundle builder with T3-H gating + tests ([f749edc](https://github.com/event4u-app/agent-config/commit/f749edc8c0f16cded153eb24580c4b262a6065ae))

package/README.md

@@ -2,16 +2,26 @@
 
 > **agent-config is not a runtime, but it ships a deterministic orchestration contract / state machine for host agents.**
 
-Teach your AI agents Laravel, PHP, testing, Git workflows, and **120+ more skills** — with quality guardrails built in.
+Give your AI agents an audit-disciplined orchestration contract — testing, Git, CI, code review, and **120+ stack-aware skills** — with quality guardrails built in.
 
-> Your agent learns to write Laravel code, run tests, create PRs, fix CI — and follows your team's coding standards while doing it.
+> Your agent picks up the project's stack, runs tests, prepares PRs, fixes CI — and follows your team's coding standards while doing it. Stack-aware skill sets ship for PHP (Laravel · Symfony · Zend/Laminas), JavaScript (Next.js · React · Node), and cross-stack concerns (API · testing · security · observability).
 
 <p align="center">
-  <strong>128 Skills</strong> · <strong>55 Rules</strong> · <strong>77 Commands</strong> · <strong>46 Guidelines</strong> · <strong>8 AI Tools</strong>
+  <strong>129 Skills</strong> · <strong>58 Rules</strong> · <strong>95 Commands</strong> · <strong>48 Guidelines</strong> · <strong>8 AI Tools</strong>
 </p>
 
 ---
 
+## Start here
+
+New to agent-config? 60 seconds, three links:
+
+1. **[Install](#quickstart)** — `composer require` or `npm install`, then run the installer.
+2. **[First command](#2-minute-demo-implement-ticket)** — `/implement-ticket` or `/work` walkthrough.
+3. **[Where the rules live](#documentation)** — `.augment/`, `.claude/`, `.cursor/`, and friends.
+
+---
+
 ## Quickstart
 
 Two minutes from `composer require` to a better-behaved agent.
@@ -177,7 +187,7 @@ switches the engine to one of three directive sets:
 
 Four load-bearing properties: (1) **existing-UI audit is a hard gate** —
 no `apply` without audit, enforced at dispatcher AND
-[`ui-audit-before-build`](.agent-src/rules/ui-audit-before-build.md) rule;
+[`ui-audit-gate`](.agent-src/rules/ui-audit-gate.md) rule;
 (2) **design brief is locked microcopy** — placeholders (`<placeholder>`,
 `Lorem`, `TODO:`) rejected at both ends; (3) **polish has a 2-round
 ceiling**, then halts ship-as-is / abort / hand-off; (4) **a11y precedence**
@@ -206,11 +216,11 @@ description of intent — not a guarantee of output.
 | Default behavior | With agent-config (the agent is instructed to) |
 |---|---|
 | Guess and edit blindly | Analyze code before changing it — no blind edits |
-| Drift from project conventions | Follow the project's PHP/Laravel coding standards |
-| Skip or invent tests | Write Pest tests following the project's conventions |
-| Write generic commit messages | Use Conventional Commits with scope and Jira links |
-| Skip quality checks | Run PHPStan, Rector, ECS and fix reported errors |
-| Open PRs without context | Produce structured PR descriptions from Jira tickets |
+| Drift from project conventions | Follow the project's coding standards (detected from the stack) |
+| Skip or invent tests | Write tests in the project's framework (Pest, PHPUnit, Vitest, Jest, …) |
+| Write generic commit messages | Use Conventional Commits with scope and ticket links |
+| Skip quality checks | Run the project's quality pipeline (PHPStan/Rector/ECS, ESLint/Prettier/tsc, …) and fix reported errors |
+| Open PRs without context | Produce structured PR descriptions from Jira / Linear / GitHub tickets |
 | Claim "done" without proof | Verify with real execution before claiming "done" |
 
 ---
@@ -252,9 +262,9 @@ session is explicitly not.
 
 Start with **Rules + Skills**. Everything else is optional.
 
-| Mode | What's active | Token overhead |
+| Mode | What's active | Runtime process overhead |
 |---|---|---|
-| **Minimal** (default) | Rules, Skills, Commands | Zero |
+| **Minimal** (default) | Rules, Skills, Commands | None |
 | **Balanced** | + Runtime Dispatcher for skills that declare a shell command | Low |
 | **Full** | + Tool Adapters (GitHub / Jira read-only, opt-in) | Moderate |
 
@@ -270,21 +280,17 @@ Nothing runs automatically without your control. [Configure modes →](docs/cust
 
 ## Who this is for
 
-The content is **built for PHP / Laravel teams** and is where the package
-is most useful out of the box. Skills, rules, and quality-tool integration
-assume a Laravel-style repository (Pest, PHPStan, Rector, ECS, Artisan,
-Composer workflows). You can install it on any project, but:
+`agent-config` ships a **stack-agnostic governance core** (orchestration contract, role modes, command clusters, quality gates, audit-discipline) plus **parallel stack-specific skill sets** at varying depth:
 
-| Stack | Fit |
+| Stack | Coverage |
 |---|---|
-| **Laravel / modern PHP** | ✅ Primary audience — most skills apply directly |
-| **Other PHP frameworks** (Symfony, Zend/Laminas) | ☑️ Deep-analysis skills apply; framework-specific ones do not |
-| **JavaScript / TypeScript / Next.js / Node** | ☑️ General skills + governance apply; PHP-specific skills are noise |
-| **Other stacks** | ⚠️ Cherry-pick rules/commands; expect to disable a lot |
+| Laravel · modern PHP | Skills, rules, project-analysis, quality-tool wiring (Pest · PHPStan · Rector · ECS) |
+| Symfony · Zend / Laminas | Project-analysis skills + shared PHP coder/quality skills |
+| Next.js · React · Node / Express | Project-analysis skills + UI directive set (`react-shadcn`) |
+| Vue · plain HTML | UI directive set (`vue` / `plain`) — analysis skills as they ship |
+| Cross-stack | API design · testing · security · database · Docker · Git · CI · review · threat modeling · observability |
 
-A language-agnostic core is on the roadmap but not yet extracted. If you
-adopt the package outside the primary audience, please open an issue so we
-can prioritize the right skills for extraction.
+**Deepest reference stack today: Laravel.** Skill density covers Pest, PHPStan, Rector, Eloquent, Livewire/Flux, Horizon, Pulse, Reverb, Pennant — the stack the package was first proven on. Other stacks ship in the order they are battle-tested, not second-class. Adopting on a thin stack? Open an issue so we can prioritize the right skills for extraction.
 
 ---
 
@@ -297,8 +303,8 @@ can prioritize the right skills for extraction.
 | [`eloquent`](.agent-src/skills/eloquent/SKILL.md) | Eloquent models, relationships, scopes, eager loading, type safety |
 | [`create-pr`](.agent-src/commands/create-pr.md) | Create GitHub PRs with structured descriptions from Jira tickets |
 | [`commit`](.agent-src/commands/commit.md) | Stage and commit changes following Conventional Commits |
-| [`fix-ci`](.agent-src/commands/fix-ci.md) | Fetch CI errors from GitHub Actions and fix them |
-| [`fix-pr-comments`](.agent-src/commands/fix-pr-comments.md) | Fix and reply to all open review comments on a PR |
+| [`/fix ci`](.agent-src/commands/fix.md) | Fetch CI errors from GitHub Actions and fix them |
+| [`/fix pr-comments`](.agent-src/commands/fix.md) | Fix and reply to all open review comments on a PR |
 | [`quality-fix`](.agent-src/commands/quality-fix.md) | Run PHPStan/Rector/ECS and fix all errors |
 | [`bug-analyzer`](.agent-src/skills/bug-analyzer/SKILL.md) | Root cause analysis from Sentry errors or Jira tickets |
 | [`improve-before-implement`](.agent-src/rules/improve-before-implement.md) | Challenge weak requirements before coding |
@@ -307,7 +313,7 @@ can prioritize the right skills for extraction.
 | [`api-design`](.agent-src/skills/api-design/SKILL.md) | REST conventions, versioning, deprecation |
 | [`database`](.agent-src/skills/database/SKILL.md) | MariaDB optimization, indexing, query performance |
 
-→ [Browse all skills](docs/skills-catalog.md) · [llms.txt](llms.txt)
+→ [Public catalog](docs/catalog.md) (all rules, skills, commands, guidelines) · [Skills only](docs/skills-catalog.md) · [llms.txt](llms.txt)
 
 ---
 
@@ -317,14 +323,16 @@ can prioritize the right skills for extraction.
 |---|---|
 | [`/commit`](.agent-src/commands/commit.md) | Stage and commit with Conventional Commits |
 | [`/create-pr`](.agent-src/commands/create-pr.md) | Create PR with Jira-linked description |
-| [`/fix-ci`](.agent-src/commands/fix-ci.md) | Fetch and fix GitHub Actions failures |
-| [`/fix-pr-comments`](.agent-src/commands/fix-pr-comments.md) | Fix and reply to review comments |
+| [`/fix ci`](.agent-src/commands/fix.md) | Fetch and fix GitHub Actions failures |
+| [`/fix pr-comments`](.agent-src/commands/fix.md) | Fix and reply to review comments |
+| [`/optimize skills`](.agent-src/commands/optimize.md) | Audit skills, find duplicates, run linter |
+| [`/feature plan`](.agent-src/commands/feature.md) | Interactively plan a feature |
 | [`/quality-fix`](.agent-src/commands/quality-fix.md) | Run and fix all quality checks |
 | [`/review-changes`](.agent-src/commands/review-changes.md) | Self-review before creating a PR |
 | [`/jira-ticket`](.agent-src/commands/jira-ticket.md) | Read ticket from branch, implement feature |
 | [`/compress`](.agent-src/commands/compress.md) | Compress skills for token efficiency |
 
-→ [Browse all 77 commands](.agent-src/commands/)
+→ [Browse all 95 active commands](.agent-src/commands/)
 
 ---
 
@@ -349,7 +357,7 @@ Every developer gets the same behavior. No per-user setup needed.
 native slash-commands)
 
 > **What this means in practice:** Augment Code and Claude Code get the full
-> package (rules + 128 skills + 77 native commands). Cursor, Cline, Windsurf,
+> package (rules + 129 skills + 95 native commands). Cursor, Cline, Windsurf,
 > Gemini CLI, and GitHub Copilot only get the **rules** natively; skills and
 > commands are available to them as documentation the agent can read, not as
 > first-class features.
@@ -481,20 +489,11 @@ task lint-skills   # Lint skills, rules, commands
   orchestrator skips bridges and completes the payload sync.
 - **Composer or npm** — to pull the package itself.
 
-**Platform support:**
-
-| Platform | Status |
-|---|---|
-| macOS 12.3+ | ✅ Supported |
-| Linux (modern distros) | ✅ Supported |
-| Windows (WSL2) | ✅ Supported |
-| Windows (Git Bash) | ⚠️ Works; symlinks need Developer Mode |
-| Windows (native PowerShell/cmd) | ❌ Not supported |
-
-**For contributors only** (rebuilding `.augment/` locally):
-
-- [Task](https://taskfile.dev/) — runs the CI pipeline (`task ci`).
+**Platform support:** macOS 12.3+, Linux (modern distros), and Windows
+(WSL2) are fully supported. Git Bash works but symlinks require
+Developer Mode; native PowerShell / cmd is not supported. Contributors
+rebuilding `.augment/` locally also need [Task](https://taskfile.dev/).
 
 ## License
 
-[MIT](LICENSE) — you can use, fork, and redistribute this freely.
+[MIT](LICENSE).

package/config/agent-settings.template.yml

@@ -138,6 +138,63 @@ subagents:
   # Integer, default 3. Set to 1 to serialize. Hard cap enforced by runtime.
   max_parallel: 3
 
+# --- AI Council (external second-opinion network) ---
+#
+# When enabled, the /council command lets the agent poll independent
+# external models (OpenAI, Anthropic) for a neutral critique of a
+# roadmap, diff, prompt, or file set. Council members never see the
+# host agent's reasoning — only the artefact + a neutral system prompt.
+#
+# Tokens are NEVER stored here. They live in ~/.config/agent-config/
+# <provider>.key (mode 0600), installed via:
+#   bash scripts/install_anthropic_key.sh
+#   bash scripts/install_openai_key.sh
+#
+# Cost note: every consultation makes real, paid API calls. The
+# autonomy directive does NOT silently spend tokens — the /council
+# command always asks before invoking, even under autonomy: on.
+ai_council:
+  # Master switch (true, false). Default false — installing a key is
+  # not the same as wanting the agent to spend money on it.
+  enabled: false
+
+  # Default transport mode for every member (overridable per-member
+  # below, and per-invocation via `/council mode:<x>`).
+  #
+  #   api        = direct SDK call against the provider's API (billable).
+  #   manual     = copy-paste loop, user is the transport (free).
+  #   playwright = browser automation (Phase 2c, not yet wired).
+  #
+  # Precedence: invocation flag > per-member mode > global mode > "api".
+  mode: "api"
+
+  # Per-member configuration. Set enabled=true on the providers you want
+  # to consult. The model field selects which model receives the query.
+  # Optional `mode:` overrides the global setting for that member only.
+  members:
+    anthropic:
+      enabled: false
+      model: "claude-sonnet-4-5"
+      # mode: "api"      # uncomment to override ai_council.mode
+    openai:
+      enabled: false
+      model: "gpt-4o"
+      # mode: "manual"   # uncomment to override ai_council.mode
+
+  # Hard cost ceiling per /council invocation. The orchestrator pauses
+  # before any member whose projected spend would breach a cap and asks
+  # the user to continue. `max_total_usd: 0` disables the USD ceiling
+  # (token caps still apply).
+  #
+  # Prices come from `.agent-prices.md` (gitignored, refreshed weekly
+  # by `python3 scripts/update_prices.py`; bootstrapped from
+  # scripts/ai_council/_default_prices.py on first run).
+  cost_budget:
+    max_input_tokens: 50000
+    max_output_tokens: 20000
+    max_calls: 10
+    max_total_usd: 0.50
+
 # --- Onboarding ---
 #
 # Tracks whether the initial setup flow (/onboard) has been completed
@@ -155,7 +212,7 @@ onboarding:
 # When the user's free-form prompt matches an eligible slash command,
 # the agent surfaces a numbered-options block with the recommendation
 # plus an always-present "run as-is" option. The suggestion layer
-# never auto-executes — the user picks. See rules/command-suggestion.md.
+# never auto-executes — the user picks. See rules/command-suggestion-policy.md.
 commands:
   suggestion:
     # Master switch (true, false). false = the layer is silent; explicit

package/config/gitignore-block.txt

@@ -26,3 +26,6 @@
 # Agent config — artefact engagement telemetry (default-off, maintainer-only, never commit)
 .agent-engagement.jsonl
 .agent-engagement.jsonl.bak
+
+# Agent config — AI Council price table (refreshed weekly, never commit)
+.agent-prices.md

package/docs/architecture.md

@@ -19,9 +19,7 @@ Stability tiers follow [`docs/contracts/STABILITY.md`](contracts/STABILITY.md):
 - **experimental** = scaffold or pilot status; breaks allowed in any release.
 
 > The previous "observability, feedback, lifecycle" layers were removed in
-> 1.5 — they were scaffolds without production consumers. See the
-> [`archive/road-to-9.md`](../agents/roadmaps/archive/road-to-9.md) roadmap,
-> phase 4, for the rationale.
+> 1.5 — they were scaffolds without production consumers.
 
 ## Content pipeline
 
@@ -64,10 +62,10 @@ fails on any source-side violation, without producing artifacts.
 
 | Layer | Count | Purpose |
 |---|---|---|
-| **Skills** | 128 | On-demand expertise — Laravel, testing, Docker, API design, security, ... |
-| **Rules** | 55 | Always-active constraints — coding standards, scope control, verification |
-| **Commands** | 77 | Slash-command workflows — `/commit`, `/create-pr`, `/fix-ci`, `/compress`, ... |
-| **Guidelines** | 46 | Coding guidelines by language — PHP patterns, Eloquent, Playwright, ... |
+| **Skills** | 129 | On-demand expertise — stack analysis (Laravel · Symfony · Zend / Laminas · Next.js · React · Node), testing, Docker, API design, security, observability, … |
+| **Rules** | 58 | Always-active constraints — coding standards, scope control, verification, language-and-tone, agent-authority |
+| **Commands** | 95 | Slash-command workflows — `/commit`, `/create-pr`, `/fix ci`, `/optimize skills`, `/feature plan`, `/work`, `/implement-ticket`, `/compress`, … |
+| **Guidelines** | 48 | Reference material cited by skills — PHP patterns, Eloquent, Playwright, agent-infra, … |
 | **Templates** | 7 | Scaffolds for features, roadmaps, contexts, skills, overrides |
 | **Contexts** | 5 | Shared knowledge about the system itself |