@event4u/agent-config 1.18.0 → 1.20.0

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Shared agent configuration \u2014 skills for AI coding tools (Claude Code, Augment, Cursor, Cline, Windsurf, Gemini CLI).",
-    "version": "1.18.0"
+    "version": "1.20.0"
   },
   "plugins": [
     {
@@ -39,9 +39,8 @@
         "./.claude/skills/bug-fix",
         "./.claude/skills/bug-investigate",
         "./.claude/skills/chat-history",
-        "./.claude/skills/chat-history-checkpoint",
-        "./.claude/skills/chat-history-clear",
-        "./.claude/skills/chat-history-resume",
+        "./.claude/skills/chat-history-import",
+        "./.claude/skills/chat-history-learn",
         "./.claude/skills/chat-history-show",
         "./.claude/skills/check-current-md",
         "./.claude/skills/check-refs",
@@ -74,6 +73,7 @@
         "./.claude/skills/dashboard-design",
         "./.claude/skills/data-flow-mapper",
         "./.claude/skills/database",
+        "./.claude/skills/dcf-modeling",
         "./.claude/skills/dependency-upgrade",
         "./.claude/skills/description-assist",
         "./.claude/skills/design-review",
@@ -105,6 +105,7 @@
         "./.claude/skills/fix-refs",
         "./.claude/skills/fix-seeder",
         "./.claude/skills/flux",
+        "./.claude/skills/funnel-analysis",
         "./.claude/skills/git-workflow",
         "./.claude/skills/github-ci",
         "./.claude/skills/grafana",
@@ -150,6 +151,7 @@
         "./.claude/skills/module-explore",
         "./.claude/skills/module-management",
         "./.claude/skills/multi-tenancy",
+        "./.claude/skills/okr-tree-modeling",
         "./.claude/skills/onboard",
         "./.claude/skills/openapi",
         "./.claude/skills/optimize",
@@ -195,6 +197,7 @@
         "./.claude/skills/requesting-code-review",
         "./.claude/skills/review-changes",
         "./.claude/skills/review-routing",
+        "./.claude/skills/rice-prioritization",
         "./.claude/skills/roadmap",
         "./.claude/skills/roadmap-create",
         "./.claude/skills/roadmap-execute",
@@ -227,6 +230,7 @@
         "./.claude/skills/threat-model",
         "./.claude/skills/threat-modeling",
         "./.claude/skills/traefik",
+        "./.claude/skills/unit-economics-modeling",
         "./.claude/skills/universal-project-analysis",
         "./.claude/skills/update-form-request-messages",
         "./.claude/skills/upstream-contribute",

package/AGENTS.md

@@ -14,6 +14,18 @@ when they install the package.
 
 ## What this repo is
 
+`event4u/agent-config` is a **governed skill suite** for two cognition
+clusters: engineering depth (Wing 1) and senior cross-department
+cognition (Wings 2–4: Product + Foundation, GTM + Growth, Money +
+Strategy + Ops). The differentiator is **depth over breadth, decisions
+over boilerplate, under a shared Iron-Law floor** (`commit-policy`,
+`non-destructive-by-default`, `language-and-tone`, `skill-quality`,
+`direct-answers`). The same agent that ships a refactor commit also
+runs DCF sensitivity, OKR-tree decomposition, and launch-funnel
+diagnosis — under the same governance.
+
+Mechanically the package is:
+
 - 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).
@@ -21,6 +33,26 @@ when they install the package.
 - Installed into consumer projects via `scripts/install.sh` (Bash) and
   `scripts/install.py` (Python bridge).
 
+## The four wings
+
+The skill suite is organized as four wings under one Iron-Law floor.
+Each wing has its own roadmap, its own personas, and its own plate;
+they compose via the cross-wing handoff contract
+([`docs/contracts/cross-wing-handoff.md`](docs/contracts/cross-wing-handoff.md) (beta),
+landing in `road-to-suite-closure.md` Phase 3).
+
+| Wing | Cognition cluster |
+|---|---|
+| **1 — Engineering** | Code craft, debugging, refactoring, release discipline; depth-first |
+| **2 — Product + Foundation** | Roles cluster (PM, designer, QA, EM); product discovery, prioritization, delivery shape |
+| **3 — GTM + Growth** | CMO + marketing + sales + lifecycle; channel-agnostic positioning + funnel cognition |
+| **4 — Money + Strategy + Ops** | CFO + COO + board-level strategy, valuation, org-design; stage-agnostic financial + operational cognition |
+
+Per-wing plates (roadmaps, persona maps, decision logs) live under
+`agents/roadmaps/` and `agents/contexts/`. Roadmaps are transient
+working layers — agents that need a wing's plate look it up by wing
+number rather than by file path (per `no-roadmap-references`).
+
 ## Source of truth
 
 | Directory | Purpose | Editable? |
@@ -48,6 +80,15 @@ No application code or framework runtime (no Laravel / Symfony / Next.js /
 Express). The `composer.json` / `package.json` are thin distribution
 manifests.
 
+**Cognition-only floor for Wings 2–4.** Wings 2, 3, and 4 enforce a
+no-SaaS-auth, no-vendor-SDK, no-stage-prescription floor: cognition
+artifacts (markdown tables, scoring rubrics, walkthroughs) must work
+in any host without external dependencies. The structural-malice
+check in `skill_linter.py` enforces this boundary mechanically (no
+credential exfiltration, no remote execution, no shell injection in
+subprocess calls — see `.agent-src.uncompressed/rules/skill-quality.md`
+§ Structural Malice Floor).
+
 ## Working on this repo
 
 ```bash
@@ -102,9 +143,9 @@ and
 
 ```
 .agent-src.uncompressed/      ← edit here
-  skills/       (129 skills)
-  rules/        (58 rules)
-  commands/     (95 commands)
+  skills/       (134 skills)
+  rules/        (56 rules)
+  commands/     (94 commands)
   personas/     (7 personas)
   templates/    (AGENTS.md, copilot-instructions.md, skill.md, …)
   contexts/

package/CHANGELOG.md

@@ -318,6 +318,179 @@ our recommendation order, not its support status.
   users" tension without removing any path that an existing user
   might rely on.
 
+## [1.20.0](https://github.com/event4u-app/agent-config/compare/1.19.0...1.20.0) (2026-05-06)
+
+### Features
+
+* **rules:** add no-attribution-footers + create-pr strip-pass ([7f72630](https://github.com/event4u-app/agent-config/commit/7f72630e0f334b30df6bc8ffc0fabb82fcca2fe3))
+* **orchestration:** mode-6 do-in-worktrees for cross-wing chains ([9087e50](https://github.com/event4u-app/agent-config/commit/9087e50f753fa5c4ef0eb1a048a64f7ccb4994af))
+* **cognition:** port five senior-tier cognition skills (Wings 3+4) ([aa958e7](https://github.com/event4u-app/agent-config/commit/aa958e772f82f05f3b23f9bbdd38ff0c8a89bd51))
+* **handoff:** cross-wing handoff contract + lint ([cb8e73a](https://github.com/event4u-app/agent-config/commit/cb8e73a8e0dd433d8e166ab926f585914aa5dbf1))
+* **skill-quality:** senior-tier authoring standard + structural malice lint ([bcbf8de](https://github.com/event4u-app/agent-config/commit/bcbf8de61f4d6b47fe244c80722886f512315caf))
+* **chat-history:** surface helper-built summary in session picker ([0bdd61b](https://github.com/event4u-app/agent-config/commit/0bdd61b1f00ed911ee5dbf764e9598f24d80fb54))
+* **infra:** relocate chat-history + prices to agents/ folder ([2727f26](https://github.com/event4u-app/agent-config/commit/2727f26bb986b4ed7414f466561ae600ca3a24ba))
+* **council:** add --model per-invocation override ([b21a20c](https://github.com/event4u-app/agent-config/commit/b21a20c16b49392070c62fc21af8ab887b8df978))
+* **settings:** expose chat_history.text_limits in template ([7941d7f](https://github.com/event4u-app/agent-config/commit/7941d7fd9a4a66fde046646661c0f8a467fc6900))
+* add docs-verified hook extractors for cursor/cline/windsurf/gemini ([5fa2e14](https://github.com/event4u-app/agent-config/commit/5fa2e14dd5cd2b88156d36d5cc47d9fad918758a))
+* **hooks:** universal capture + redact tooling for verified-platforms roadmap ([32a6ecd](https://github.com/event4u-app/agent-config/commit/32a6ecdc1f68c7187aa73a98e2116fb2f26ee201))
+* **hooks:** cowork platform support + hook-manifest tightening ([6016286](https://github.com/event4u-app/agent-config/commit/601628601dde7bb15e0e5ae4d3d23fbdeac8d3a9))
+* **chat-history:** schema v4 — stateless multi-session, position-based pruning, work-engine hook fix ([364990b](https://github.com/event4u-app/agent-config/commit/364990b3768af8d19bb6ecca916d3e5dac8c56c4))
+* **chat-history:** shrink session sidecar to {fp, started_at} ([c00a3e2](https://github.com/event4u-app/agent-config/commit/c00a3e27691637c1ffe9ca6b05d1f0531c95e85d))
+* **chat-history:** add /chat-history learn for selective historical context import ([2a88511](https://github.com/event4u-app/agent-config/commit/2a885111399eac7a5756edfaea5981e403e93177))
+* **chat-history:** add session isolation (schema v3) with read filter and sessions API ([6fd118d](https://github.com/event4u-app/agent-config/commit/6fd118d0f138068789e2167226a524ef92b82eab))
+* **contexts:** drop handshake context, slim platform-hooks doc ([ad39197](https://github.com/event4u-app/agent-config/commit/ad39197a089d79b00263625a4c84bb1ed1937193))
+* **commands:** trim /chat-history to show-only ([ba1d305](https://github.com/event4u-app/agent-config/commit/ba1d305e2ca6365a0668113ce94a3c3afc78bcee))
+* **work-engine:** drop chat-history turn-check + heartbeat hooks ([7883e64](https://github.com/event4u-app/agent-config/commit/7883e640bf880bf371ad1dd14a37b1f79d9aaf88))
+* **chat-history:** auto-adopt on session_start + delete cooperative rules ([579a1bc](https://github.com/event4u-app/agent-config/commit/579a1bcdea2b4fe7dbff8d650997c35d5366d292))
+
+### Bug Fixes
+
+* **no-roadmap-refs:** drop roadmap file links from stable artifacts ([b4a56f4](https://github.com/event4u-app/agent-config/commit/b4a56f499d1c070ad658fb9a87b6d272f1d05b79))
+* **public-links:** tag cross-wing-handoff as beta, drop link into agents/contexts/ ([89ac1ac](https://github.com/event4u-app/agent-config/commit/89ac1ac13ce52d26914abe14de2336f68f4e252f))
+* **check-refs:** allow runtime-bootstrapped agents/.agent-prices.md ([5b45a17](https://github.com/event4u-app/agent-config/commit/5b45a176cc42a04a771a01aa9384a0ad8da0b222))
+* **roadmap:** demote Kill-switch headings so check-roadmap-trackable stops parsing them as phases ([3029195](https://github.com/event4u-app/agent-config/commit/3029195c75eb16b95f57dd2c04401f8ead63f5e9))
+* **roadmap:** repair remaining check-refs errors in event-driven-discipline ([bd8f908](https://github.com/event4u-app/agent-config/commit/bd8f908f9d5955cb8aa8a6b8c841076f0ee4dc91))
+* **roadmap:** repair broken refs in event-driven-discipline ([6584a52](https://github.com/event4u-app/agent-config/commit/6584a5221a0fdb05b2f69d7a6b5c9c4c7b8ee163))
+* **chat-history:** migrate stale v3 header in-place on first hook write ([d239a39](https://github.com/event4u-app/agent-config/commit/d239a3903a81a569ee2cd372dd3c6c709153bbb8))
+* **lint:** add skills frontmatter to /chat-history learn ([01e8db3](https://github.com/event4u-app/agent-config/commit/01e8db31a1822c275dff6410fed2622ba9683fad))
+* **readme:** drop agents/contexts/ deep-link, mark hook-architecture-v1 as beta ([eeacbeb](https://github.com/event4u-app/agent-config/commit/eeacbeb1e748e98613102f0008756a5db155159b))
+
+### Documentation
+
+* **roadmaps:** add productization + kernel-and-router roadmaps ([1f7fbd4](https://github.com/event4u-app/agent-config/commit/1f7fbd4aca67e33a086d90e8a9e316ab0d7d8815))
+* **roadmap:** add road-to-package-optimization + dashboard sync ([016597f](https://github.com/event4u-app/agent-config/commit/016597ff468bc74cfefa0af9e86052cce872d865))
+* **analysis:** add package-optimizer design comparison ([607cf7f](https://github.com/event4u-app/agent-config/commit/607cf7f2b1786b62b36265798f66daa057d37e8f))
+* **council:** add package-optimizer design Q&A ([2211a59](https://github.com/event4u-app/agent-config/commit/2211a59fc8ae408a18a01101ac33711eda8a8285))
+* **roadmap:** add road-to-token-optimization + dashboard sync ([6348108](https://github.com/event4u-app/agent-config/commit/6348108162993e5947eea3d5612e43c4fdc18686))
+* **analysis:** add token-optimizer design comparison ([05462cf](https://github.com/event4u-app/agent-config/commit/05462cf17ebab4dd9c02b9683bc741e5be3c8a12))
+* **council:** add token-optimizer skill design Q&A ([eb6f9c3](https://github.com/event4u-app/agent-config/commit/eb6f9c3aad9c4ef20707181f8f3454f37f405761))
+* **roadmap:** add road-to-ruflo-adoption + dashboard sync ([009d94d](https://github.com/event4u-app/agent-config/commit/009d94d26c83c28dc0b2bac52b7109ff5f6a72d9))
+* **analysis:** add ruflo harvest comparison ([55d371c](https://github.com/event4u-app/agent-config/commit/55d371c1d427d20391f875430541d47b81fb9095))
+* **council:** add ruflo harvest prioritization Q&A ([7452d39](https://github.com/event4u-app/agent-config/commit/7452d3966bd6f7ce8e8f6e03e88a6bc6acb6fef8))
+* **roadmap:** add road-to-mobile-adoption + dashboard sync ([ca092df](https://github.com/event4u-app/agent-config/commit/ca092df913d00870d3227e212e507075462f0d87))
+* **analysis:** add mobile harvest comparison ([6791a78](https://github.com/event4u-app/agent-config/commit/6791a780276da3fccd100d6f5fd6b6e29c466673))
+* **council:** add mobile harvest prioritization Q&A ([48cc665](https://github.com/event4u-app/agent-config/commit/48cc6655927447e18fea455c89c7c7066c4ec9f6))
+* **roadmap:** add road-to-deep-research-adoption + dashboard sync ([9adc2d8](https://github.com/event4u-app/agent-config/commit/9adc2d8b0dd7ee0cdd2b919a4d776cab0f9f4b7a))
+* **analysis:** add deep-research harvest comparison ([4f5ead5](https://github.com/event4u-app/agent-config/commit/4f5ead50ee02de32016262fe6189208c7f9c6cbc))
+* **council:** add deep-research harvest prioritization Q&A ([1b08ea5](https://github.com/event4u-app/agent-config/commit/1b08ea5bdac158bb119f0851684f391e69e26c72))
+* add Microck deep-scan harvest analysis, council artifacts, and roadmap ([36baf23](https://github.com/event4u-app/agent-config/commit/36baf23ef898ab860163fcacfa9239a403032df0))
+* add Microck methodology comparison analysis ([1e34e78](https://github.com/event4u-app/agent-config/commit/1e34e788877a9f6101af5426587de63156e267dd))
+* add markitdown adoption analysis, council artifacts, and roadmap ([276b5d4](https://github.com/event4u-app/agent-config/commit/276b5d4374547386d407b1a01995620c90754363))
+* **suite:** lock identity as four-wing governed skill suite ([47c8211](https://github.com/event4u-app/agent-config/commit/47c8211ab7b42fa97352f747e2081fba82fe92b5))
+* **roadmap:** expand event-driven-discipline with platform tiers ([11edf9b](https://github.com/event4u-app/agent-config/commit/11edf9bb7666eaac18f7b8937437ff07db2b28f7))
+* sync active command count to 94 (drift fix) ([9be26bc](https://github.com/event4u-app/agent-config/commit/9be26bc6f4a2dbfd2bb53fe7052ce5717a6f9c47))
+* **roadmap:** event-driven agent discipline v3 ([71728cd](https://github.com/event4u-app/agent-config/commit/71728cde49a08f74c9fb44b133befcd4b6b89796))
+* **hooks:** relocate payload capture guide to docs/ ([4d39510](https://github.com/event4u-app/agent-config/commit/4d395108d461137e4df15adb04eed5fdd2a27dbb))
+* **rules,roadmap:** inline user-interaction failure-mode catalog + chat-history verified-platforms roadmap ([7ec07a0](https://github.com/event4u-app/agent-config/commit/7ec07a0733179373bcf3df6affcefe75ce341440))
+* **chat-history:** document v3 sidecar shape and legacy kill-switch ([2d1a393](https://github.com/event4u-app/agent-config/commit/2d1a39316c595810b24cc5e14fb153a2cf6a48c3))
+* bump remaining 92 → 93 command counts in browse + tools blurb ([1eeb019](https://github.com/event4u-app/agent-config/commit/1eeb019e34f1dfa0747e65eee304b8897c650389))
+* regenerate index/catalog and tag sidecar-shrink complexity ([c8e25d8](https://github.com/event4u-app/agent-config/commit/c8e25d86f6b19b10c06a7d845dc81da840ea6fb6))
+* bump command count to 93 across README, AGENTS, and architecture ([1902f22](https://github.com/event4u-app/agent-config/commit/1902f2230c433f1f33bf2ae4ad2cfbf2cfc3274c))
+* **chat-history:** document session-isolation read contract in platform-hooks context ([a59602e](https://github.com/event4u-app/agent-config/commit/a59602e8ad160f2da90ca8553b4e7c5fd8f62a60))
+
+### Refactoring
+
+* **work-engine:** remove obsolete chat-history heartbeat hook ([df2c6f1](https://github.com/event4u-app/agent-config/commit/df2c6f101edd60f77877c6162753c5b7d13f1992))
+* **chat-history:** split learn into import + project-learning workflow ([e11daa5](https://github.com/event4u-app/agent-config/commit/e11daa5c389ca1a4f3dd9b5ca123c57e145476c8))
+
+### Tests
+
+* **budget:** re-baseline TOP5_CEILING after language-and-tone re-sync ([3ac7b7b](https://github.com/event4u-app/agent-config/commit/3ac7b7b5b92d7a1cdfd6b80c6d77151034847939))
+
+### Chores
+
+* **matrix:** regenerate ownership matrix after no-attribution-footers add ([1bb7a9e](https://github.com/event4u-app/agent-config/commit/1bb7a9e452089f57f29c5aa74673fe682ecc682b))
+* **index:** regenerate after no-attribution-footers rule add ([0a95647](https://github.com/event4u-app/agent-config/commit/0a9564795b7d1c0a9e353927c07d9f15459f5ee8))
+* **tools:** regenerate .windsurfrules after no-attribution-footers trim ([d2a780b](https://github.com/event4u-app/agent-config/commit/d2a780b9c538c22fdc56ebcb1c245b23dababdee))
+* **rules:** trim no-attribution-footers to satisfy long_rule budget ([c407192](https://github.com/event4u-app/agent-config/commit/c40719271caddb1ccb0bf7e144aa42a295e391a5))
+* **ci:** unblock PR #44 — broken refs + word-count regression ([eccede0](https://github.com/event4u-app/agent-config/commit/eccede000451c4cec5b547deca1d78e0d3d916b5))
+* regenerate roadmap progress dashboard ([0c68f5b](https://github.com/event4u-app/agent-config/commit/0c68f5b354a61865836cde2e07fbfb19a3446e31))
+* **ownership-matrix:** regenerate after suite-closure work ([0b7f992](https://github.com/event4u-app/agent-config/commit/0b7f9920702df1e8b5b7db47d596caec312e0c17))
+* **roadmaps:** tag wing roadmaps with complexity: structural ([1e0c9c6](https://github.com/event4u-app/agent-config/commit/1e0c9c6b32e5ba16f34e62efb56a5a563a42b11c))
+* **index:** regenerate agents/index and docs/catalog ([9a3c1cb](https://github.com/event4u-app/agent-config/commit/9a3c1cb5c6730e5d48c85b85cf055f6e0302a5a7))
+* **sync:** refresh compression hashes and gitignore ([5f91975](https://github.com/event4u-app/agent-config/commit/5f91975f81c2c1ba0bf079b8366750e2aec1e984))
+* **roadmaps:** regenerate roadmaps-progress dashboard ([3d85dbd](https://github.com/event4u-app/agent-config/commit/3d85dbd854cbabc0c85c47685bdb96a22338a9fa))
+* **council:** remove unused playwright transport-mode scaffold ([672c512](https://github.com/event4u-app/agent-config/commit/672c5126e477ec43e4cc50d17e34f7ee3bca9a53))
+* **council:** default transport mode to manual instead of api ([4a41dfb](https://github.com/event4u-app/agent-config/commit/4a41dfbbaf879f5333ba5b665d5a0e32c4fac82d))
+* **roadmap:** regenerate roadmaps-progress dashboard ([6b01795](https://github.com/event4u-app/agent-config/commit/6b01795a267d5f69c5754ef7d59fbb125187be3a))
+* **ownership:** regenerate file-ownership matrix ([383d580](https://github.com/event4u-app/agent-config/commit/383d5808d5a0234149a69deb744625b1bc983b95))
+* **compress:** re-compress language-and-tone + user-interaction mirrors ([66a9f91](https://github.com/event4u-app/agent-config/commit/66a9f91520775f0097e33f688b2a2fa458c2d14b))
+* **index:** regenerate index + catalog after command-count sync ([03cf603](https://github.com/event4u-app/agent-config/commit/03cf603e84feedb7eea1845f39f258dbf0225f3a))
+* **hashes:** refresh compression hashes for language-and-tone + user-interaction ([fc361b4](https://github.com/event4u-app/agent-config/commit/fc361b49f19c14ddc3e4b8aa33093d1f9fa4ca7c))
+* add chat history cross agend hardening ([b9b9adb](https://github.com/event4u-app/agent-config/commit/b9b9adb2fb14ca089e92070a57821762269517b6))
+* **rules:** tighten language-and-tone and user-interaction iron laws ([57fa47d](https://github.com/event4u-app/agent-config/commit/57fa47d4331f0c2043165d82a3cbb2941c6278f9))
+* **roadmap:** archive road-to-verified-chat-history-platforms ([b1881f0](https://github.com/event4u-app/agent-config/commit/b1881f084d2d2f9eba225d7144345163fcb0e1b3))
+* **handoff:** close cowork chat-history handoff after council verification ([99190c9](https://github.com/event4u-app/agent-config/commit/99190c9f0f3c475ca11bab0e0482b20e82c1717c))
+* **roadmap:** regenerate roadmap-progress dashboard ([c7e2ff1](https://github.com/event4u-app/agent-config/commit/c7e2ff14b6d7afc593a2d9b12775f16fe491e452))
+* **roadmap:** archive sidecar-shrink roadmap with council notes ([3cd3826](https://github.com/event4u-app/agent-config/commit/3cd3826d86197e8e5297cef300d97ca23d7efc40))
+* regenerate file-ownership matrix for /chat-history learn ([537e13e](https://github.com/event4u-app/agent-config/commit/537e13e2ccea293d9f15a0a68ee27bf21f1ddbb7))
+* **roadmaps:** archive hook-only and session-isolation; add sidecar-shrink follow-up ([099a81d](https://github.com/event4u-app/agent-config/commit/099a81de5b90bd28dd7e4748612cf2efaf71ff28))
+* **docs:** drop roadmap citations from superseded markers ([369eb7e](https://github.com/event4u-app/agent-config/commit/369eb7e33b831daf3cf3a1348637596913923bbe))
+* **docs:** sync command counts to 92 after chat-history trim ([0b20e8f](https://github.com/event4u-app/agent-config/commit/0b20e8f05332974ad6ace222dfa152b086a42bf8))
+* **docs+settings:** hook-only sweep + remove dead phase-coupling guard ([5a66dc9](https://github.com/event4u-app/agent-config/commit/5a66dc954959c0dd02babb0661014fbf387ffec4))
+
+## [1.19.0](https://github.com/event4u-app/agent-config/compare/1.18.0...1.19.0) (2026-05-05)
+
+### Features
+
+* **rules:** treat slash command as operator and prose as target ([f73947e](https://github.com/event4u-app/agent-config/commit/f73947e93bc8121524d811a5f17d548499023751))
+* **ai-council:** auto-prune session folders past retention window ([bbfaa93](https://github.com/event4u-app/agent-config/commit/bbfaa93fd28bc3a84030c30ab9cea429ac68bea5))
+* **settings-sync:** additive sync with verbatim user-line preservation ([f996cf3](https://github.com/event4u-app/agent-config/commit/f996cf3811e924d2ffecbc3d11bac447308efc5a))
+* **roadmap:** add quality_cadence setting to throttle /roadmap execute pipeline runs ([d5ef7bf](https://github.com/event4u-app/agent-config/commit/d5ef7bf85e70c95103c6fc65507f99fdd35050dd))
+* **ci:** add lint_showcase_sessions gate ([c4f48bb](https://github.com/event4u-app/agent-config/commit/c4f48bba05d266899282742320b7f83bc636cc7c))
+* **council:** add CLI entry-point with estimate/run/render subcommands (Phase 6.7) ([f20f599](https://github.com/event4u-app/agent-config/commit/f20f5993dda1325f19f8e26a130ef37f995b5a9d))
+* **taskfile:** modularize Taskfile.yml into taskfiles/ groups (Phase 6.1) ([41cbe46](https://github.com/event4u-app/agent-config/commit/41cbe46d6f9289c98bb3f717dcac74c44154fc21))
+* **hooks:** add verify-before-complete and minimal-safe-diff concerns ([2507aef](https://github.com/event4u-app/agent-config/commit/2507aefcc88857fd120cfd09d5c93555cb89b868))
+* **governance:** one-off-script lifecycle + showcase capture + tier-retrofit archive ([0940f91](https://github.com/event4u-app/agent-config/commit/0940f91d74a759de6601f5367e8fd3e2925f4c51))
+* **work_engine:** decision-trace + memory-visibility hooks, scoring, contracts ([91cb0a5](https://github.com/event4u-app/agent-config/commit/91cb0a547971ff5f9597997bc36607ca6049be89))
+* **rules:** tier frontmatter sweep across all 58 rules + lint + budget rebaseline ([a9c3694](https://github.com/event4u-app/agent-config/commit/a9c3694bb22cbd87574c1ffd53d0cb9b76a60479))
+* **hooks:** per-platform bridges, install integration, hooks:status, smoke ([c33058a](https://github.com/event4u-app/agent-config/commit/c33058a49a20c6d4d21a7933b85ea3b618a6d433))
+* **hooks:** universal dispatcher, manifest, envelope, state I/O ([28c4f8c](https://github.com/event4u-app/agent-config/commit/28c4f8c7f0e7bd50b6403dfeab0dcaa623dd5ca3))
+* add collision check to roadmap creation flow ([19b65d5](https://github.com/event4u-app/agent-config/commit/19b65d5f2500ddb7c8bfcbb7466c33de0d64043c))
+
+### Bug Fixes
+
+* **ai-council:** use max_completion_tokens for OpenAI o1 models ([8d9e179](https://github.com/event4u-app/agent-config/commit/8d9e179a36d3ba2c68de09ba426782fd43792b85))
+* **skills/roadmap-management:** drop task-ci literal to satisfy portability lint ([790af5e](https://github.com/event4u-app/agent-config/commit/790af5e61a3af3472027d2eef1d939106c95d6ea))
+* **install.sh:** avoid SIGPIPE race in clean_stale that deleted live files ([08670d6](https://github.com/event4u-app/agent-config/commit/08670d66c6285a84d15e44d00e5cfecc6870a4e7))
+* **roadmaps:** re-anchor relative paths in archived 3a protocol ([e0017de](https://github.com/event4u-app/agent-config/commit/e0017de1b55b43e2c8ea5b3f9b51f077cb68e0e3))
+
+### Performance
+
+* **ci:** parallelise test suite — bash xargs -P + pytest-xdist ([2e74b31](https://github.com/event4u-app/agent-config/commit/2e74b3104d0a881832cbebb4dcaddecc865b65c3))
+* **ai-council/bundler:** fix catastrophic regex backtracking in redact() ([0e277e7](https://github.com/event4u-app/agent-config/commit/0e277e7ca36b452cc1cc4d8abdeaaa14e9aebbaf))
+
+### Documentation
+
+* **roadmaps:** add chat-history hook-only reduction roadmap ([529f3b7](https://github.com/event4u-app/agent-config/commit/529f3b7c06fae8b560ce0bb436fc701b1418a024))
+* **roadmaps:** add road-to-proof-not-features draft ([4664bd4](https://github.com/event4u-app/agent-config/commit/4664bd42a0e0bd8ff9eddc6d8907ff9a217a8f11))
+* tighten wording in three rules and one command ([14ed864](https://github.com/event4u-app/agent-config/commit/14ed8640f18e3bfc52819bb150066ecc453fb17a))
+* **roadmap:** archive road-to-feedback-consolidation (43/43 done) ([f053c6d](https://github.com/event4u-app/agent-config/commit/f053c6df94620a4cbf89e75ba73a7bb369c9395b))
+* **roadmap:** close Phase 1 — showcase infra shipped, sessions deferred ([49a156b](https://github.com/event4u-app/agent-config/commit/49a156b40eecd728841b2eaef3565850f1020e0a))
+* **roadmap:** close Phase 6 — mark 6.1/6.4/6.5/6.7 complete (89%) ([4b645cf](https://github.com/event4u-app/agent-config/commit/4b645cf9fc9acb7b7bc227f790e00c3efae66790))
+* **readme:** 3-path entry table + tier-coverage drift sentinel (Phase 6.4 + 6.5) ([ae712f0](https://github.com/event4u-app/agent-config/commit/ae712f034e5eb67481175835d7a9eded921ee222))
+* **roadmap:** mark Phase 5 complete (Tier-1 hook concerns shipped) ([433c5d1](https://github.com/event4u-app/agent-config/commit/433c5d1efb352de26671caed0e24a6b1e673eab6))
+* **readme:** trim under 500-line linter ceiling ([2c3b496](https://github.com/event4u-app/agent-config/commit/2c3b496552cdd73b02e7b08d5c231a9f86e326c3))
+* **agents:** roadmap progress, ownership matrix, agents index sync ([2368e37](https://github.com/event4u-app/agent-config/commit/2368e37aee886125997bfda4299599ebea9a14ec))
+* add feedback consolidation roadmap and regenerate dashboard ([96fce45](https://github.com/event4u-app/agent-config/commit/96fce45055b2da367b8a45536c7a5bdcd1e03d84))
+
+### Refactoring
+
+* **hooks:** concerns share atomic-write state I/O + dispatcher-friendly stdin ([5cac705](https://github.com/event4u-app/agent-config/commit/5cac705edfd46ad8d27ffd0008bdf4723317a4eb))
+
+### Tests
+
+* **hooks:** parity tests for tier-1 hook concerns ([540468c](https://github.com/event4u-app/agent-config/commit/540468cd150447d6b588d3015865660a555e4f8d))
+
+### Chores
+
+* **tools:** regenerate .windsurfrules with slash-command-routing-policy operator/target sections ([7825600](https://github.com/event4u-app/agent-config/commit/78256000a2da9cc313eb272059bb363acbc5290e))
+* **rules:** sync compressed slash-command-routing-policy with operator/target sections ([916357c](https://github.com/event4u-app/agent-config/commit/916357c7d185d717187845478e8318025330d3a9))
+* **rules:** promote verify-before-complete and minimal-safe-diff to tier 2a ([d62fb84](https://github.com/event4u-app/agent-config/commit/d62fb845a14065706c46c4425b261b57ac155c27))
+* ignore .agent-chat-history.session sidecar ([42741c8](https://github.com/event4u-app/agent-config/commit/42741c87f83bf24416eb3916cbced865ae642688))
+* **infra:** wire lint-rule-tiers + lint-hook-manifest + lint-one-off-age tasks; pyproject pytest importlib; .windsurfrules Copilot fallback ([5b88093](https://github.com/event4u-app/agent-config/commit/5b8809398dd332a3ebad3478f7a38cf48ef119e1))
+* **roadmaps:** archive structural-optimization companion artefacts ([928c884](https://github.com/event4u-app/agent-config/commit/928c88469787cd037c54acd0006039ee9b86f9bb))
+
 ## [1.18.0](https://github.com/event4u-app/agent-config/compare/1.17.0...1.18.0) (2026-05-04)
 
 ### Features

package/README.md

@@ -7,20 +7,22 @@ Give your AI agents an audit-disciplined orchestration contract — testing, Git
 > 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>129 Skills</strong> · <strong>58 Rules</strong> · <strong>95 Commands</strong> · <strong>51 Guidelines</strong> · <strong>8 AI Tools</strong>
+  <strong>134 Skills</strong> · <strong>56 Rules</strong> · <strong>94 Commands</strong> · <strong>51 Guidelines</strong> · <strong>8 AI Tools</strong>
 </p>
 
 ---
 
 ## Start here
 
-New to agent-config? 60 seconds, three links:
+Three ways in, depending on what you're doing today:
 
-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.
+| Path | Audience | What it does |
+|---|---|---|
+| **[`/onboard`](.agent-src/commands/onboard.md)** | New user, fresh install | Captures name, IDE, rtk, and cost profile; sets `onboarding.onboarded=true` |
+| **[`task ci`](docs/development.md#ci--verification)** | Contributor working **on** this package | Runs the full sync + lint + test pipeline; must be green before push |
+| **[`task generate-tools`](docs/development.md#tool-generation)** | Multi-agent user / consumer project | Rebuilds `.claude/`, `.cursor/`, `.clinerules/`, `.windsurfrules` from the source |
 
----
+If none of those apply yet — start with the [Quickstart](#quickstart) and pick a path once it's installed.
 
 ## Quickstart
 
@@ -63,6 +65,14 @@ project-locally for all supported AI tools. Task is required for
 *contributors* who want to rebuild the compressed content locally — see
 [CONTRIBUTING.md](CONTRIBUTING.md).
 
+**Verify hook coverage** after installing — every supported platform
+(Augment, Claude Code, Cowork, Cursor, Cline, Windsurf, Gemini CLI,
+Copilot fallback) is wired through one universal dispatcher per
+[`hook-architecture-v1`](docs/contracts/hook-architecture-v1.md) (beta). Run
+`./agent-config hooks:status` for the matrix (`--strict` for CI,
+`--format json` for tooling). The installer also dry-fires the
+dispatcher per bridge as a post-install smoke test (skip: `--no-smoke`).
+
 ### For individual use (optional)
 
 Install directly in your agent for global, cross-project use:
@@ -332,7 +342,7 @@ Nothing runs automatically without your control. [Configure modes →](docs/cust
 | [`/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 95 active commands](.agent-src/commands/)
+→ [Browse all 94 active commands](.agent-src/commands/)
 
 ---
 
@@ -357,7 +367,7 @@ 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 + 129 skills + 95 native commands). Cursor, Cline, Windsurf,
+> package (rules + 134 skills + 94 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.
@@ -479,20 +489,10 @@ task lint-skills   # Lint skills, rules, commands
 
 ## Requirements
 
-**To install the package into a consumer project:**
-
-- **Bash** — primary installer is `scripts/install`, orchestrating
-  `scripts/install.sh` (payload sync) and `scripts/install.py` (bridges).
-  Available on macOS, Linux, and WSL.
-- **Python 3.10+** — required for the bridge stage only. Pre-installed
-  on macOS 12.3+ and all major Linux distros. If missing, the
-  orchestrator skips bridges and completes the payload sync.
-- **Composer or npm** — to pull the package itself.
-
-**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/).
+- **Bash** — `scripts/install` orchestrates payload sync (`install.sh`) and bridges (`install.py`).
+- **Python 3.10+** — bridge stage only; missing → orchestrator skips bridges.
+- **Composer or npm** — to pull the package.
+- **Platform:** macOS 12.3+, Linux, WSL2. Git Bash needs Developer Mode for symlinks; native PowerShell / cmd unsupported. Contributors rebuilding `.augment/` also need [Task](https://taskfile.dev/).
 
 ## License
 

package/config/agent-settings.template.yml

@@ -84,7 +84,7 @@ eloquent:
 
 # --- Chat history (crash recovery) ---
 #
-# Persistent JSONL log at .agent-chat-history (project root, git-ignored).
+# Persistent JSONL log at agents/.agent-chat-history (git-ignored).
 # Keeps a durable record of the conversation so a crashed or switched
 # agent session can be resumed. See scripts/chat_history.py for the API.
 chat_history:
@@ -105,12 +105,19 @@ chat_history:
   #   compress = mark for summarization on the next agent turn
   on_overflow: __CHAT_HISTORY_ON_OVERFLOW__
 
-  # Heartbeat marker visibility (token-cost knob)
-  #   on     = print the 📒 marker every reply (~20 tokens/reply, legacy)
-  #   off    = never print (zero tokens, drift only visible by reading the file)
-  #   hybrid = print only on drift states (missing/foreign/returning); silent otherwise
-  # YAML 1.1 booleanizes bare on/off — both are accepted, no quoting needed.
-  heartbeat: hybrid
+  # Per-entry-type text-length caps (chars). 0 = verbatim, no slice.
+  # N > 0 = collapse whitespace, slice to N chars, append " … [+K chars]"
+  # so the log self-reports truncation. Defaults match the hardcoded
+  # fallback in scripts/chat_history.py (DEFAULT_TEXT_LIMITS).
+  #   user  = your messages — full text by default (most valuable for crash recovery)
+  #   agent = agent replies — capped to keep the log compact under load
+  #   tool  = tool inputs/outputs — short by default; bump for noisy debugging
+  #   phase = workflow phase markers — short by default
+  text_limits:
+    user: 0
+    agent: 5000
+    tool: 200
+    phase: 200
 
 # --- Optional pipelines ---
 pipelines:
@@ -121,6 +128,24 @@ pipelines:
   # want a silent agent; `custom` profile ignores this default entirely.
   skill_improvement: true
 
+# --- Roadmap execution ---
+#
+# Controls when /roadmap execute runs the project's quality pipeline
+# (the `task ci` / `make test` / `npm run check` style command).
+# Steps are ALWAYS marked `[x]` and the dashboard is ALWAYS regenerated
+# in the same response — that cadence is governed by `roadmap-progress-sync`
+# and is non-negotiable. This setting only governs *quality tool runs*.
+roadmap:
+  # When to run quality tools during /roadmap execute.
+  #   end_of_roadmap = once, before archiving the completed roadmap (default — fastest, fewest tokens)
+  #   per_phase      = once after every completed phase
+  #   per_step       = after every completed step (legacy verbose; highest token cost)
+  # Trade-off: end_of_roadmap saves tokens and time but lets errors compound
+  # across phases. Pick per_phase if the work is risky or unfamiliar.
+  # Iron Law `verify-before-complete` still applies — fresh quality output
+  # is mandatory before any "roadmap complete" claim regardless of cadence.
+  quality_cadence: end_of_roadmap
+
 # --- Subagent orchestration ---
 #
 # Controls model selection and parallelism for subagent-based workflows
@@ -161,12 +186,11 @@ ai_council:
   # 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).
+  #   api    = direct SDK call against the provider's API (billable).
+  #   manual = copy-paste loop, user is the transport (free).
   #
-  # Precedence: invocation flag > per-member mode > global mode > "api".
-  mode: "api"
+  # Precedence: invocation flag > per-member mode > global mode > "manual".
+  mode: "manual"
 
   # Per-member configuration. Set enabled=true on the providers you want
   # to consult. The model field selects which model receives the query.
@@ -186,7 +210,7 @@ ai_council:
   # 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
+  # Prices come from `agents/.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:
@@ -195,6 +219,11 @@ ai_council:
     max_calls: 10
     max_total_usd: 0.50
 
+  # Retention for `agents/council-sessions/` audit folders. Sessions
+  # older than this are pruned automatically on the next `save()`.
+  # `0` disables pruning (keep forever — disk grows unbounded).
+  session_retention_days: 14
+
 # --- Onboarding ---
 #
 # Tracks whether the initial setup flow (/onboard) has been completed

package/config/gitignore-block.txt

@@ -19,13 +19,13 @@
 .agent-settings.backup.key-value
 
 # Agent config — persistent chat history (crash recovery, never commit)
-.agent-chat-history
-.agent-chat-history.bak
-.agent-chat-history.*.bak
+/agents/.agent-chat-history
+/agents/.agent-chat-history.bak
+/agents/.agent-chat-history.*.bak
 
 # 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
+/agents/.agent-prices.md

package/docs/architecture.md

@@ -62,9 +62,9 @@ fails on any source-side violation, without producing artifacts.
 
 | Layer | Count | Purpose |
 |---|---|---|
-| **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`, … |
+| **Skills** | 134 | On-demand expertise — stack analysis (Laravel · Symfony · Zend / Laminas · Next.js · React · Node), testing, Docker, API design, security, observability, … |
+| **Rules** | 56 | Always-active constraints — coding standards, scope control, verification, language-and-tone, agent-authority |
+| **Commands** | 94 | Slash-command workflows — `/commit`, `/create-pr`, `/fix ci`, `/optimize skills`, `/feature plan`, `/work`, `/implement-ticket`, `/compress`, … |
 | **Guidelines** | 51 | 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 |