@event4u/agent-config 5.10.0 → 6.0.0

package/docs/architecture.md

@@ -34,7 +34,7 @@ Stability tiers follow [`docs/contracts/STABILITY.md`](contracts/STABILITY.md):
 
 Four load-bearing additions reshaped the top of the model between 2.2.2 and the current release. They are listed here so the diagram above reads as the *current* package, not a historical accumulation:
 
-1. **Router-Kernel** — the always-loaded Iron Laws collapsed into a 9-rule kernel with explicit per-rule character budgets enforced by `task lint-rule-budget`; everything else routes via tier-1/2 (`.agent-src/router.json`). Contract: [`kernel-membership.md`](contracts/kernel-membership.md) + [`rule-router.md`](contracts/rule-router.md) — both (beta).
+1. **Router-Kernel** — the always-loaded Iron Laws collapsed into a 9-rule kernel with explicit per-rule character budgets enforced by `task lint-rule-budget`; everything else routes via tier-1/2 (`dist/agent-src/router.json`). Contract: [`kernel-membership.md`](contracts/kernel-membership.md) + [`rule-router.md`](contracts/rule-router.md) — both (beta).
 2. **MCP Lite/Full** — replaces the old "Tool Adapters" layer at the top level. Lite is the hosted read-only surface (Claude.ai, Cloud agents); Full is the local stdio server consumers self-host. Promotion to beta is gated on six falsifiable artefacts in `docs/contracts/mcp-beta-criteria.md`; the old GitHub / Jira adapters remain as an internal detail of the Execution Contracts layer (see Tool Adapters subsection below).
 3. **npx distribution** — Composer and `npm install` paths retired in favour of `npx @event4u/agent-config`, with the lockfile-equivalent role played by `agent_config_version` in `.agent-settings.yml`. Full rationale in the "Distribution model" subsection below.
 4. **Command tiering** — `/`-commands now declare a `tier:` (0 / 1 / 2 / 3) that maps to invocation frequency and surface budget; tier-0 is the trimmed Tier-0 set surfaced in `agent-config --help` after the 2.7.x surface-discipline pass. Contract: [`command-surface-tiers.md`](contracts/command-surface-tiers.md) + [`command-clusters.md`](contracts/command-clusters.md) — both (beta).
@@ -53,7 +53,7 @@ and cites the script, Taskfile target, and test file that prove
 the pipeline.
 
 ```
-.agent-src.uncondensed/   ──Pipeline A──▶  .agent-src/
+.agent-src.uncondensed/   ──Pipeline A──▶  dist/agent-src/
                                               │
                                               ├──Pipeline B──▶  .augment/
                                               │
@@ -65,7 +65,7 @@ the pipeline.
 
 | Pipeline | Page | Output |
 |---|---|---|
-| **A.** Source projection | [`architecture/source-projection.md`](architecture/source-projection.md) | `.agent-src/` |
+| **A.** Source projection | [`architecture/source-projection.md`](architecture/source-projection.md) | `dist/agent-src/` |
 | **B.** Augment projection | [`architecture/augment-projection.md`](architecture/augment-projection.md) | `.augment/` |
 | **C.** Multi-tool projection | [`architecture/multi-tool-projection.md`](architecture/multi-tool-projection.md) | `.claude/`, `.cursor/`, `.clinerules/`, `.windsurfrules`, `GEMINI.md` |
 | **D.** Claude.ai bundle | [`architecture/claude-bundle.md`](architecture/claude-bundle.md) | `dist/cloud/<skill>.zip` |
@@ -79,13 +79,13 @@ Taskfile target — or vice versa.
 
 For every tool the package supports, **filesystem** is the canonical channel that the consumer installer (`scripts/install.sh`) writes — see [`contracts/skill-distribution-channels.md`](contracts/skill-distribution-channels.md). Pipeline C above always writes the filesystem trees (`.claude/skills/`, `.cursor/rules/`, `.clinerules/`, `.windsurfrules`, etc.) into the consumer project. Plugin manifests at the package source (`.claude-plugin/marketplace.json`, `.augment-plugin/marketplace.json`) are preserved for users who install via the host's plugin registry, but the installer does **not** project a second registry into consumer projects. Users on older harnesses that require both channels opt in with `bash scripts/install.sh --legacy-both`. Regression test: [`tests/test_canonical_distribution.py`](../tests/test_canonical_distribution.py).
 
-Cross-references inside `.agent-src/rules/*.md` are written
-**relative to `.agent-src/rules/`** (e.g. `../contexts/execution/foo.md`,
+Cross-references inside `dist/agent-src/rules/*.md` are written
+**relative to `dist/agent-src/rules/`** (e.g. `../contexts/execution/foo.md`,
 `../docs/guidelines/agent-infra/foo.md`). Source files under
 `.agent-src.uncondensed/rules/` use **logical names** without a
 directory prefix (e.g. `contexts/execution/foo.md`); the
 condense-time path rewriter in `scripts/condense.py` translates
-them to the relative form when writing into `.agent-src/`. Hardcoding
+them to the relative form when writing into `dist/agent-src/`. Hardcoding
 `.agent-src.uncondensed/` in source frontmatter or body links is
 forbidden and caught by `scripts/check_condensed_paths.py`.
 
@@ -116,7 +116,7 @@ collapses all three failure modes.
 `composer.lock` / `package-lock.json` previously froze the runtime
 version per repo. Under npx-only, the equivalent role is played by the
 `agent_config_version` field in the consumer's `.agent-settings.yml`
-(see `config/agent-settings.template.yml`). The dispatcher reads the
+(see `src/config/agent-settings.template.yml`). The dispatcher reads the
 pin on every invocation and re-execs `npx @event4u/agent-config@<pin>`
 if the resolved version diverges (P3.2 pin-resolver). The pin lives in
 the consumer's repo, is reviewed in PRs, and survives `npx`'s own
@@ -146,10 +146,10 @@ note, package-internal path-swap, description budget, and the
 
 | Layer | Count | Purpose |
 |---|---|---|
-| **Skills** | 223 | On-demand expertise — stack analysis (Laravel · Symfony · Zend / Laminas · Next.js · React · Node), testing, Docker, API design, security, observability, … |
+| **Skills** | 227 | On-demand expertise — stack analysis (Laravel · Symfony · Zend / Laminas · Next.js · React · Node), testing, Docker, API design, security, observability, … |
 | **Rules** | 79 | Always-active constraints — coding standards, scope control, verification, language-and-tone, agent-authority |
 | **Commands** | 150 | Slash-command workflows — `/commit`, `/create-pr`, `/fix ci`, `/optimize skills`, `/feature plan`, `/work`, `/implement-ticket`, `/condense`, … |
-| **Guidelines** | 73 | Reference material cited by skills — PHP patterns, Eloquent, Playwright, agent-infra, … |
+| **Guidelines** | 78 | 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 |
 
@@ -330,7 +330,7 @@ Installed (copy-if-missing) by `scripts/install.sh` from
 the installer never overwrites.
 
 The mechanical floor is `scripts/check_condensed_paths.py`, wired into
-`task ci` as `check-condensed-paths`. It validates `.agent-src/rules/*.md`:
+`task ci` as `check-condensed-paths`. It validates `dist/agent-src/rules/*.md`:
 
 - `load_context:` entries must resolve to existing files.
 - Forbidden substrings (`.agent-src.uncondensed/`, `../../docs/`,
@@ -346,7 +346,7 @@ If a regression is suspected, replay the smoke test against the
 package's own `.augment/` projection:
 
 ```bash
-task sync                              # regenerate .agent-src/ → .augment/
+task sync                              # regenerate dist/agent-src/ → .augment/
 python3 scripts/smoke_path_resolution.py
 ```
 

package/docs/archive/CHANGELOG-pre-2.17.0.md

@@ -56,7 +56,7 @@
 ### Chores
 
 * **template:** bump agent_config_version pin to 2.15.0 ([093367d](https://github.com/event4u-app/agent-config/commit/093367d3e417a11a28295f2efa574e8c3fef6524))
-* **sync:** propagate Step 8 agent_settings.py to .agent-src/ projection ([7ce92e5](https://github.com/event4u-app/agent-config/commit/7ce92e514a8edbd970a4118b91d2f651bf730070))
+* **sync:** propagate Step 8 agent_settings.py to dist/agent-src/ projection ([7ce92e5](https://github.com/event4u-app/agent-config/commit/7ce92e514a8edbd970a4118b91d2f651bf730070))
 * **roadmap:** archive Step 8 discovery polish ([1c21982](https://github.com/event4u-app/agent-config/commit/1c219825dc413cfe45aefc3b12c08d2720583880))
 * **changelog:** split era 2.11.x → pre-2.15.0 ([c79363c](https://github.com/event4u-app/agent-config/commit/c79363c05d775ecfa95ab6fff5b3bbe706f797c9))
 

package/docs/archive/CHANGELOG-pre-2.2.0.md

@@ -685,7 +685,7 @@ Tests: 2471
 ### Chores
 
 * **generate-tools:** refresh .windsurfrules after roadmap-progress-sync body expansion ([3fdba11](https://github.com/event4u-app/agent-config/commit/3fdba11cd4e91425a05ef9ad82b0e7c611180668))
-* **condense:** sync .agent-src/ with hardened roadmap-progress-sync rule ([30e7d1a](https://github.com/event4u-app/agent-config/commit/30e7d1ab455da823afbe7602f01d543d3fe91c5d))
+* **condense:** sync dist/agent-src/ with hardened roadmap-progress-sync rule ([30e7d1a](https://github.com/event4u-app/agent-config/commit/30e7d1ab455da823afbe7602f01d543d3fe91c5d))
 * **roadmap:** archive markitdown-adoption + refresh progress dashboard ([5481d90](https://github.com/event4u-app/agent-config/commit/5481d9025f4c85f33e11533099cf725eeb306455))
 * add skills-provenance registry for upstream attribution ([65c2eeb](https://github.com/event4u-app/agent-config/commit/65c2eeb3d1c9d0f86957757ce22221ed0e255292))
 * **roadmap:** harden process-full to ignore horizon markers ([36d0fa6](https://github.com/event4u-app/agent-config/commit/36d0fa6c263721618999b7fa27ddb9cb336dd6c2))
@@ -1115,7 +1115,7 @@ Tests: 2471
 * **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 condensed outputs + tool projections for Phase 1 clusters ([99466c0](https://github.com/event4u-app/agent-config/commit/99466c0a77116c7ed70db38fd957d061ad18e307))
-* **sync:** condense contexts/judges/persona-voice-rubric.md into .agent-src/ ([4060d01](https://github.com/event4u-app/agent-config/commit/4060d01af0680c2a913295166b978b605b1453db))
+* **sync:** condense contexts/judges/persona-voice-rubric.md into dist/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))
@@ -1810,7 +1810,7 @@ Tests: 2471
 * add iron rule for skill independence ([b060730](https://github.com/event4u-app/agent-config/commit/b060730e98b15b6bc498ad68a111035fab72907f))
 * address Copilot PR review feedback ([11b4d20](https://github.com/event4u-app/agent-config/commit/11b4d2060084d1739bfc9e6550fc78c4a4a0bcb7))
 * address consumer-api PR [#1466](https://github.com/event4u-app/agent-config/issues/1466) bot feedback ([c5f8e18](https://github.com/event4u-app/agent-config/commit/c5f8e18a6c429e2f8f0224e1d9130233107ce65e))
-* **check-refs:** resolve .augment/X as alias for .agent-src/X ([ff3b094](https://github.com/event4u-app/agent-config/commit/ff3b09479a7fa266606467d862f8de9277ef1fc4))
+* **check-refs:** resolve .augment/X as alias for dist/agent-src/X ([ff3b094](https://github.com/event4u-app/agent-config/commit/ff3b09479a7fa266606467d862f8de9277ef1fc4))
 * **check-refs:** skip forward refs in unchecked TODO items ([1458a18](https://github.com/event4u-app/agent-config/commit/1458a181eb5bbe3189777b87bd9ad210b8cc00c5))
 * **check-refs:** validate paths inside memory YAML + exempt consumer dirs ([ec4e8aa](https://github.com/event4u-app/agent-config/commit/ec4e8aae2a0f8e7c489442441b8cfa7f9242be2f))
 * **ci:** add PR comment permissions, fix lint failure, sync condensation hashes ([dee8c47](https://github.com/event4u-app/agent-config/commit/dee8c47d080176d49c94d63d33be7ada025b0a64))
@@ -1928,16 +1928,16 @@ Tests: 2471
 ## [1.4.0] — 2026-04-18
 
 ### Added
-- **`.agent-src/` replaces `.augment/` as the canonical condensed directory
+- **`dist/agent-src/` replaces `.augment/` as the canonical condensed directory
   shipped in the package.** The new name is tool-agnostic. The installer on
   the consumer side still writes into `.augment/`, unchanged.
-- `.augment/` is now a **local projection** of `.agent-src/` for Augment Code
+- `.augment/` is now a **local projection** of `dist/agent-src/` for Augment Code
   (gitignored in this repo, rebuilt by `task sync`). Rules are copied (Augment
   Code cannot load symlinked rules); everything else is symlinked to save
   space.
 - `scripts/install.sh` and `scripts/install.py` now read from vendor's
-  `.agent-src/` with automatic fallback to `.augment/` for pre-2.0 packages.
-- `task project-augment` — rebuild the `.augment/` projection from `.agent-src/`.
+  `dist/agent-src/` with automatic fallback to `.augment/` for pre-2.0 packages.
+- `task project-augment` — rebuild the `.augment/` projection from `dist/agent-src/`.
 - MIT License file in the repository root (previously `license: proprietary` in
   `composer.json` with no `LICENSE` file).
 - Root-level package docs (`AGENTS.md`, `.github/copilot-instructions.md`) are

package/docs/archive/CHANGELOG-pre-2.20.0.md

@@ -146,7 +146,7 @@ Tests: 4476 (+17 since 2.17.0)
 
 * **scripts:** draft update-github-metadata.sh (step-12 P6 L113) ([2a2c5c2](https://github.com/event4u-app/agent-config/commit/2a2c5c20cadb4ba653a5660797b28add7dfc43a6))
 * **index:** regen index + catalog after description trimming ([f4915e4](https://github.com/event4u-app/agent-config/commit/f4915e47172a7b4482a5440f17d543072c90c303))
-* **condensation:** propagate trimmed descriptions to .agent-src + hashes ([0a9352d](https://github.com/event4u-app/agent-config/commit/0a9352d7d20856301746a5839d25e2d52398920b))
+* **condensation:** propagate trimmed descriptions to dist/agent-src + hashes ([0a9352d](https://github.com/event4u-app/agent-config/commit/0a9352d7d20856301746a5839d25e2d52398920b))
 * **ownership:** regen file-ownership matrix ([bc13dd2](https://github.com/event4u-app/agent-config/commit/bc13dd2fe67d5c571f05964b84702cb6d7b193c2))
 * **index:** regen agents/index.md + docs/catalog.md ([20fefb0](https://github.com/event4u-app/agent-config/commit/20fefb043a25034a715cb7e76ec6174831357061))
 * **roadmaps:** step-12 phases 3 / 5 / 6 done + regen dashboard ([f07a0b1](https://github.com/event4u-app/agent-config/commit/f07a0b15cbe784eb17b9b75d06cae91e726b08f8))

package/docs/archive/CHANGELOG-pre-2.25.0.md

@@ -114,7 +114,7 @@ Tests: 4559 (+0 since 2.21.0)
 * **refs:** inline roadmap council citations + mark contract council-refs as ADR trace ([5a11951](https://github.com/event4u-app/agent-config/commit/5a11951ebff87ba95465c0a6b9b59fd9a4d4cee2))
 * **contracts:** drop roadmap reference from condensation-default-kill-criterion ([f2b2124](https://github.com/event4u-app/agent-config/commit/f2b212495744dae1904b256aa11d47e230e7b534))
 * **contracts:** add stability frontmatter to telegraph-telemetry + cost-summary-schema ([c7efa54](https://github.com/event4u-app/agent-config/commit/c7efa54cc3587f42f3a21ca18b783b5504c56e04))
-* **portability:** apply task-invocation fix in .agent-src/ projection ([be87c2b](https://github.com/event4u-app/agent-config/commit/be87c2be1637570a61b7a8863216288f3828609c))
+* **portability:** apply task-invocation fix in dist/agent-src/ projection ([be87c2b](https://github.com/event4u-app/agent-config/commit/be87c2be1637570a61b7a8863216288f3828609c))
 * **portability:** swap task invocations for script paths in condense-memory skill ([886f9f4](https://github.com/event4u-app/agent-config/commit/886f9f4a615fa2351b9261a62fd49173f8e87c2f))
 * **roadmap:** clarify agent-status is a command not a skill in step-16 ([96df39d](https://github.com/event4u-app/agent-config/commit/96df39de7a7562df946c37fea8bc42927851071f))
 * **template:** bump agent_config_version pin to 2.20.1 ([c275864](https://github.com/event4u-app/agent-config/commit/c2758641718077baaaaefea1191760d397f6b47e))

package/docs/archive/CHANGELOG-pre-2.7.0.md

@@ -48,7 +48,7 @@ Tests: 3530 (+9 since 2.4.1)
 ### Bug Fixes
 
 * **install:** write lockfile to canonical event4u namespace ([ca57607](https://github.com/event4u-app/agent-config/commit/ca5760785f150903bcad74e278b59e534f83634d))
-* **install:** source global deploy from .agent-src/ subdirectories ([f151caf](https://github.com/event4u-app/agent-config/commit/f151caf854d9ce8519bc244d441a7c8bf73e7fde))
+* **install:** source global deploy from dist/agent-src/ subdirectories ([f151caf](https://github.com/event4u-app/agent-config/commit/f151caf854d9ce8519bc244d441a7c8bf73e7fde))
 
 Tests: 3521 (+0 since 2.4.0)
 

package/docs/archive/CHANGELOG-pre-3.0.0.md

@@ -120,7 +120,7 @@ Tests: 4645
 ### Chores
 
 * add claude rules ([744328d](https://github.com/event4u-app/agent-config/commit/744328d57b4ba3c502ab3b41ded10e25ba3db8cf))
-* condense 4 .md files into .agent-src/ ([96ef2f9](https://github.com/event4u-app/agent-config/commit/96ef2f94504661f71b86a3fb16762069c39caaa7))
+* condense 4 .md files into dist/agent-src/ ([96ef2f9](https://github.com/event4u-app/agent-config/commit/96ef2f94504661f71b86a3fb16762069c39caaa7))
 * regenerate compiled trees for new rule (82 to 83) ([8b8af6a](https://github.com/event4u-app/agent-config/commit/8b8af6a4a918e927dbaafaeadc4402e3a7220981))
 
 ### Other

package/docs/archive/CHANGELOG-pre-3.1.0.md

@@ -77,7 +77,7 @@
 ### Bug Fixes
 
 * **ci:** sync condensed outputs (fetch description, failure-modes heading, agent-settings code block) ([6bb9b36](https://github.com/event4u-app/agent-config/commit/6bb9b363a46310ffe32d1859ed356eaf0cbd6b18))
-* **ci:** propagate path refactor into .agent-src/, trim ghostwriter description ([2747288](https://github.com/event4u-app/agent-config/commit/2747288b62ee4135d5f5459d2864f3a8fe0ce97a))
+* **ci:** propagate path refactor into dist/agent-src/, trim ghostwriter description ([2747288](https://github.com/event4u-app/agent-config/commit/2747288b62ee4135d5f5459d2864f3a8fe0ce97a))
 * **ui:** surface field errors on wizard step nav and toggle/radio inputs ([3abd156](https://github.com/event4u-app/agent-config/commit/3abd1560691397a4bfbf85f1279b6f9146513418))
 * **roadmaps:** update wizard-install-py-wiring parent link to archive path ([a40ae6e](https://github.com/event4u-app/agent-config/commit/a40ae6e2da01e2b96120af3fe87f2a787dc9b076))
 * **ui:** close diff modal and focus first errored field on save failure ([dd5bc72](https://github.com/event4u-app/agent-config/commit/dd5bc7236e26757dc4f809f49ee8f600710baebf))

package/docs/archive/CHANGELOG-pre-3.2.0.md

@@ -252,7 +252,7 @@ Tests: 4839 (+0 since 3.1.0)
 * **roadmap:** archive implementation-sequence.md (phases 1-6 complete) ([46ad4b1](https://github.com/event4u-app/agent-config/commit/46ad4b18a4fc7a855bb87aff6a71c03d266be6af))
 * **roadmap:** sync Phase 6 checkboxes + regen dashboard (30/35 done) ([69bc787](https://github.com/event4u-app/agent-config/commit/69bc787d516f7b45fc247c3b29f80f283946301e))
 * **roadmap:** mark monorepo-phase-5 complete ([41a68e9](https://github.com/event4u-app/agent-config/commit/41a68e9bb88ad052257bf53048c678e4dc88ec02))
-* **sync:** regenerate .agent-src/ orchestration.py template ([84d21c4](https://github.com/event4u-app/agent-config/commit/84d21c49d15036db5639557a38c649289d3bb6a6))
+* **sync:** regenerate dist/agent-src/ orchestration.py template ([84d21c4](https://github.com/event4u-app/agent-config/commit/84d21c49d15036db5639557a38c649289d3bb6a6))
 * **contracts:** regenerate mcp-tool-inventory.md line refs ([6726203](https://github.com/event4u-app/agent-config/commit/67262039c82003c7a03f5ba6b3d9d1eafa070d7b))
 * **migration:** physical move of ~700 artefacts to packages/ layout ([9f62fd2](https://github.com/event4u-app/agent-config/commit/9f62fd2e9ca8fd3b0126a35a7a040ce366bfd710))
 * **claude:** commit projected install-via-agent skill ([84676d4](https://github.com/event4u-app/agent-config/commit/84676d4726e342a6087a11b2665eb252bafd222c))

package/docs/archive/CHANGELOG-pre-4.5.0.md

@@ -221,7 +221,7 @@ Tests: 5052 (+9 since 4.1.0)
 * **portability:** rephrase `task sync` → "sync pipeline" in cheap-question-mechanics ([5341087](https://github.com/event4u-app/agent-config/commit/534108756e13a8ddec4bb27d6a3e9ebd7a677aec))
 * **ci:** clear v4 install-cutover blockers on PR #244 ([a031da4](https://github.com/event4u-app/agent-config/commit/a031da428c1427ea8080d56cc11c2e3db7efa356))
 * **authority:** block execution offers after roadmap/vision artifact save ([d30d441](https://github.com/event4u-app/agent-config/commit/d30d441e27c0820df82102e7afa4a12e4cb45cac))
-* **installer:** accept monorepo packs/<pack>/.agent-src.uncompressed/ prefix ([ac0b716](https://github.com/event4u-app/agent-config/commit/ac0b71651512b39c1f207204b1e3b02d33440031))
+* **installer:** accept monorepo packs/<pack>/dist/agent-src.uncompressed/ prefix ([ac0b716](https://github.com/event4u-app/agent-config/commit/ac0b71651512b39c1f207204b1e3b02d33440031))
 * **ci:** AGENTS.md size cap + scope_guard bash 5 set -e compatibility ([6018308](https://github.com/event4u-app/agent-config/commit/6018308ec622e29eaab42c35d43b462569a192db))
 * **tests:** mirror agent_settings.py into work_engine template copy ([a755bb7](https://github.com/event4u-app/agent-config/commit/a755bb7cc2a0cc8b3f4dcbf2c24ba37ef8738472))
 * **adr:** allow council refs in ADR decision-trace blocks ([f069596](https://github.com/event4u-app/agent-config/commit/f069596537c8ebd4ad6f2d828357d29e3a835739))

package/docs/archive/CHANGELOG-pre-5.4.0.md

@@ -39,7 +39,7 @@
 
 ### Chores
 
-* **frontmatter:** drop defaulted fields from the condensed .agent-src tree ([58e2c2a](https://github.com/event4u-app/agent-config/commit/58e2c2a6fc7cf7011e6c9b00801c9f8ff1412684))
+* **frontmatter:** drop defaulted fields from the condensed dist/agent-src tree ([58e2c2a](https://github.com/event4u-app/agent-config/commit/58e2c2a6fc7cf7011e6c9b00801c9f8ff1412684))
 * **roadmaps:** archive road-to-distribution-identity — CI green on PR #290 ([2ffeb62](https://github.com/event4u-app/agent-config/commit/2ffeb6239697228541334c7e234554f77c6935aa))
 * **roadmaps:** flip Phase 0 checkboxes + regen dashboard ([070e33e](https://github.com/event4u-app/agent-config/commit/070e33e4fd704ec0257f4c5cf6a72052c97796d3))
 

package/docs/archive/CHANGELOG-pre-5.9.0.md

@@ -172,7 +172,7 @@ Tests: 5375 (+0 since 5.6.0)
 * **schema:** rule description cap 160 -> 190 (smoke gate treats over-cap as FAIL) ([72f05e0](https://github.com/event4u-app/agent-config/commit/72f05e02cca4e196e514d8f4f573ac9890f52583))
 * **kernel:** repoint iron_law_sha to packages/core layout (Iron-Law SHA gate was broken) ([aab5755](https://github.com/event4u-app/agent-config/commit/aab57558f7047fc21d0107dbab5aa3b49ebe4e2f))
 * **schema:** add lean_projection.mode to the settings schema (template-parity gate) ([51ed03e](https://github.com/event4u-app/agent-config/commit/51ed03ec9e74d4573b7da43a6b45804535986690))
-* **bench:** repoint bench_runner SKILLS_DIR to .agent-src for packages/core layout ([e183527](https://github.com/event4u-app/agent-config/commit/e183527c0efa4e3fe7dfb6a9df2c1e21534925a8))
+* **bench:** repoint bench_runner SKILLS_DIR to dist/agent-src for packages/core layout ([e183527](https://github.com/event4u-app/agent-config/commit/e183527c0efa4e3fe7dfb6a9df2c1e21534925a8))
 
 ### Performance
 

package/docs/artefact-census.md

@@ -0,0 +1,71 @@
+# Artefact census
+
+A point-in-time count of the package's artefacts per type, with a stated,
+reproducible methodology. This is the **baseline the Phase-3 consolidation
+discovery scan reports against** (positioning roadmap), and it resolves the
+prior "≈530 vs ≈560" total-artefact ambiguity by being explicit about *what is
+counted and how*.
+
+> **Measured:** 2026-06-09 against `main`. Counts drift as artefacts land — to
+> refresh, re-run the commands in **Methodology** and update the table. No
+> version is pinned; this is a measurement, not a release target.
+
+## Counts
+
+| Type | Count | Counted from (source of truth) |
+|---|---:|---|
+| Skills | 227 | `src/skills/*/SKILL.md` |
+| Rules | 79 | `src/rules/*.md` |
+| Commands | 150 | `src/domains/**/command.md` |
+| Guidelines | 75 | `docs/guidelines/**/*.md` |
+| Personas (core) | 25 | `src/agent-src/personas/*.md` |
+| Personas (advisors) | 5 | `src/agent-src/personas/advisors/*.md` |
+| Contexts | 35 | `src/agent-src/contexts/**/*.md` |
+
+## Totals — explicit groupings (resolving the ambiguity)
+
+The total depends on which artefact classes you include. State the grouping, not
+a bare number:
+
+- **Catalog four** (skills + rules + commands + guidelines) = **531**.
+  This is the set surfaced in [`catalog.md`](catalog.md) as the public capability
+  surface.
+- **+ personas (core + advisors, 30)** = **561**.
+- **+ contexts (35)** = **596** (contexts are reviewer/lookup material, not a
+  user-invoked surface — usually excluded from "capability" totals).
+
+The "≈530" figure was the catalog four; "≈560" added personas. Both were
+correct for their grouping; the ambiguity was an unstated scope.
+
+## Methodology
+
+All counts come from the **source of truth** (`src/`, and `docs/guidelines/` for
+guidelines), never from a generated projection (`dist/agent-src/`, `.augment/`,
+`.claude/`). Reproduce:
+
+```bash
+ls -d src/skills/*/SKILL.md            | wc -l   # skills
+ls    src/rules/*.md                   | wc -l   # rules
+find  src/domains -name command.md     | wc -l   # commands
+find  docs/guidelines -name '*.md'     | wc -l   # guidelines
+ls    src/agent-src/personas/*.md      | wc -l   # personas (core)
+ls    src/agent-src/personas/advisors/*.md | wc -l   # advisors
+find  src/agent-src/contexts -name '*.md'  | wc -l   # contexts
+```
+
+Notes:
+
+- **Commands** all live under `src/domains/<pack>/.../command.md` (the
+  `src/agent-src/commands/` legacy location is empty).
+- **Skills vs commands as "Claude skills":** Claude Code surfaces both skills and
+  commands as `.claude/skills/` entries (≈377), which is why a tool-side count
+  differs from the per-type source count. The census counts by **artefact type at
+  source**, which is the stable denominator for the Phase-3 scan.
+- **Public subset:** [`catalog.md`](catalog.md) publishes the catalog four minus
+  artefacts marked non-public in frontmatter; it is the consumer-facing list, not
+  the full source census above.
+
+## See also
+
+- [`catalog.md`](catalog.md) — the public capability surface (regenerated by `task generate-index`).
+- Positioning roadmap Phase 3 — the consolidation discovery scan that reports against this baseline.

package/docs/case-studies/frontend-design-vs-ui-ux-pro-max.md

@@ -0,0 +1,86 @@
+# Competitive positioning — `frontend-design` pack vs. `ui-ux-pro-max`
+
+> Ours-vs-theirs verdict per the `competitive-positioning` skill,
+> closing `road-to-frontend-design-intelligence` Phase 8. Evidence:
+> full-tree deep-dive of `nextlevelbuilder/ui-ux-pro-max-skill`
+> @ `b7e3af80f6e331f6fb456667b82b12cade7c9d35` (2026-06-07) vs. this
+> repo post-adoption (ADR-061).
+
+## 1. Frame
+
+- **Theirs:** "Make any AI agent produce professional UI" — a
+  searchable design-knowledge corpus + BM25 engine + generative asset
+  add-ons, installed per-tool via an npm CLI. Segment: any developer
+  using an AI coding tool.
+- **Ours:** a governed skill/rule/command suite where frontend design is
+  one orchestrated capability among many — audit → design → apply →
+  review → polish with hard gates, now **grounded in the same corpus**.
+  Segment: teams standardizing AI-agent behavior across tools.
+
+## 2. Axes
+
+- **Design-knowledge grounding** — the differentiated capability that
+  triggered this adoption.
+- **Orchestration & gates** — who controls when knowledge is applied.
+- **Accessibility depth** — audit method, not just data.
+- **Stack coverage** — per-framework Do/Don't knowledge.
+- **Token authoring** — DTCG system + generators.
+- **Generative assets** — logo/CIP/banner generation.
+- **Governance & provenance** — licensing, refresh, safety surfaces.
+
+## 3. Verdict table
+
+| Axis | Ours (post-adoption) | Theirs | Verdict | Adopt? | Rationale |
+|---|---|---|---|---|---|
+| Design-knowledge grounding | Same corpus (11 CSVs + 16 stack CSVs + reasoning map) behind a **generalized manifest engine** with confidence + evidence-gap on every output | Origin of the corpus; frontend-hardcoded scripts | **Parity-plus** | done | ADR-061 adoption; our engine adds structured filters, named retrievers, schema-agnostic manifests |
+| Orchestration & gates | Directive set with audit gate, microcopy placeholder lock, a11y severity gate, polish ceiling | Skill prose + conventions; no enforced gates | **Ours** | — | Their corpus now feeds our gates — the combination argument inverts |
+| Accessibility depth | `accessibility-auditor` (WCAG 2.2 AA method) + corpus a11y data (contrast-adjusted palettes, chart grades, 44pt rules) | Checklist rows + a11y-graded data, no audit method | **Ours** | done | Their data enriched our gate; method stays ours |
+| Stack coverage | 16 stack corpora via `--stack` (Vue gap closed) + stack-dispatched executor skills | Same 16 CSVs | **Parity** | done | Verbatim adoption, one search mechanism |
+| Token authoring | `design-tokens` skill — DTCG 3-layer + Python generate/validate/embed (no Node dep) | `.cjs` generators (Node required) | **Ours (slight)** | done | Port removes the Node runtime requirement; brand→token sync deferred (watch note) |
+| Generative assets | **Not shipped** — gated by `domain-adoption-policy` (watch note); would adapt into `pack-ai-video` | Gemini logo/CIP/icon/banner/social suite | **Theirs** | gated | Heavy deps (`google-genai`, Chrome, API key) + no demand signal; revisit on trigger |
+| Governance & provenance | ADR-061, ATTRIBUTION with SHA pins, owner + cadence per corpus, runtime-safety review, Apache §4b markings | MIT/Apache files present; no refresh discipline documented | **Ours** | — | The axis their 86k-star repo does not compete on |
+
+## 4. Invariants (moats)
+
+- **Orchestration & gates** — inversion: "would a consumer drop our suite
+  for theirs?" Only if they wanted raw knowledge without enforcement;
+  the placeholder lock, audit gate, and a11y floor do not exist upstream.
+- **Governance & provenance** — refresh cadence + SHA pins + safety
+  reviews are structural in this package; a knowledge dump cannot match
+  them without becoming a governed suite itself.
+
+## 5. Adoption queue
+
+Empty — every `adopt? = done` row landed in
+`road-to-frontend-design-intelligence` Phases 1–6. The single open
+upstream capability (generative suite) is gated, not queued
+(`agents/settings/contexts/domain-watch/generative-brand-assets.md`).
+
+## 6. Unknowns
+
+- Their npm CLI's 18-tool projection breadth vs. our generator's
+  supported set: we verified parity for **our** targets
+  (`.claude` / `.cursor` / `.clinerules` / `.windsurf` / `.augment` via
+  `task generate-tools`); no claim about the 13 other tools they list —
+  we do not target them.
+- Real-session quality delta of grounded vs. ungrounded briefs — the
+  council's change-my-mind anchor (≥10 real sessions) applies to our own
+  Phase 9 expansion, and equally to claiming superiority here.
+
+## Net
+
+A consumer installing **our package alone** now gets the
+`ui-ux-pro-max` design knowledge **plus** orchestration, hard gates,
+a11y method, token authoring without Node, and provenance discipline.
+The combination is unnecessary; the gated generative suite is the one
+deliberate exception.
+
+## Upstream-contribute consideration (Step 8.3)
+
+Improvements worth proposing back (MIT obligations honored either way):
+the BM25 dedupe (`core.py` / `slide_search_core.py` byte-identical),
+the Python token toolchain (drops their Node dependency), and the
+manifest/filters layer. **Decision: defer the upstream PR** until the
+engine has soaked through one internal release cycle — proposing an
+interface we might still move is noise for the maintainer. Revisit at
+the first quarterly corpus refresh.