@event4u/agent-config 8.4.0 → 8.5.0

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Bootstrap shim for the event4u agent-config suite. This plugin ships ONLY the dispatcher hooks plus one install-pointer skill — ALL content (skills, rules, commands) is installed via `npx -y @event4u/agent-config init`, which writes the file projection AND registers the same hooks in ~/.claude/settings.json. DEPRECATED as a content channel; kept so the marketplace listing stays discoverable and existing installs keep working hooks.",
-    "version": "8.4.0",
+    "version": "8.5.0",
     "keywords": [
       "agent-config",
       "skills",

package/CHANGELOG.md

@@ -989,6 +989,79 @@ our recommendation order, not its support status.
 > that forces a new era split (`# Era: 8.2.x`, etc.) — see
 > [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
 
+## [8.5.0](https://github.com/event4u-app/agent-config/compare/8.4.1...8.5.0) (2026-07-08)
+
+### Features
+
+* **counts:** single-source every public artefact count + drift gate ([34204ed](https://github.com/event4u-app/agent-config/commit/34204ed9b1048704cf3ebb917e2abc7f952ee62a))
+* **doctor:** settings-review-pending check ([f2e5198](https://github.com/event4u-app/agent-config/commit/f2e51984cc32a44792660e1ef0ad5c66ed2b859f))
+* **ui:** upgrade settings-review page + pending banner ([6272721](https://github.com/event4u-app/agent-config/commit/6272721f34f0a1f01d6ef3bccd08f468448ea8f0))
+* **server:** pending settings-changes routes + API contract ([bddd2c5](https://github.com/event4u-app/agent-config/commit/bddd2c5a01c8ff04a69a786de8e3f076e9788217))
+* **install:** snapshot the settings surface + write the upgrade delta ([21b2ddd](https://github.com/event4u-app/agent-config/commit/21b2ddd2e05eecc9996d43ab0a380c7ec45ec105))
+* **settings:** shared settings-surface flatten/delta/classify engine ([c73adb8](https://github.com/event4u-app/agent-config/commit/c73adb859eb25562e382c735fea696d10f6657c3))
+* **lint:** validate routes_to + bare-invocation story; repoint atomic-command linter ([8f5a5eb](https://github.com/event4u-app/agent-config/commit/8f5a5eb56b71c2451e510948dbbdc5d1d5d2737f))
+* **server:** prefill local/dry-run tests from the real user-global config ([08c3a01](https://github.com/event4u-app/agent-config/commit/08c3a01a9c022709953cf4fb68e5e1a45792687e))
+* **ui:** prune nav to real surfaces; gate Project and Workspace tabs ([4b437b9](https://github.com/event4u-app/agent-config/commit/4b437b95afbaee3765c87d93defc1065d779dcfe))
+* **wizard:** remember roles and pack selection across runs ([befb5aa](https://github.com/event4u-app/agent-config/commit/befb5aaf14ea7b5b76db2600e9554375f5204340))
+* **settings:** standalone hub with simple/advanced tiers, search, modified badges ([6138089](https://github.com/event4u-app/agent-config/commit/613808968a63dd5ceeda26245e2d055fdd0fd86c))
+* **ui:** dark-first visual system v2 with theme toggle ([6204194](https://github.com/event4u-app/agent-config/commit/6204194b4c8777260fd68bc4087500af2be44b4a))
+* **wizard:** consolidate flow, add start screen, review summary, finish checklist ([d58d4a4](https://github.com/event4u-app/agent-config/commit/d58d4a4f0a063bc051573d7df95bd35344432b66))
+* **wizard:** prefill installed packs and flag removals ([8cad9d3](https://github.com/event4u-app/agent-config/commit/8cad9d367ce27c4393486349ed2d1428dd2834b9))
+* **cli:** add config command and init --project routing ([7a4f26a](https://github.com/event4u-app/agent-config/commit/7a4f26ad6deada4567a8fc7f04df0bc3d460760b))
+
+### Bug Fixes
+
+* **release:** guard the Tests: footer counter against vitest recursion ([6538636](https://github.com/event4u-app/agent-config/commit/653863666e7376280046a9570a2f9c65e6ee2f12))
+* **converge:** surface the live-session remedy after a plugin-cache reap ([0c84dbc](https://github.com/event4u-app/agent-config/commit/0c84dbc9923916a00f4fd4738c2089997614fe82))
+* **ci:** replaces arrays, legacy-path literal, cookbook test fixture ([a300ba0](https://github.com/event4u-app/agent-config/commit/a300ba03a4a17424ac5b24bf7713e7311c47a051))
+* **pack:** ship src/shared + src/server/schemas with the tarball ([39f6b66](https://github.com/event4u-app/agent-config/commit/39f6b668f14f26d8dc9e768bb8b400aa35e36039))
+* **cli:** list config in the Bash help output ([72f168e](https://github.com/event4u-app/agent-config/commit/72f168ec370671a0116ed7ff1ce76e4488b52390))
+* **install:** work around Claude Code flat user-command discovery regression ([af00db9](https://github.com/event4u-app/agent-config/commit/af00db98e7bf26a47a525f59a272647f5342a7e4))
+* **cli:** list every dispatched command in help output ([3e366d6](https://github.com/event4u-app/agent-config/commit/3e366d63dcced166ecfe54a184baf38def2c504c))
+* **wizard:** review chip overflow + dry-run apply hard floor; add browser E2E ([d5b0977](https://github.com/event4u-app/agent-config/commit/d5b09775cf1276d22624236cf49818f6d77afb04))
+
+### Documentation
+
+* update cross-references to nested command paths ([6ca8b56](https://github.com/event4u-app/agent-config/commit/6ca8b564f44c3631d5b4d29272679e4e65eb8c95))
+* **contracts:** register Phase-4 command clusters + bare-invocation rule (ADR-114) ([9e9f3c2](https://github.com/event4u-app/agent-config/commit/9e9f3c2fc437bce9066b0f4e3259c358ee80ada4))
+* document config command, init --project, wizard flow and settings hub ([d4a5df1](https://github.com/event4u-app/agent-config/commit/d4a5df1c050831f29d655775a2ad8a38b037f4bb))
+
+### Refactoring
+
+* **scripts:** retire py2ts parity rationale from all src/scripts comments ([4ec6f07](https://github.com/event4u-app/agent-config/commit/4ec6f07c5e36240c572426ff8e17ae857efc2ba4))
+* **commands:** nest 19 flat commands into Phase-4 clusters ([fa918c2](https://github.com/event4u-app/agent-config/commit/fa918c23d99f1b1100210be6757906bbcc68153f))
+
+### Tests
+
+* **budget:** align fixtures with the re-anchored mcp_schemas cap ([fa3c93f](https://github.com/event4u-app/agent-config/commit/fa3c93f637e751dc31bd6cc2b3b71a740fca33f1))
+
+### Chores
+
+* **counts:** re-sync prose counts after the main merge (172 commands) ([1042fad](https://github.com/event4u-app/agent-config/commit/1042fad691a0c2c3aa01079ef21654e816565863))
+* **hygiene:** fix stale references, triage claims debt, revive Tests: footer ([2379d4b](https://github.com/event4u-app/agent-config/commit/2379d4bf1821c0cbcb11d1ca919677a65bce86bf))
+* **roadmaps:** land the inbox-consolidation roadmap set (council 2026-07-08) ([f25b3bb](https://github.com/event4u-app/agent-config/commit/f25b3bb4a6fa68444e79e0cca80b2c3813bd3484))
+* regenerate dist, projections, catalogs, and pack manifests ([fa45778](https://github.com/event4u-app/agent-config/commit/fa45778ada09381701222a12be064932bb572c7d))
+* **bench:** re-anchor kernel-prefix snapshot after main's commit-policy edit ([98ee05a](https://github.com/event4u-app/agent-config/commit/98ee05a18736d016361d7dab88373b819ff1922e))
+* **bench:** refresh token baseline after run_tests exec pilot ([140697e](https://github.com/event4u-app/agent-config/commit/140697e177672805319fe2425c7e641d266c0843))
+* **budget:** re-anchor mcp_schemas.gpt cap after run_tests exec pilot ([0b49bd4](https://github.com/event4u-app/agent-config/commit/0b49bd4bd389ead796a59eb61c29b5fcc584d520))
+* **kernel:** ADR-114 — commit-policy Iron-Law override ([edabc87](https://github.com/event4u-app/agent-config/commit/edabc8753c218ed1661ccd664a7ce513b7f0b34b))
+* **matrix:** regenerate file-ownership matrix (new files from branch + main merge) ([8a88564](https://github.com/event4u-app/agent-config/commit/8a88564c7f01d2bfe5e35287e55ad0b1fca655f8))
+* **roadmap:** allow-pragma for historical council output path ([67076a4](https://github.com/event4u-app/agent-config/commit/67076a46c3228752bea11a050fb193e695e5b04c))
+* **docs:** add required stability frontmatter to surface-matrix contract ([e16a998](https://github.com/event4u-app/agent-config/commit/e16a998b499a8cdcdfc1a5f2f20d66c5031fe5b5))
+* **tiers:** register mcp_exec cluster (lab) in surface-tiers.yml ([55c3eda](https://github.com/event4u-app/agent-config/commit/55c3eda9c3fd148bae3b620c7214cfaa69ec9eb3))
+* **lint:** re-bump leakage allowlist lines after main's content sweep ([c2843ae](https://github.com/event4u-app/agent-config/commit/c2843ae9943305915ddf57ddad971f4e5aaf7799))
+* **index:** regenerate agents/index.md + docs/catalog.md after main merge ([2b85d9c](https://github.com/event4u-app/agent-config/commit/2b85d9c9aeb53b84f1be5473c835dd54ba73bb16))
+* **build:** regenerate install bundle (flat-command wrappers + packs lockfile) ([9952ae1](https://github.com/event4u-app/agent-config/commit/9952ae1512a1b4a0c76151b26fdf5a12632e1344))
+* **roadmap:** add + archive road-to-setup-experience (all phases shipped) ([54f01e5](https://github.com/event4u-app/agent-config/commit/54f01e5ad8ae37e277103973f93abd38c46e476e))
+
+Tests: 6936
+
+## [8.4.1](https://github.com/event4u-app/agent-config/compare/8.4.0...8.4.1) (2026-07-08)
+
+### Bug Fixes
+
+* **package:** ship src/install + agent-src script trees; gate imports at prepack ([77d53bc](https://github.com/event4u-app/agent-config/commit/77d53bcb2e14da1cff308cd0a8dd5d11d8783d5b))
+
 ## [8.4.0](https://github.com/event4u-app/agent-config/compare/8.3.0...8.4.0) (2026-07-08)
 
 ### Features

package/README.md

@@ -4,19 +4,19 @@
 
 [![Smoke](https://github.com/event4u-app/agent-config/actions/workflows/smoke.yml/badge.svg)](https://github.com/event4u-app/agent-config/actions/workflows/smoke.yml) [![Public install smoke (3 OS × 2 Node)](https://github.com/event4u-app/agent-config/actions/workflows/smoke-public-install.yml/badge.svg)](https://github.com/event4u-app/agent-config/actions/workflows/smoke-public-install.yml) [![npm](https://img.shields.io/npm/v/@event4u/agent-config?style=flat-square&label=npm&color=orange)](https://www.npmjs.com/package/@event4u/agent-config) [![agent-config MCP server](https://glama.ai/mcp/servers/event4u-app/agent-config/badges/score.svg)](https://glama.ai/mcp/servers/event4u-app/agent-config)
 
-[![Skills](https://img.shields.io/badge/Skills-264-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-95-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-166-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-87-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-29-orange?style=flat-square)](dist/agent-src/personas/) [![Advisors](https://img.shields.io/badge/Advisors-5-orange?style=flat-square)](dist/agent-src/personas/advisors/)
+[![Skills](https://img.shields.io/badge/Skills-264-orange?style=flat-square)](dist/agent-src/skills/) [![Rules](https://img.shields.io/badge/Rules-95-orange?style=flat-square)](dist/agent-src/rules/) [![Commands](https://img.shields.io/badge/Commands-172-orange?style=flat-square)](dist/agent-src/commands/) [![Guidelines](https://img.shields.io/badge/Guidelines-87-orange?style=flat-square)](docs/guidelines/) [![Personas](https://img.shields.io/badge/Personas-29-orange?style=flat-square)](dist/agent-src/personas/) [![Advisors](https://img.shields.io/badge/Advisors-5-orange?style=flat-square)](dist/agent-src/personas/advisors/)
 
 > **Choose your experience — developer · founder · content · agency · finance · ops. Add packs. Get a focused command set, not a 500-artefact dump.** Bring your own AI provider.
 
 **Every public claim in this README is machine-checked — [verify it yourself](docs/proof.md).** In a market that runs on unbacked headline numbers, this one binds each claim to resolvable evidence or fails its own build.
 
-**258 skills, 162 commands, 93 governed rules** — plus a capability router that loads the right skill on intent, and multi-agent orchestration with consensus review. The whole layer is compiled into 7+ host agents (Claude Code, Cursor, Augment, Cline, Windsurf, Copilot, Gemini) with **zero runtime daemon**.<!-- claim:no-runtime-daemon --> Six role-shaped entry paths sit on top, so any host becomes a reliable team member — without locking you to a single model or vendor.
+**264 skills, 172 commands, 95 governed rules** — plus a capability router that loads the right skill on intent, and multi-agent orchestration with consensus review. The whole layer is compiled into 7+ host agents (Claude Code, Cursor, Augment, Cline, Windsurf, Copilot, Gemini) with **zero runtime daemon**.<!-- claim:no-runtime-daemon --> Six role-shaped entry paths sit on top, so any host becomes a reliable team member — without locking you to a single model or vendor.
 
 ### What's different
 
 It is both deep **and** disciplined — and honest about what it deliberately is not:
 
-- **Depth that routes itself** — 258 skills + 162 commands, with a capability router that loads the right one on intent, not a 500-artefact context dump.
+- **Depth that routes itself** — 264 skills + 172 commands, with a capability router that loads the right one on intent, not a 500-artefact context dump.
 - **Governance on every host** — rules compiled into each tool's native format at projection time; deterministic runtime hooks added on hook-capable hosts. This config-space, host-agnostic governance is the moat ([the governance advantage](docs/governance-advantage.md) · [enforcement by host](docs/enforcement-by-host.md)).
 - **Surgical uninstall** — removes only its own keys from a shared host config (matched by JSON-pointer + SHA-256), never a neighbour tool's entries.<!-- claim:surgical-uninstall -->
 - **Pack-scoped install** — writes the active pack only, not a 500-artefact dump.
@@ -65,7 +65,7 @@ what is *not* loaded · examples):
 
 ### Workflows, not raw commands
 
-You don't memorize 150 commands — you run a **work journey**. Four flows span the
+You don't memorize 172 commands — you run a **work journey**. Four flows span the
 developer story end-to-end; each names the command you TYPE to start and the
 skills it composes:
 
@@ -380,6 +380,18 @@ flags a missing-from-`PATH` binary or broken hook wiring. See
 [getting-started § Keeping current](docs/getting-started.md#keeping-current) ·
 [Troubleshooting](#troubleshooting).
 
+### The command surface at a glance
+
+| Command | What it does |
+|---|---|
+| `agent-config init` | One-shot install — opens the browser wizard (recommended path or step-by-step) |
+| `agent-config init --project` | Initialize a project: minimal `agents/` bridge + managed `.gitignore` block |
+| `agent-config config` | Open the configuration GUI — global settings hub (simple + advanced tiers, search, reset-to-default) |
+| `agent-config config --project` | Open the project configuration surface |
+| `agent-config setup` | Re-run the guided onboarding wizard (prefilled from your current state) |
+| `agent-config upgrade` | Update the global install to the latest release + additively sync settings |
+| `agent-config doctor` | Read-only health/drift report |
+
 ### Cloud / Hosted-agent surfaces
 
 For platforms where the package's scripts cannot run, artefacts are built for paste-in or upload:
@@ -447,7 +459,7 @@ When a prompt matches a command's purpose ("setze ticket ABC-123 um" → `/imple
 | [**Migration**](docs/MIGRATION.md) | Per-version upgrade steps |
 | [**Showcase**](docs/showcase.md) | More examples & expected behavior |
 
-Browse content: [all 166 commands](dist/agent-src/commands/) · [skills catalog](docs/skills-catalog.md) · [full catalog](docs/catalog.md) · [`llms.txt`](llms.txt).
+Browse content: [all 172 commands](dist/agent-src/commands/) · [skills catalog](docs/skills-catalog.md) · [full catalog](docs/catalog.md) · [`llms.txt`](llms.txt).
 
 ---
 

package/dist/agent-src/README.md

@@ -42,7 +42,7 @@ For full details see [augment-infrastructure.md](contexts/augment-infrastructure
 |---|---|
 | `/agent-handoff` | Generate context summary for a fresh chat |
 | `/fix-pr-comments` | Fix all open PR review comments |
-| `/quality-fix` | Run PHPStan + Rector and fix errors |
+| `/fix quality` | Run PHPStan + Rector and fix errors |
 | `/create-pr` | Create a GitHub PR with description |
 | `/bug-investigate` | Investigate a bug from Jira/Sentry |
 | `/tests-create` | Write tests for current changes |

package/dist/agent-src/commands/{analyze-reference-repo.md → analyze/reference-repo.md}

@@ -1,9 +1,11 @@
 ---
 model_tier: high
 name: analyze-reference-repo
-pack: engineering-base
+pack: analysis-workbench
 tier: 2
 visibility: internal
+sub: reference-repo
+cluster: analyze
 skills: [project-analyzer, learning-to-rule-or-skill]
 description: Analyze an external reference repository (competitor, inspiration, peer) and produce a structured comparison + adoption plan for this project.
 suggestion:

package/dist/agent-src/commands/analyze.md

@@ -4,11 +4,11 @@ name: analyze
 disable-model-invocation: true
 pack: analysis-workbench
 intent: "Analysis dispatcher — classify input by keywords, propose a weighted framework path, let the user pick"
-routes_to: [analyze-postmortem, analyze-premortem, analyze-decision, analyze-near-miss, analyze-incident]
+routes_to: [analyze-postmortem, analyze-premortem, analyze-decision, analyze-near-miss, analyze-incident, analyze-reference-repo]
 replaces: []
 tier: 1
 visibility: advanced
-description: Analysis orchestrator — confidence-weighted suggester that routes to postmortem, premortem, decision-review, near-miss, or incident frameworks.
+description: Analysis orchestrator — confidence-weighted suggester that routes to postmortem, premortem, decision-review, near-miss, incident, or reference-repo analysis.
 cluster: analyze
 type: orchestrator
 suggestion:
@@ -37,6 +37,7 @@ to the chosen sub-command. Never auto-selects silently.
 | `/analyze:decision` | `analyze/decision/command.md` | Audit a past architectural decision (did it hold?) |
 | `/analyze:near-miss` | `analyze/near-miss/command.md` | Post-mortem for a near-miss (same flow, lighter severity framing) |
 | `/analyze:incident` | `analyze/incident/command.md` | Full incident flow: commander → RCA → post-mortem → memory candidate |
+| `/analyze:reference-repo` | `analyze/reference-repo/command.md` | Deep-dive an external reference repo (competitor, inspiration, peer) → structured comparison + adoption plan |
 
 ## Dispatch
 
@@ -60,6 +61,7 @@ match:
 | "pre-mortem", "what could go wrong", "imagine failure", "vor dem Start" | `premortem` |
 | "decision review", "ADR", "did this hold up", "rückblick Architektur" | `decision` |
 | "production is down", "active incident", "Vorfall", "Prod ist down" | `incident` |
+| external repo URL / `owner/repo`, "how does X do this", "compare with that repo", "competitor" | `reference-repo` |
 
 Assign a confidence level (high / medium / low) per framework based on
 signal count. A framework with zero signals gets `low`.
@@ -77,7 +79,8 @@ escape:
 > 3. [low] Pre-mortem (`/analyze:premortem`) — imagined-failure analysis before committing
 > 4. [low] Decision review (`/analyze:decision`) — did a past architectural decision hold up?
 > 5. [low] Incident (`/analyze:incident`) — full live-incident coordination + RCA + post-mortem
-> 6. Describe in your own words — I'll re-classify
+> 6. [low] Reference repo (`/analyze:reference-repo`) — deep-dive an external repo → comparison + adoption plan
+> 7. Describe in your own words — I'll re-classify
 
 **Empfehlung:** 1
 
@@ -91,7 +94,7 @@ Ask one question (per `ask-when-uncertain`):
 > What happened or what are you trying to analyse?
 
 Re-run Step 2 with the answer. Present the menu again. Do not loop
-more than twice — on the third attempt, show all five options unranked
+more than twice — on the third attempt, show all six options unranked
 and let the user pick.
 
 ### 5. Unknown sub-command
@@ -112,11 +115,11 @@ and ask which one was intended. One question, no guessing.
 - **Memory loop applies** — every sub-command that produces an
   analysis output MUST draft a memory candidate via
   `/memory propose` per
-  [`docs/contracts/analysis-memory-loop.md`](../docs/contracts/analysis-memory-loop.md).
+  [`docs/contracts/analysis-memory-loop.md`](../../../docs/contracts/analysis-memory-loop.md).
 
 ## See also
 
-- [`docs/contracts/analysis-memory-loop.md`](../docs/contracts/analysis-memory-loop.md) — produce → propose → promote → retrieve contract
+- [`docs/contracts/analysis-memory-loop.md`](../../../docs/contracts/analysis-memory-loop.md) — produce → propose → promote → retrieve contract
 - [`blameless-post-mortem`](../../../skills/blameless-post-mortem/SKILL.md) — post-mortem + near-miss skill
 - [`root-cause-frameworks`](../../../skills/root-cause-frameworks/SKILL.md) — RCA engine
 - [`premortem`](../../../skills/premortem/SKILL.md) — forward-looking imagined-failure skill

package/dist/agent-src/commands/{bug-fix.md → bug/fix.md}

@@ -4,6 +4,8 @@ name: bug-fix
 pack: engineering-base
 tier: 2
 visibility: internal
+sub: fix
+cluster: bug
 skills: [bug-analyzer, pest-testing]
 description: Plan and implement a bug fix — based on investigation, with quality checks and test verification
 council_depth: deep
@@ -191,4 +193,4 @@ What next?
 
 ## See also
 
-- [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md#developer) — Developer mode output contract (Goal / Plan / Changes / Tests / Open questions)
+- [`role-contracts`](../../../docs/guidelines/agent-infra/role-contracts.md#developer) — Developer mode output contract (Goal / Plan / Changes / Tests / Open questions)

package/dist/agent-src/commands/{bug-investigate.md → bug/investigate.md}

@@ -4,6 +4,8 @@ name: bug-investigate
 pack: engineering-base
 tier: 2
 visibility: internal
+sub: investigate
+cluster: bug
 skills: [bug-analyzer, sentry-integration]
 description: Investigate a bug — auto-detect ticket from branch, gather Jira/Sentry/description context, trace root cause
 council_depth: deep
@@ -183,5 +185,5 @@ What's next?
 
 ## See also
 
-- [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md#incident) — Incident mode output contract (Symptom / Reproduction / Minimal reversible change / Deferred verification / Follow-up commitment) — use when the bug is a live production issue with `break-glass: true`
-- [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md#developer) — Developer mode output contract for non-incident bugs
+- [`role-contracts`](../../../docs/guidelines/agent-infra/role-contracts.md#incident) — Incident mode output contract (Symptom / Reproduction / Minimal reversible change / Deferred verification / Follow-up commitment) — use when the bug is a live production issue with `break-glass: true`
+- [`role-contracts`](../../../docs/guidelines/agent-infra/role-contracts.md#developer) — Developer mode output contract for non-incident bugs

package/dist/agent-src/commands/bug.md

@@ -0,0 +1,59 @@
+---
+model_tier: medium
+name: bug
+disable-model-invocation: true
+pack: engineering-base
+intent: "Bug dispatcher — investigate the root cause or implement the fix"
+routes_to: [bug-investigate, bug-fix]
+replaces: []
+tier: 2
+visibility: internal
+description: Bug orchestrator — routes to investigate (root cause) and fix (plan + implement)
+cluster: bug
+type: orchestrator
+suggestion:
+  eligible: true
+  trigger_description: "there is a bug, something is broken, investigate or fix this error"
+  trigger_context: "user reports a defect without saying whether they want root-cause analysis or the fix"
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+---
+
+# /bug
+
+Top-level orchestrator for the `/bug` family — triage entry point when the
+user knows they have a defect but has not picked a workflow yet.
+
+## Sub-commands
+
+| Sub-command | Routes to | Purpose |
+|---|---|---|
+| `/bug investigate` | `commands/bug/investigate.md` | Investigate a bug — auto-detect ticket from branch, gather Jira/Sentry context, trace root cause |
+| `/bug fix` | `commands/bug/fix.md` | Plan and implement a bug fix — based on investigation, with quality checks and test verification |
+
+Sub-command names match the locked contract in
+[`docs/contracts/command-clusters.md`](../../docs/contracts/command-clusters.md).
+
+## Dispatch
+
+1. Parse the user's argument: `/bug <sub-command> [args]`.
+2. Look up the sub-command in the table above.
+3. Load the body of the corresponding `commands/bug/<sub>.md` file and follow
+   its `## Instructions` (or `## Steps`) section verbatim.
+4. If the sub-command is unknown or missing, print the menu and ask — do not
+   guess:
+
+   > 1. investigate — trace the root cause (Jira/Sentry/stack-trace context)
+   > 2. fix — plan and implement the fix (quality checks + test verification)
+
+## Rules
+
+- **Investigate before fix when the cause is unknown.** `/bug fix` assumes an
+  investigation result or an obvious cause; if neither exists, recommend
+  `/bug investigate` first.
+- **Do NOT chain sub-commands silently.** One `/bug <sub>` per turn; the
+  investigate output ends with a hand-back, not an auto-started fix.
+- If the user invokes `/bug` with no argument, **show the menu** — do not
+  guess which workflow they meant.

package/dist/agent-src/commands/{set-cost-profile.md → cost/profile.md}

@@ -1,9 +1,12 @@
 ---
 model_tier: medium
-name: set-cost-profile
+name: cost-profile
 pack: meta
 tier: 2
 visibility: internal
+replaces: [set-cost-profile]
+sub: profile
+cluster: cost
 description: Change the rule_loading_tier in .agent-settings.yml — shows each profile's meaning and applies the selection
 skills: [file-editor]
 suggestion:
@@ -20,7 +23,7 @@ packs:
 # /set-cost-profile
 
 Changes `rule_loading_tier` in `.agent-settings.yml`. Four profiles are defined in
-the [`agent-settings` template](../templates/agent-settings.md#cost-profiles):
+the [`agent-settings` template](../../templates/agent-settings.md#cost-profiles):
 
 - `minimal` · `balanced` · `full` · `custom`
 
@@ -32,7 +35,7 @@ the [`agent-settings` template](../templates/agent-settings.md#cost-profiles):
 - For first-run setup use [`/onboard`](onboard.md).
 - For any other single-value change, edit `.agent-settings.yml`
   directly or ask the agent — the merge rules live in
-  [`layered-settings`](../docs/guidelines/agent-infra/layered-settings.md#section-aware-merge-rules).
+  [`layered-settings`](../../../docs/guidelines/agent-infra/layered-settings.md#section-aware-merge-rules).
 - For role modes use [`/mode`](mode.md) — different concept (sets
   `roles.active_role`, not `rule_loading_tier`).
 
@@ -80,7 +83,7 @@ value directly — still echo the old → new line in step 6.
 ### 5. Write the value
 
 Update `rule_loading_tier` in `.agent-settings.yml` using the
-[section-aware merge rules](../docs/guidelines/agent-infra/layered-settings.md#section-aware-merge-rules)
+[section-aware merge rules](../../../docs/guidelines/agent-infra/layered-settings.md#section-aware-merge-rules)
 (preserve comments, preserve key order, touch only the changed field).
 
 If the user picked "Keep current", do nothing and stop.
@@ -113,7 +116,7 @@ flip. Cost behaviour on those surfaces is governed by the platform itself.
 
 ## See also
 
-- [`agent-settings`](../templates/agent-settings.md) — profile matrix and settings reference
-- [`layered-settings`](../docs/guidelines/agent-infra/layered-settings.md) — merge rules for settings edits
+- [`agent-settings`](../../templates/agent-settings.md) — profile matrix and settings reference
+- [`layered-settings`](../../../docs/guidelines/agent-infra/layered-settings.md) — merge rules for settings edits
 - [`onboard`](onboard.md) — first-run setup (includes profile confirmation)
 - [`mode`](mode.md) — role-mode setter (different concept)

package/dist/agent-src/commands/{cost-report.md → cost/report.md}

@@ -4,6 +4,8 @@ name: cost-report
 pack: analytics
 tier: 2
 visibility: internal
+sub: report
+cluster: cost
 description: Capture token cost from the active Claude Code session, append to the local sessions store, and surface the 50/75/90/100% budget alert ladder with cost-profile suggestions.
 skills: [file-editor]
 suggestion:
@@ -76,7 +78,7 @@ Recommend the model lever first:
 ### 4. First-run: prompt to set a budget
 
 If `budget.mjs check` reports `no budget configured`, ask the user (one
-question per turn — see [`ask-when-uncertain`](../rules/ask-when-uncertain.md)):
+question per turn — see [`ask-when-uncertain`](../../rules/ask-when-uncertain.md)):
 
 > No budget set yet. What monthly USD cap do you want to track against?
 > (e.g. 25, 50, 200)
@@ -103,9 +105,10 @@ Allowed values: `today`, `week`, `month`, `all` (default).
 ### 6. Orchestration telemetry summary (when telemetry exists)
 
 Read the current-month JSONL from `agents/runtime/state/audit/YYYY-MM.jsonl`
-(`YYYY-MM` = current UTC month). If it exists and has lines with `input_kind:
-"orchestration"`, surface an orchestration summary via `readOrchestrationMetrics`
-from `src/scripts/_lib/subagent_steering.ts`:
+(where `YYYY-MM` is the current UTC month). If the file exists and contains
+lines with `input_kind: "orchestration"`, surface an orchestration summary
+using `readOrchestrationMetrics` from
+`src/scripts/_lib/subagent_steering.ts`:
 
 ```
 Orchestration telemetry (YYYY-MM, N dispatches):
@@ -115,15 +118,15 @@ Orchestration telemetry (YYYY-MM, N dispatches):
   guardrail breaches:  [token_blowup | spawn_failure | verify_skip | none]
 ```
 
-No orchestration lines yet (capture not running or no delegated dispatches this
-month) → surface:
+If no orchestration lines exist yet (telemetry capture not yet running or
+no delegated dispatches this month), surface:
 
 > No orchestration telemetry yet — subagent dispatches begin writing to
 > `agents/runtime/state/audit/YYYY-MM.jsonl` once `subagents.enabled: true`
 > and a dispatch runs.
 
-Skip this step entirely if the user did not ask about orchestration telemetry and
-there is no `agents/runtime/state/audit/` directory.
+Skip this step entirely if the user did not ask about orchestration telemetry
+and there is no `agents/runtime/state/audit/` directory.
 
 ## Rules
 
@@ -133,8 +136,8 @@ there is no `agents/runtime/state/audit/` directory.
 - **Don't auto-switch profiles.** This command surfaces a recommendation;
   the user runs [`/set-cost-profile`](set-cost-profile.md) themselves.
   Auto-mutation of `.agent-settings.yml` would breach
-  [`commit-policy`](../rules/commit-policy.md) and
-  [`scope-control`](../rules/scope-control.md).
+  [`commit-policy`](../../rules/commit-policy.md) and
+  [`scope-control`](../../rules/scope-control.md).
 - **Honor HARD_STOP.** When `budget.mjs check` exits 1, surface the alert
   prominently and stop the current task — do not keep working through the
   cap silently.
@@ -145,13 +148,11 @@ there is no `agents/runtime/state/audit/` directory.
   `.agent-settings.yml`.
 - [`/agent-status`](agent-status.md) — per-conversation token estimate
   (different scope: in-flight estimate, not historical actuals).
-- [`scripts/cost/track.mjs`](../../scripts/cost/track.mjs) — tracker source.
-- [`scripts/cost/budget.mjs`](../../scripts/cost/budget.mjs) — budget source.
+- [`scripts/cost/track.mjs`](../../../scripts/cost/track.mjs) — tracker source.
+- [`scripts/cost/budget.mjs`](../../../scripts/cost/budget.mjs) — budget source.
 
 ## Attribution
 
-Forked from
-an external reference
-`plugins/external-cost-tracker/scripts/{track,budget}.mjs`. The MCP
-`memory_store` dependency was replaced with a local JSONL append; the
-50/75/90/100% alert ladder and pricing tiers are preserved verbatim.
+Adapted from an external reference. The MCP `memory_store` dependency
+was replaced with a local JSONL append; the 50/75/90/100% alert ladder
+and pricing tiers are preserved verbatim.

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

@@ -0,0 +1,57 @@
+---
+model_tier: medium
+name: cost
+disable-model-invocation: true
+pack: meta
+intent: "Cost dispatcher — session cost report or rule-loading cost profile"
+routes_to: [cost-report, cost-profile]
+replaces: []
+tier: 2
+visibility: internal
+description: Cost orchestrator — routes to report (session token cost + budget ladder) and profile (change the rule_loading_tier)
+cluster: cost
+type: orchestrator
+suggestion:
+  eligible: true
+  trigger_description: "how expensive is this session, check token budget, change the cost profile"
+  trigger_context: "user asks about token cost or budget tiers without picking report vs profile"
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+---
+
+# /cost
+
+Top-level orchestrator for the `/cost` family — token-budget observability
+and configuration.
+
+## Sub-commands
+
+| Sub-command | Routes to | Purpose |
+|---|---|---|
+| `/cost report` | `commands/cost/report.md` | Capture the active session's token cost, append to the local store, surface the 50/75/90/100% budget alert ladder |
+| `/cost profile` | `commands/cost/profile.md` | Change the `rule_loading_tier` in `.agent-settings.yml` — shows each profile's meaning, applies the selection |
+
+Sub-command names match the locked contract in
+[`docs/contracts/command-clusters.md`](../../docs/contracts/command-clusters.md).
+
+## Dispatch
+
+1. Parse the user's argument: `/cost <sub-command> [args]`.
+2. Look up the sub-command in the table above.
+3. Load the body of the corresponding `commands/cost/<sub>.md` file and
+   follow its `## Instructions` (or `## Steps`) section verbatim.
+4. If the sub-command is unknown or missing, print the menu and ask — do not
+   guess:
+
+   > 1. report — session token cost + budget alert ladder (read-only)
+   > 2. profile — change the rule_loading_tier (settings mutation)
+
+## Rules
+
+- **`report` is read-only; `profile` mutates settings.** The profile change
+  always shows the diff and asks before writing.
+- **Do NOT chain sub-commands.** One `/cost <sub>` per turn.
+- If the user invokes `/cost` with no argument, **show the menu** — do not
+  guess which sub-command they meant.

package/dist/agent-src/commands/evals/{review-changes.json → review.json}

@@ -1,34 +1,38 @@
 {
-  "command": "review-changes",
-  "intent": "Multi-judge review of the current diff — bugs, security, tests, quality, architecture",
+  "command": "review",
+  "intent": "Review dispatcher — multi-judge self-review of the current diff, or reviewer routing",
   "cases": [
     {
       "prompt": "self-review my changes before I open a PR",
-      "expected": "review-changes"
+      "expected": "review"
     },
     {
       "prompt": "run all the judges on my current diff",
-      "expected": "review-changes"
+      "expected": "review"
     },
     {
       "prompt": "check my changes for bugs, security, and test coverage",
-      "expected": "review-changes"
+      "expected": "review"
     },
     {
       "prompt": "do a full pre-PR review of the working tree",
-      "expected": "review-changes"
+      "expected": "review"
     },
     {
       "prompt": "review the diff across architecture and quality lenses",
-      "expected": "review-changes"
+      "expected": "review"
     },
     {
       "prompt": "vet these changes before committing",
-      "expected": "review-changes"
+      "expected": "review"
     },
     {
       "prompt": "get an external second opinion from another model",
       "expected": "council"
+    },
+    {
+      "prompt": "who should review this PR, suggest reviewers for the diff",
+      "expected": "review"
     }
   ]
 }

package/dist/agent-src/commands/{quality-fix.md → fix/quality.md}

@@ -1,9 +1,12 @@
 ---
 model_tier: medium
-name: quality-fix
+name: fix-quality
 pack: engineering-base
 tier: 2
 visibility: internal
+replaces: [quality-fix]
+sub: quality
+cluster: fix
 skills: [quality-tools]
 description: Run quality pipeline (PHP and/or JS/TS) and fix all errors — auto-detects language from changed files
 suggestion:
@@ -21,7 +24,7 @@ packs:
 ## Step 0: Detect language
 
 Resolve the quality toolchain via the
-[`toolchain-resolver`](../contexts/execution/toolchain-resolver.md) — it
+[`toolchain-resolver`](../../contexts/execution/toolchain-resolver.md) — it
 returns the per-ecosystem `quality` commands (phpstan / pint / tsc /
 eslint / ruff / mypy / …) alongside the test runner, from the same
 manifest read. The wrapper-first preference and the language table below