@event4u/agent-config 1.32.0 → 1.34.0

package/.agent-src/skills/ui-component-architect/SKILL.md

@@ -0,0 +1,153 @@
+---
+name: ui-component-architect
+description: "Use when shaping a UI component tree — composition vs inheritance, slot patterns, prop API design, controlled vs uncontrolled, polymorphic — even on 'split this component'."
+personas:
+  - frontend-engineer
+source: package
+domain: engineering
+---
+
+# ui-component-architect
+
+> Decide the **shape** of a component tree before the markup is
+> written. Picks composition over inheritance, names the slot
+> contract, draws the controlled/uncontrolled axis, and stops
+> prop bags from growing into god-components. Stack-agnostic —
+> the same lens applies to Blade, Livewire, React, or Vue trees.
+> Pair with [`existing-ui-audit`](../existing-ui-audit/SKILL.md)
+> first; never invent components that already exist.
+
+## When to use
+
+- A new component / screen is being designed and the boundary
+  between parent and children is unclear.
+- An existing component has > 10 props, conditional rendering
+  trees nested ≥ 3 deep, or a `variant`-prop with > 4 values.
+- A primitive (button, card, dialog) is being added to the design
+  system and its API will be reused across teams.
+- German triggers: "wie schneide ich die Komponente?", "Slots
+  oder Props?", "controlled oder uncontrolled?".
+
+Do NOT use when:
+
+- The component is a one-off, used in one place, and unlikely to
+  be reused — over-architecting hurts more than it helps.
+- The question is **styling**, not shape — route to
+  [`tailwind-engineer`](../tailwind-engineer/SKILL.md).
+- The audit step has not run — route to
+  [`existing-ui-audit`](../existing-ui-audit/SKILL.md) first; reusing
+  beats inventing.
+
+## Procedure
+
+### 1. Inspect prior art, state the responsibility in one sentence
+
+Review existing components in the codebase for the same
+responsibility — extend rather than rebuild when a match is found.
+If none exists, write the new component's purpose: *"Renders a
+labelled input with inline error and hint."* If the sentence has an
+"and" joining two unrelated jobs, the component is two components.
+Reject the draft and split before continuing.
+
+### 2. Pick composition over inheritance
+
+Rules of thumb:
+
+| Pattern | When |
+|---|---|
+| Compound components (`Card.Header`, `Card.Body`) | Multiple slots with order semantics |
+| Children + named slots | One main child, plus 1–2 optional regions |
+| Render props / function-as-children | Caller controls rendering of internal state |
+| Polymorphic (`as` prop) | Same shell, different semantic element |
+| Inheritance / class-extension | Almost never — last resort for legacy adapters |
+
+Composition trades verbose call-sites for a tiny, stable component.
+Inheritance trades short call-sites for ABI fragility.
+
+### 3. Draw the controlled / uncontrolled axis
+
+For every piece of state (open, value, selected, expanded), pick:
+
+- **Controlled** — caller passes value + onChange. Caller owns
+  state. Use when state must sync across siblings or persist.
+- **Uncontrolled** — component owns state internally; caller reads
+  via ref or onChange callback. Use for ephemeral state local to
+  the component.
+- **Controlled with default** — both APIs supported via
+  `defaultValue` + optional `value`. The most flexible, also the
+  most code; reserve for design-system primitives.
+
+Mixing controlled / uncontrolled in the same prop without a
+default is the single largest source of "why doesn't my component
+update?" tickets.
+
+### 4. Cap the prop API
+
+Prop budget per component:
+
+| Tier | Cap |
+|---|---|
+| Primitive (Button, Input) | ≤ 6 props + `...rest` to underlying element |
+| Composite (Card, Dialog) | ≤ 8 props; prefer slots for variants |
+| Page section / feature shell | ≤ 4 props; everything else via context |
+
+Over-budget triggers a refactor: extract a config object, push
+state into context, or split into compound parts.
+
+### 5. Name the slot contract
+
+For every slot, document: required vs optional, expected element
+type or component, default rendering when absent, accessibility
+implications (does the slot become the accessible name?). Slots
+without contracts become "stuff a div in there and pray".
+
+## Output format
+
+Return:
+
+1. Responsibility + composition pick — single-sentence purpose, chosen
+   pattern (compound / slots / render-props / polymorphic) with the
+   one-line trade-off.
+2. State + prop API — controlled / uncontrolled / both per state piece,
+   prop list with type and purpose, slot inventory with a11y notes.
+3. Anti-case list — the combinations the component refuses to support
+   (the explicit "no" surface that callers can rely on).
+
+Concrete shape:
+
+```
+Component:        <Name>
+Responsibility:   <one sentence — reject if "and" joins two jobs>
+Pattern:          <compound | slots | render-props | polymorphic>
+State:            value=<controlled|uncontrolled|both>; open=<...>; ...
+Props (≤ tier):   [name: type — purpose]
+Slots:            [name: required? default? a11y note]
+Children:         <count, kind>
+Anti-cases:       <combinations the component refuses to support>
+```
+
+## Gotcha
+
+- `variant` props with > 4 values are usually two components in a
+  trench coat — split when the rendering branches diverge.
+- `as` polymorphism is cheap in TypeScript when typed via generics,
+  expensive without — the type cost is invisible in plain JS.
+- Compound components share state via context; nesting two
+  compound trees of the same family in one parent silently
+  crosses contexts — namespace the context per instance or
+  refuse the nesting.
+- "Render props" + memoization fight; if the function changes
+  every render, the child re-renders too. Stabilize via
+  `useCallback` or hoist.
+
+## Do NOT
+
+- Do NOT design a component without running
+  [`existing-ui-audit`](../existing-ui-audit/SKILL.md) first.
+  Reinventing primitives is the #1 source of design drift.
+- Do NOT use inheritance when composition fits — class-extension
+  hierarchies in UI age badly.
+- Do NOT ship a "kitchen-sink" prop (`config={...}`) just to dodge
+  the prop cap — that hides the API instead of taming it.
+- Do NOT push the architecture into the tracker as code AC — output
+  is a design note for refinement, not implementation steps.

package/.agent-src/skills/unit-economics-modeling/SKILL.md

@@ -4,6 +4,7 @@ description: "Use when modeling CAC, LTV, gross-margin payback, or contribution
 status: active
 tier: senior
 source: package
+domain: product
 ---
 
 # unit-economics-modeling

package/.agent-src/skills/universal-project-analysis/SKILL.md

@@ -2,6 +2,7 @@
 name: universal-project-analysis
 description: "ONLY when user explicitly requests: full project analysis, deep codebase audit, or comprehensive architecture review. Routes to core and framework-specific analysis skills."
 source: package
+domain: discovery
 ---
 
 # universal-project-analysis

package/.agent-src/skills/upstream-contribute/SKILL.md

@@ -2,6 +2,7 @@
 name: upstream-contribute
 description: "Use when a learning, new skill, rule improvement, or bug fix from a consumer project should be contributed back to the shared agent-config package."
 source: package
+domain: process
 execution:
   type: assisted
   handler: internal

package/.agent-src/skills/using-git-worktrees/SKILL.md

@@ -2,6 +2,7 @@
 name: using-git-worktrees
 description: "Use when starting parallel work in isolation from the current branch — spawn a git worktree with ignore-safety checks and a clean test baseline — even when the user says 'try this on the side'."
 source: package
+domain: process
 ---
 
 # using-git-worktrees

package/.agent-src/skills/validate-feature-fit/SKILL.md

@@ -2,6 +2,7 @@
 name: "validate-feature-fit"
 description: "Validate whether a feature request fits the existing codebase — check for duplicates, contradictions, scope creep, and architectural misfit"
 source: package
+domain: quality
 execution:
   type: assisted
   handler: internal

package/.agent-src/skills/verify-completion-evidence/SKILL.md

@@ -2,6 +2,7 @@
 name: verify-completion-evidence
 description: "Use when claiming 'done', suggesting a commit, push, or PR — runs the evidence gate so completion claims come from fresh output in this message, not memory or earlier runs."
 source: package
+domain: quality
 ---
 
 # verify-completion-evidence

package/.agent-src/skills/websocket/SKILL.md

@@ -2,6 +2,7 @@
 name: websocket
 description: "Use when building real-time features — WebSocket broadcasting, live updates, presence channels, connection state — even when the user just says 'push this to the client live'."
 source: package
+domain: engineering
 ---
 
 # websocket

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": "1.32.0"
+    "version": "1.34.0"
   },
   "plugins": [
     {
@@ -15,6 +15,7 @@
       "source": "./",
       "strict": false,
       "skills": [
+        "./.claude/skills/accessibility-auditor",
         "./.claude/skills/adr-create",
         "./.claude/skills/adversarial-review",
         "./.claude/skills/agent-docs-writing",
@@ -32,6 +33,7 @@
         "./.claude/skills/api-design",
         "./.claude/skills/api-endpoint",
         "./.claude/skills/api-testing",
+        "./.claude/skills/architecture-review-lens",
         "./.claude/skills/artisan-commands",
         "./.claude/skills/async-python-patterns",
         "./.claude/skills/authz-review",
@@ -78,6 +80,7 @@
         "./.claude/skills/data-flow-mapper",
         "./.claude/skills/database",
         "./.claude/skills/dcf-modeling",
+        "./.claude/skills/decision-record",
         "./.claude/skills/deep-reading-analyst",
         "./.claude/skills/defense-in-depth",
         "./.claude/skills/dependency-upgrade",
@@ -112,6 +115,7 @@
         "./.claude/skills/fix-refs",
         "./.claude/skills/fix-seeder",
         "./.claude/skills/flux",
+        "./.claude/skills/form-handler",
         "./.claude/skills/funnel-analysis",
         "./.claude/skills/git-workflow",
         "./.claude/skills/github-ci",
@@ -119,6 +123,7 @@
         "./.claude/skills/grill-me",
         "./.claude/skills/guideline-writing",
         "./.claude/skills/implement-ticket",
+        "./.claude/skills/incident-commander",
         "./.claude/skills/jira-integration",
         "./.claude/skills/jira-ticket",
         "./.claude/skills/jobs-events",
@@ -143,6 +148,7 @@
         "./.claude/skills/learning-to-rule-or-skill",
         "./.claude/skills/lint-skills",
         "./.claude/skills/livewire",
+        "./.claude/skills/livewire-architect",
         "./.claude/skills/logging-monitoring",
         "./.claude/skills/markitdown",
         "./.claude/skills/mcp",
@@ -154,6 +160,7 @@
         "./.claude/skills/memory-promote",
         "./.claude/skills/memory-propose",
         "./.claude/skills/merge-conflicts",
+        "./.claude/skills/migration-architect",
         "./.claude/skills/migration-creator",
         "./.claude/skills/mobile-e2e-strategy",
         "./.claude/skills/mode",
@@ -184,7 +191,9 @@
         "./.claude/skills/php-coder",
         "./.claude/skills/php-debugging",
         "./.claude/skills/php-service",
+        "./.claude/skills/playwright-architect",
         "./.claude/skills/playwright-testing",
+        "./.claude/skills/po-discovery",
         "./.claude/skills/prepare-for-review",
         "./.claude/skills/project-analysis-core",
         "./.claude/skills/project-analysis-hypothesis-driven",
@@ -213,9 +222,12 @@
         "./.claude/skills/repomix-packer",
         "./.claude/skills/requesting-code-review",
         "./.claude/skills/research",
+        "./.claude/skills/research-deep",
+        "./.claude/skills/research-report",
         "./.claude/skills/review-changes",
         "./.claude/skills/review-routing",
         "./.claude/skills/rice-prioritization",
+        "./.claude/skills/risk-officer",
         "./.claude/skills/roadmap",
         "./.claude/skills/roadmap-ai-council",
         "./.claude/skills/roadmap-create",
@@ -239,10 +251,13 @@
         "./.claude/skills/skill-reviewer",
         "./.claude/skills/skill-writing",
         "./.claude/skills/sql-writing",
+        "./.claude/skills/stakeholder-tradeoff",
         "./.claude/skills/subagent-orchestration",
         "./.claude/skills/sync-agent-settings",
         "./.claude/skills/sync-gitignore",
         "./.claude/skills/systematic-debugging",
+        "./.claude/skills/tailwind-engineer",
+        "./.claude/skills/tech-debt-tracker",
         "./.claude/skills/technical-specification",
         "./.claude/skills/terraform",
         "./.claude/skills/terragrunt",
@@ -256,6 +271,7 @@
         "./.claude/skills/threat-modeling",
         "./.claude/skills/token-optimizer",
         "./.claude/skills/traefik",
+        "./.claude/skills/ui-component-architect",
         "./.claude/skills/unit-economics-modeling",
         "./.claude/skills/universal-project-analysis",
         "./.claude/skills/update-form-request-messages",

package/AGENTS.md

@@ -21,6 +21,7 @@ task ci                # full pipeline — green before PR
 - **Multi-tool projection** — Augment, Claude Code, Cursor, Cline, Windsurf, Gemini CLI, Claude.ai bundle pipeline that ships from `.agent-src/` to consumer surfaces: [`docs/architecture.md`](docs/architecture.md#cloud-bundle-pipeline).
 - **Editing this repo** — Iron-Law rules (portability, source-of-truth, skill-quality) and the Thin-Root contract (caps · pointer-ratio · triage block) governing AGENTS.md: [`augment-portability`](.agent-src/rules/augment-portability.md), [`augment-source-of-truth`](.agent-src/rules/augment-source-of-truth.md), [`skill-quality`](.agent-src/rules/skill-quality.md), [`agents-md-thin-root`](.agent-src/skills/agents-md-thin-root/SKILL.md).
 - **Consumer story + architecture deep-dive** — what the package does for installers and how it ships: [`README.md`](README.md), [`docs/architecture.md`](docs/architecture.md).
+- **Personas** — 11 review-lens cast (6 core · 5 specialist), `personas:` vs `/mode` axes, citation map, override pattern: [`docs/personas.md`](docs/personas.md), schema [`docs/contracts/persona-schema.md`](docs/contracts/persona-schema.md).
 
 ## Emergency triage — read this when nothing else is reachable
 

package/CHANGELOG.md

@@ -318,6 +318,74 @@ our recommendation order, not its support status.
   users" tension without removing any path that an existing user
   might rely on.
 
+## [1.34.0](https://github.com/event4u-app/agent-config/compare/1.33.0...1.34.0) (2026-05-10)
+
+### Features
+
+* **skills:** block D — eval gate runner + ADR-006 pilot pass (D5) ([afbc4fb](https://github.com/event4u-app/agent-config/commit/afbc4fb6c23949df56376e40b3f0bdda12ee70b5))
+* **skills:** block D — discovery story trio score/audit/suggest (D2-D4) ([f79ff00](https://github.com/event4u-app/agent-config/commit/f79ff005555d84ca84aa5bda8dc4370547a135e9))
+* **skills:** block D — lint_skill_tools meta-linter + CI gate (D1) ([eff36a6](https://github.com/event4u-app/agent-config/commit/eff36a6a254dda61e8639c5d2a6782c0144ebb6c))
+* **skills:** block F UI engineers — tailwind, a11y, form-handler (F2, F3, F6) ([fb6c20a](https://github.com/event4u-app/agent-config/commit/fb6c20a6cbe2e4b6c7dc2f64ab8cad837a3a985a))
+* **skills:** block F UI architects — livewire, playwright, ui-component (F1, F4, F5) ([eeb0eaa](https://github.com/event4u-app/agent-config/commit/eeb0eaaebaf70d7efaba28057f70342745cd623d))
+* **skills:** block C architecture-review-lens — 5th judge in /review-changes (C8) ([197de6b](https://github.com/event4u-app/agent-config/commit/197de6b9687ee69803f53e13bdb9528aa95f4123))
+* **skills:** block C ops/risk — risk-officer, incident-commander, migration-architect (C2, C5, C6) ([24252f6](https://github.com/event4u-app/agent-config/commit/24252f6d754e4b5cdc9a98fd7afc2eaee225d4fb))
+* **skills:** block C product/discovery — po-discovery, decision-record, stakeholder-tradeoff, tech-debt-tracker (C1, C3, C4, C7) ([01a2725](https://github.com/event4u-app/agent-config/commit/01a27256ef175f4f25cde50f1d7b8a3d079855d3))
+* **personas:** discovery surface + public catalog (A5, A6) ([d905639](https://github.com/event4u-app/agent-config/commit/d9056397f4ce687aad65a8fdb75c100ef1d90c01))
+* **orchestration:** subagent mode 7 — do-in-worktrees competitive (A7) ([fa01033](https://github.com/event4u-app/agent-config/commit/fa0103303eaca0db1722a167e788c3a11b2f7ca7))
+* **skills:** cite specialist personas from 9 existing skills (A4) ([d123ac6](https://github.com/event4u-app/agent-config/commit/d123ac6608cf96e0971b3c71e06723e50a6f19fe))
+* **personas:** add 4 specialist personas + qa migration (A3) ([ec19dc5](https://github.com/event4u-app/agent-config/commit/ec19dc579cf69879c5fe339eb6f3d7eee6cf314d))
+* **personas:** lock specialist schema + extend linter (A1, A2) ([79a9ea2](https://github.com/event4u-app/agent-config/commit/79a9ea21202ded3ba848b1e18bf041fecef127c3))
+* **skills:** block B — lock 6-domain taxonomy + back-fill 153 skills ([dfc70fd](https://github.com/event4u-app/agent-config/commit/dfc70fdf8bf97ec30d53a3c81d0b5c4bb61291a9))
+
+### Bug Fixes
+
+* **test:** disable retention pruning in council save() artefact test ([e04de7d](https://github.com/event4u-app/agent-config/commit/e04de7d037e3dbfe7a96cf05369d6940e27298b0))
+* **refs:** post-archive ref fixes for road-to-better-skills + ADR-006 council carve-out ([b8922b7](https://github.com/event4u-app/agent-config/commit/b8922b736d40e370e1eef67500d752a028d7b1bf))
+
+### Chores
+
+* **skills:** clear missing_inspect_step + weak_output_format on Block-C/F skills ([07a72b3](https://github.com/event4u-app/agent-config/commit/07a72b3f91792e99c3acb7e3448f31b7cff7df0a))
+* **hooks:** gate command-count drift in pre-push ([7b0ff9e](https://github.com/event4u-app/agent-config/commit/7b0ff9e175bb59a9c4ca404f9b4b62149e2e8008))
+* **roadmap:** close road-to-better-skills-and-profiles (Block D pass, B4 deferred) ([f5d7170](https://github.com/event4u-app/agent-config/commit/f5d7170a8c5947be273089839f99aab6dc56a693))
+* **matrix:** regenerate file-ownership-matrix for block F skills ([83ad6a7](https://github.com/event4u-app/agent-config/commit/83ad6a777469ca0efe2da01a4d0173181356bbf1))
+* **catalog:** regenerate index + catalog for block F ([bd57d56](https://github.com/event4u-app/agent-config/commit/bd57d56d9226d2a60658dbac2b8d4b82bf48b519))
+* **sync:** refresh compression-hashes + marketplace for block F ([b45b8a9](https://github.com/event4u-app/agent-config/commit/b45b8a9cef1e74e1ee88f164f5f0cc6e92565fbc))
+* **roadmap:** close block F — flip F1-F6 + F marker to done ([e4bd5cc](https://github.com/event4u-app/agent-config/commit/e4bd5cca56e2f30234bc7833ce3650ccbe1634d8))
+* **roadmap:** flip Block C marker to done — 8 skills + 5th judge integrated ([cfd3ede](https://github.com/event4u-app/agent-config/commit/cfd3ede2cf3846570e410209df1ae18b96db2d18))
+* **matrix:** regenerate file-ownership-matrix for Block C skills ([ad89c8f](https://github.com/event4u-app/agent-config/commit/ad89c8fbb50c7bfa7b7031a21e522d5dd582c2a8))
+* **catalog:** regenerate index + catalog for Block C skills ([cfe94a5](https://github.com/event4u-app/agent-config/commit/cfe94a54d1ec448eabc4afa0810beb81e52471f0))
+* **sync:** refresh compression-hashes for review-changes after Block C ([c56dbe2](https://github.com/event4u-app/agent-config/commit/c56dbe25085255a2fb8b5cd85f75d8e471792137))
+* **roadmap:** close block C — flip C1-C8 to done, refresh counts ([954a2fd](https://github.com/event4u-app/agent-config/commit/954a2fd6205e493efd22619c73f8ff7f30b9121b))
+
+Tests: 2606 (+46 since 1.33.0)
+
+## [1.33.0](https://github.com/event4u-app/agent-config/compare/1.32.0...1.33.0) (2026-05-09)
+
+### Features
+
+* **commands:** port /research:deep + /research:report as cluster sub-commands ([71f8141](https://github.com/event4u-app/agent-config/commit/71f8141a3c553ee5b35f31ffdd7ab33e9cb110e5))
+* **guidelines:** port 5w2h, six-hats, systems-thinking, first-principles, critical-thinking from ginobefun ([40ea866](https://github.com/event4u-app/agent-config/commit/40ea8662f4e7714aa66348aff5456b53a3045350))
+
+### Bug Fixes
+
+* **roadmap:** inline council convergence summary instead of file ref ([1087cab](https://github.com/event4u-app/agent-config/commit/1087cab557c12fb353cb7a3e5ac7ab27a8d19379))
+* **research:** add ## Rules section to cluster head ([044bdab](https://github.com/event4u-app/agent-config/commit/044bdabd82b2b16350277f3f7b5e1b0e50703242))
+* **research:** collapse ADOPT citation paths into repo@sha:path tokens ([54deb0d](https://github.com/event4u-app/agent-config/commit/54deb0ddcf201ecbeecf6a57c1074d904fb2d197))
+
+### Documentation
+
+* **counts:** bump command count 101→103 in README + getting-started ([f2fb002](https://github.com/event4u-app/agent-config/commit/f2fb0026c803819569c0c739fdbad8addd96928a))
+* **roadmap:** refresh counts and progress for deep-research adoption phase 2 ([2c284cd](https://github.com/event4u-app/agent-config/commit/2c284cd431480e9c2ae39ec70132a1f8d5eb6e59))
+
+### Chores
+
+* **roadmap:** close road-to-feedback-followups (P0-P3+P5 done, P4 deferred) ([b07db6c](https://github.com/event4u-app/agent-config/commit/b07db6cae705a1e372ed9b75e47d2b14f8447b18))
+* **roadmap:** cancel road-to-event-driven-discipline (skipped, 0% executed) ([590f27d](https://github.com/event4u-app/agent-config/commit/590f27d8c7239431df92e1b7e003837c6e0be178))
+* **roadmap:** close road-to-deep-research-adoption (P1+P2 done, P3 dropped) ([d2a8808](https://github.com/event4u-app/agent-config/commit/d2a880836d79f13efefe6b3257a2ac869e6c9697))
+* **ownership:** regenerate file-ownership matrix for research cluster ([e90f886](https://github.com/event4u-app/agent-config/commit/e90f8861a356e51dbb7bce8baf5c2d8e53732bd2))
+
+Tests: 2560 (+0 since 1.32.0)
+
 ## [1.32.0](https://github.com/event4u-app/agent-config/compare/1.31.0...1.32.0) (2026-05-09)
 
 ### Features

package/README.md

@@ -7,7 +7,7 @@ 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>153 Skills</strong> · <strong>60 Rules</strong> · <strong>101 Commands</strong> · <strong>63 Guidelines</strong> · <strong>8 AI Tools</strong>
+  <strong>167 Skills</strong> · <strong>60 Rules</strong> · <strong>103 Commands</strong> · <strong>68 Guidelines</strong> · <strong>8 AI Tools</strong>
 </p>
 
 ---
@@ -343,7 +343,7 @@ kernel set: [`docs/contracts/kernel-membership.md`](docs/contracts/kernel-member
 | [`/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 101 active commands](.agent-src/commands/)
+→ [Browse all 103 active commands](.agent-src/commands/)
 
 ---
 
@@ -368,7 +368,7 @@ 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 + 153 skills + 101 native commands). Cursor, Cline, Windsurf,
+> package (rules + 167 skills + 103 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.

package/docs/architecture.md

@@ -96,10 +96,10 @@ fails on any source-side violation, without producing artifacts.
 
 | Layer | Count | Purpose |
 |---|---|---|
-| **Skills** | 153 | On-demand expertise — stack analysis (Laravel · Symfony · Zend / Laminas · Next.js · React · Node), testing, Docker, API design, security, observability, … |
+| **Skills** | 167 | On-demand expertise — stack analysis (Laravel · Symfony · Zend / Laminas · Next.js · React · Node), testing, Docker, API design, security, observability, … |
 | **Rules** | 60 | Always-active constraints — coding standards, scope control, verification, language-and-tone, agent-authority |
-| **Commands** | 101 | Slash-command workflows — `/commit`, `/create-pr`, `/fix ci`, `/optimize skills`, `/feature plan`, `/work`, `/implement-ticket`, `/compress`, … |
-| **Guidelines** | 63 | Reference material cited by skills — PHP patterns, Eloquent, Playwright, agent-infra, … |
+| **Commands** | 103 | Slash-command workflows — `/commit`, `/create-pr`, `/fix ci`, `/optimize skills`, `/feature plan`, `/work`, `/implement-ticket`, `/compress`, … |
+| **Guidelines** | 68 | 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 |