@event4u/agent-config 2.25.0 → 3.0.0

package/.agent-src/skills/readme-writing-package/SKILL.md

@@ -7,6 +7,18 @@ execution:
   type: assisted
   handler: internal
   allowed_tools: []
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+lifecycle: active
+trust:
+  level: core
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: false
 ---
 
 # readme-writing-package
@@ -53,7 +65,7 @@ what it does, whether it fits their stack, how to install it, and how to use it.
 
 Read files that define actual package behavior:
 
-- `composer.json` / `package.json` — name, description, requirements, scripts
+- Manifest: `composer.json`, `package.json`, `pyproject.toml`, `Cargo.toml`, `go.mod`, or `*.gemspec` — name, description, requirements, scripts
 - Source entrypoints — public API surface, main classes/functions
 - Config files — publishable configs, defaults
 - CI workflows — what gets tested, supported versions matrix
@@ -83,32 +95,103 @@ Skip sections that have no real content. Never pad.
 
 ### 4. Write requirements and compatibility
 
-State only what is tested and supported:
+State only what is tested and supported. Pull the values from the package's manifest, not from memory. Examples per stack:
 
 ```
-## Requirements
+## Requirements (PHP)
 
 - PHP ^8.2
-- Laravel 11.x
+- Laravel 11.x (optional integration)
 - ext-json
 ```
 
-Do NOT imply broad compatibility if only tested in narrow range.
-Include framework version, language version, required extensions, services.
+```
+## Requirements (JS / TS)
+
+- Node.js >= 20
+- TypeScript >= 5.4 (for typed consumers)
+- npm / pnpm / yarn / bun
+```
+
+```
+## Requirements (Python)
+
+- Python >= 3.11
+- pip / poetry / uv
+- Optional: `fastapi >= 0.110` for the FastAPI integration
+```
+
+```
+## Requirements (Go)
+
+- Go >= 1.22
+```
+
+```
+## Requirements (Rust)
+
+- Rust >= 1.78 (stable)
+- `cargo` workspace member or standalone crate
+```
+
+```
+## Requirements (Ruby)
+
+- Ruby >= 3.2
+- Bundler >= 2.5
+- Optional: Rails 7.1+ for the Rails integration
+```
+
+Do NOT imply broad compatibility if only tested in a narrow range.
+Include language version, framework version, required extensions, and services.
 
 ### 5. Write installation that actually works
 
-Document the exact install command and any required follow-up:
+Document the exact install command and any required follow-up. Use the
+package manager native to the stack — never edit manifests by hand.
 
 ```bash
+# PHP / Composer
 composer require vendor/package
-
-# If framework integration needed:
+# Optional Laravel integration:
 php artisan vendor:publish --tag=package-config
 ```
 
+```bash
+# JS / TS — pick whichever the consumer uses
+npm install <package>
+pnpm add <package>
+yarn add <package>
+bun add <package>
+```
+
+```bash
+# Python
+pip install <package>
+poetry add <package>
+uv add <package>
+```
+
+```bash
+# Go
+go get github.com/<owner>/<package>@latest
+```
+
+```bash
+# Rust
+cargo add <package>
+```
+
+```bash
+# Ruby
+bundle add <package>
+# or, for a standalone gem:
+gem install <package>
+```
+
 Validate each step against the actual codebase.
-Include post-install steps (publish, register, env setup) if required.
+Include post-install steps (config publish, service / module / provider
+registration, env vars, codegen, migrations) if the package requires them.
 
 ### 6. Write the minimal working example
 
@@ -148,10 +231,10 @@ splitting, duplication between README and `/docs/`).
 
 #### Per-AI catalog pattern (multi-platform AI / CLI packages)
 
-For packages targeting many AI assistants or platforms (CLI installers,
-agent-config tools, language SDKs with 10+ targets), prefer flat per-AI
-catalog over giant matrix. One line per target, install command on left,
-aligned trailing comment naming platform:
+For packages that target many AI assistants or platforms (CLI installers,
+agent-config tools, language SDKs with 10+ targets), prefer a flat per-AI
+catalog over a giant matrix. One line per target, install command on the
+left, aligned trailing comment naming the platform:
 
 ```bash
 npx <package> init --tools=claude-code      # Claude Code
@@ -160,22 +243,22 @@ npx <package> init --tools=windsurf         # Windsurf
 # ... one line per supported target
 ```
 
-Pair catalog with separate "Global install" subsection (same flags plus
-`--global`) and "Other commands" subsection. Reference example:
+Pair the catalog with a separate "Global install" subsection (same flags
+plus `--global`) and an "Other commands" subsection. Reference example:
 [`README.md § Pick specific AIs`](../../../README.md#pick-specific-ais) in
-this repo. Inspiration:
+this repository. Inspiration:
 [`ui-ux-pro-max-skill § Installation`](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill#installation).
 
-Use catalog when package's primary install action varies by platform; use
-matrix table (Tool / Rules / Skills / Commands) for capability comparison.
-Different jobs — install vs. coverage.
+Use the catalog when the package's primary install action varies by
+platform; use a matrix table (Tool / Rules / Skills / Commands) for
+capability comparison. They serve different jobs — install vs. coverage.
 
 README = enough to adopt. Docs = enough to master.
 
 ### 8. Validate
 
 - [ ] Install command is correct and complete
-- [ ] Compatibility/requirements match `composer.json` / `package.json` / CI matrix
+- [ ] Compatibility/requirements match the manifest (`composer.json`, `package.json`, `pyproject.toml`, `Cargo.toml`, `go.mod`, `*.gemspec`) and the CI matrix
 - [ ] First example matches real API (verified against source code)
 - [ ] All documented commands exist in repo
 - [ ] No invented features or capabilities
@@ -199,8 +282,8 @@ README = enough to adopt. Docs = enough to master.
 - Model tends to invent compatibility claims or setup steps
 - First example is often too large, too abstract, or uses pseudo-code
 - Model over-explains internals before showing how to use the package
-- Existing README may be outdated — verify against actual `composer.json` / source, not old text
-- Model forgets post-install steps (config publish, service provider, env vars)
+- Existing README may be outdated — verify against the actual manifest (`composer.json`, `package.json`, `pyproject.toml`, `Cargo.toml`, `go.mod`, `*.gemspec`) and source, not the old prose
+- Model forgets post-install steps (config publish, service / module / provider registration, env vars, codegen, migrations) — list whichever the stack requires
 
 ## Frugality Standards
 

package/.agent-src/skills/receiving-code-review/SKILL.md

@@ -5,6 +5,18 @@ personas:
   - critical-challenger
 source: package
 domain: process
+workspaces:
+  - engineering
+packs:
+  - engineering-base
+lifecycle: active
+trust:
+  level: core
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: false
 ---
 
 # receiving-code-review

package/.agent-src/skills/refine-prompt/SKILL.md

@@ -11,6 +11,18 @@ execution:
   type: assisted
   handler: internal
   allowed_tools: []
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+lifecycle: active
+trust:
+  level: core
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: false
 ---
 
 # Refine Prompt
@@ -284,4 +296,4 @@ For `low`, the question replaces the AC list:
 - [`work_engine.scoring.confidence`](../../templates/scripts/work_engine/scoring/confidence.py) — rubric + band thresholds
 - [`ask-when-uncertain`](../../rules/ask-when-uncertain.md) — one-question-per-turn Iron Law
 - [`artifact-drafting-protocol`](../../rules/artifact-drafting-protocol.md) — this skill was drafted under it
-- AI Council session: `agents/council-responses/prompt-master-mini.json` (2026-05-17) — analysis behind the mini/max split and `/raw` bypass <!-- council-ref-allowed: ADR decision trace -->
+- AI Council session: `agents/runtime/council/responses/prompt-master-mini.json` (2026-05-17) — analysis behind the mini/max split and `/raw` bypass <!-- council-ref-allowed: ADR decision trace -->

package/.agent-src/skills/refine-ticket/SKILL.md

@@ -14,6 +14,18 @@ execution:
   type: assisted
   handler: internal
   allowed_tools: []
+workspaces:
+  - product
+packs:
+  - product-basic
+lifecycle: active
+trust:
+  level: professional
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: true
 ---
 
 # Refine Ticket
@@ -151,7 +163,7 @@ in this skill folder) and returns:
 - `threat-modeling` — fires on any auth / webhook / upload / queue /
   secret / tenant / admin / PII / payment keyword, or a `CVE-YYYY-N`
   regex match.
-- `repo_aware` — on when `.git/`, `agents/contexts/`, `composer.json`,
+- `repo_aware` — on when `.git/`, `agents/settings/contexts/`, `composer.json`,
   or `package.json` is present in the cwd; off otherwise.
 - When `repo_aware=True`, `decision.repo_context` is populated by
   `gather_repo_context()`:
@@ -159,7 +171,7 @@ in this skill folder) and returns:
     convention signal).
   - `recent_commits` — up to 30 most recent commit subjects (active
     modules + verb conventions).
-  - `context_docs` — every `agents/contexts/*.md` filename (domain
+  - `context_docs` — every `agents/settings/contexts/*.md` filename (domain
     vocabulary).
 - Outside a repo the context is empty — the skill produces the same
   output shape, minus repo-specific citations (graceful degrade).

package/.agent-src/skills/refine-ticket/detection-map.yml

@@ -110,12 +110,12 @@ sub_skills:
 repo_aware:
   description: >
     When invoked inside a repo clone, /refine-ticket loads
-    agents/contexts/ for domain vocabulary and scans recent branches /
+    agents/settings/contexts/ for domain vocabulary and scans recent branches /
     commits for naming conventions. Outside a repo, skip silently.
   signals:
     - path: .git
       type: dir
-    - path: agents/contexts
+    - path: agents/settings/contexts
       type: dir
     - path: composer.json
       type: file

package/.agent-src/skills/release-comms/SKILL.md

@@ -7,8 +7,18 @@ source: package
 domain: product
 context_spine: [product, team]
 recommended_for_user_types: [creator, gtm, founder]
-
-
+workspaces:
+  - gtm
+packs:
+  - gtm-marketing
+lifecycle: active
+trust:
+  level: professional
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: true
 ---
 
 # release-comms

package/.agent-src/skills/repomix-packer/SKILL.md

@@ -3,6 +3,18 @@ name: repomix-packer
 description: "Use when packaging a codebase to a single AI-friendly file for LLM analysis — local or remote, XML/Markdown/JSON, token counting, gitignore filtering, peer-side `repomix` CLI."
 source: package
 domain: process
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+lifecycle: active
+trust:
+  level: core
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: false
 ---
 
 > **Pinned upstream:** `repomix` CLI (npm: `repomix`, brew: `repomix`). Re-verify per minor bump. Repomix is an **optional dependency** — this skill never installs it silently.
@@ -132,5 +144,5 @@ Cite the snapshot path so the consumer skill can read it.
 
 - Upstream tool: https://github.com/yamadashy/repomix (MIT).
 - Adopted from: `Microck/ordinary-claude-skills@8f5c83174f7aa683b4ddc7433150471983b93131:skills_all/repomix/SKILL.md` (MIT, © 2025 Microck) — wrapper-style adoption, no upstream code vendored.
-- Provenance registry: `agents/contexts/skills-provenance.yml` (entry: `repomix`).
+- Provenance registry: `agents/settings/contexts/skills-provenance.yml` (entry: `repomix`).
 - Iron-Law floor: `non-destructive-by-default`, `missing-tool-handling`, `tool-safety`.

package/.agent-src/skills/requesting-code-review/SKILL.md

@@ -5,6 +5,18 @@ personas:
   - critical-challenger
 source: package
 domain: process
+workspaces:
+  - engineering
+packs:
+  - engineering-base
+lifecycle: active
+trust:
+  level: core
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: false
 ---
 
 # requesting-code-review

package/.agent-src/skills/retention-loops/SKILL.md

@@ -6,6 +6,18 @@ tier: senior
 source: package
 domain: product
 context_spine: [product, customer-segment, funnel-stage]
+workspaces:
+  - product
+packs:
+  - product-basic
+lifecycle: active
+trust:
+  level: professional
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: true
 ---
 
 # retention-loops

package/.agent-src/skills/review-routing/SKILL.md

@@ -3,6 +3,18 @@ name: review-routing
 description: "Use when preparing a PR description, suggesting reviewers, or flagging risk — produces owner-mapped roles plus historical bug-pattern matches from project-local YAML."
 source: package
 domain: quality
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+lifecycle: active
+trust:
+  level: core
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: false
 ---
 
 # review-routing

package/.agent-src/skills/rice-prioritization/SKILL.md

@@ -5,6 +5,18 @@ status: active
 tier: senior
 source: package
 domain: product
+workspaces:
+  - product
+packs:
+  - product-basic
+lifecycle: active
+trust:
+  level: professional
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: true
 ---
 
 # rice-prioritization

package/.agent-src/skills/risk-officer/SKILL.md

@@ -6,6 +6,18 @@ personas:
   - senior-engineer
 source: package
 domain: quality
+workspaces:
+  - engineering
+packs:
+  - engineering-base
+lifecycle: active
+trust:
+  level: core
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: false
 ---
 
 # risk-officer

package/.agent-src/skills/roadmap-management/SKILL.md

@@ -3,6 +3,18 @@ name: roadmap-management
 description: "Use when the user says "create roadmap", "show roadmap", or "execute roadmap". Creates, reads, and manages roadmap files with phase tracking."
 source: package
 domain: process
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+lifecycle: active
+trust:
+  level: core
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: false
 ---
 
 # roadmap-manager
@@ -93,7 +105,7 @@ Every roadmap follows this structure:
 ## Acceptance Criteria
 
 - [ ] {Observable, testable criterion}
-- [ ] All quality gates pass (PHPStan, Rector, tests)
+- [ ] All quality gates pass — the project's type-checker, auto-fixer, linter, and full test suite (see the `quality-tools` skill for stack-specific invocations)
 
 ## Notes
 

package/.agent-src/skills/roadmap-writing/SKILL.md

@@ -3,6 +3,18 @@ name: roadmap-writing
 description: "Use when authoring or rewriting a roadmap in agents/roadmaps/ — phase prose, goal sentence, acceptance criteria, council notes — even when the user just says 'write a plan for X' or 'draft a roadmap'."
 source: package
 domain: process
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+lifecycle: active
+trust:
+  level: core
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: false
 ---
 
 <!-- cloud_safe: degrade -->

package/.agent-src/skills/rtk-output-filtering/SKILL.md

@@ -7,6 +7,18 @@ execution:
   type: assisted
   handler: shell
   allowed_tools: []
+workspaces:
+  - agent-config-maintainer
+packs:
+  - meta
+lifecycle: active
+trust:
+  level: core
+  confidence: high
+  human_review_required: false
+install:
+  default: true
+  removable: false
 ---
 
 # rtk (Rust Token Killer)
@@ -37,12 +49,22 @@ rtk npm test          # same for JS/TS
 rtk docker compose ps # compact container status
 ```
 
-## Procedure: Wrap commands with rtk
+## Procedure: Analyze, then wrap commands with rtk
 
-1. Read `personal.rtk_installed` from `.agent-settings.yml`.
-2. **If `true`** → prefix commands with `rtk` when output >30 lines expected.
-3. **If `false` or missing** → use plain commands. Do not prompt the user.
-4. After wrapping: verify output is useful (not truncated on completeness-critical commands).
+### 1. Analyze the current setup
+
+- Read `personal.rtk_installed` from `.agent-settings.yml`.
+- Review the command about to run: estimated output size, whether
+  completeness matters (e.g. diff review), and whether a project-local
+  filter exists in `.rtk/filters.toml`.
+
+### 2. Wrap (or skip)
+
+1. **If `personal.rtk_installed: true`** → prefix commands with `rtk`
+   when output >30 lines expected.
+2. **If `false` or missing** → use plain commands. Do not prompt the user.
+3. After wrapping: verify output is useful (not truncated on
+   completeness-critical commands).
 
 Installation and one-time setup are owned by
 [`/onboard`](../../commands/onboard.md). If the user asks to install rtk
@@ -153,10 +175,15 @@ When debugging or reviewing diffs, **always run the raw command** without rtk.
 
 ## Project-Local Filters
 
-Custom filters for the project's PHP/Laravel toolchain live in `.rtk/filters.toml`
-(project root, versioned in Git). These override global filters for matching commands.
+Project-local custom filters live in `.rtk/filters.toml` (project root, versioned in Git). These override global filters for matching commands. Add entries for whatever tools the project actually runs.
 
-Covered: PHPStan, Pest, ECS, Rector, Docker Compose, Artisan, Composer.
+Coverage shipped with this package (extend per project):
+- PHP / Laravel: PHPStan, Pest, PHPUnit, ECS, Rector, Composer, Artisan
+- JS / TS: tsc, eslint, prettier, vitest, jest, playwright, pnpm/npm/yarn install + run
+- Python: ruff, mypy, pyright, pytest, pip / poetry / uv
+- Go: `go test`, `go build`, `go vet`, `golangci-lint`
+- Rust: `cargo build`, `cargo test`, `cargo clippy`, `cargo fmt`
+- Infra / runtime: Docker Compose, Terraform, kubectl
 
 To generate or update project-local filters → use the `/optimize-rtk-filters` command.