5 Commits

Author SHA1 Message Date
78429a709f fix(marketplace): correct stale hook references and migration guide errors
- claude-config-audit-settings.md: update hook inventory to post-Decision #29 state
- maintainer.md: remove PostToolUse references, update to current hook types
- settings-optimization.md: update review layer table and hooks.json format
- claude-config-optimize-settings.md: fix stale doc-guardian PostToolUse reference
- project-hygiene/claude-md-integration.md: rewrite for manual /hygiene check
- doc-guardian: update doc-sync.md and sync-workflow.md hook references
- MIGRATION-v9.md: mark deleted commands as Removed, not renamed
- projman/task-sizing.md: PostToolUse → PreToolUse in example
- scripts/setup.sh: /labels-sync → /labels sync
- docs/CONFIGURATION.md: doc-guardian "Commands and hooks" → "Commands only"
- docs/prompts/INDEX.md: add prompt execution index

Version: 9.0.1

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-07 15:23:57 -05:00
382a3a3af8 Merge pull request 'feat: Command consolidation + 8 new plugins (v8.1.0 → v9.0.0)' (#445) from feat/phase-1b-command-consolidation into development
Reviewed-on: #445
2026-02-06 20:02:12 +00:00
2d51df7a42 feat(marketplace): command consolidation + 8 new plugins (v8.1.0 → v9.0.0) [BREAKING]
Phase 1b: Rename all ~94 commands across 12 plugins to /<noun> <action>
sub-command pattern. Git-flow consolidated from 8→5 commands (commit
variants absorbed into --push/--merge/--sync flags). Dispatch files,
name: frontmatter, and cross-reference updates for all plugins.

Phase 2: Design documents for 8 new plugins in docs/designs/.

Phase 3: Scaffold 8 new plugins — saas-api-platform, saas-db-migrate,
saas-react-platform, saas-test-pilot, data-seed, ops-release-manager,
ops-deploy-pipeline, debug-mcp. Each with plugin.json, commands, agents,
skills, README, and claude-md-integration. Marketplace grows from 12→20.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 14:52:11 -05:00
5098422858 Merge pull request 'feat: Phase 1 evolution — domain metadata + hook migration (v8.0.0 → v8.1.0)' (#444) from feat/phase-1-evolution into development
Reviewed-on: #444
2026-02-06 17:31:18 +00:00
9ba2e660d3 feat(marketplace): hook migration, projman commands, optimizations [BREAKING]
Remove all SessionStart and PostToolUse hooks across the marketplace,
retaining only PreToolUse safety hooks and UserPromptSubmit quality hooks.
Add /project and /adr command families, /hygiene check, /cv status.
Create 7 new projman skills for project lifecycle management.
Remove /pm-debug, /suggest-version, /proposal-status commands.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 12:28:06 -05:00
367 changed files with 14706 additions and 2877 deletions

View File

@@ -6,7 +6,7 @@
},
"metadata": {
"description": "Project management plugins with Gitea and NetBox integrations",
"version": "8.0.0"
"version": "9.0.1"
},
"plugins": [
{
@@ -20,9 +20,6 @@
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/projman/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"hooks": [
"./hooks/hooks.json"
],
"category": "development",
"tags": [
"sprint",
@@ -44,9 +41,6 @@
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/doc-guardian/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"hooks": [
"./hooks/hooks.json"
],
"category": "productivity",
"tags": [
"documentation",
@@ -90,9 +84,6 @@
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/project-hygiene/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"hooks": [
"./hooks/hooks.json"
],
"category": "productivity",
"tags": [
"cleanup",
@@ -139,9 +130,6 @@
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/claude-config-maintainer/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"hooks": [
"./hooks/hooks.json"
],
"category": "development",
"tags": [
"claude-md",
@@ -210,9 +198,6 @@
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/pr-review/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"hooks": [
"./hooks/hooks.json"
],
"category": "development",
"tags": [
"code-review",
@@ -234,9 +219,6 @@
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/data-platform/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"hooks": [
"./hooks/hooks.json"
],
"category": "data",
"tags": [
"pandas",
@@ -260,9 +242,6 @@
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/viz-platform/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"hooks": [
"./hooks/hooks.json"
],
"category": "visualization",
"tags": [
"dash",
@@ -287,9 +266,6 @@
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/contract-validator/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"hooks": [
"./hooks/hooks.json"
],
"category": "development",
"tags": [
"validation",
@@ -301,6 +277,186 @@
],
"license": "MIT",
"domain": "core"
},
{
"name": "saas-api-platform",
"version": "0.1.0",
"description": "REST and GraphQL API scaffolding for FastAPI and Express projects",
"source": "./plugins/saas-api-platform",
"author": {
"name": "Leo Miranda",
"email": "leobmiranda@gmail.com"
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/saas-api-platform/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"category": "development",
"tags": [
"api",
"rest",
"graphql",
"fastapi",
"express",
"openapi"
],
"license": "MIT",
"domain": "saas"
},
{
"name": "saas-db-migrate",
"version": "0.1.0",
"description": "Database migration management for Alembic, Prisma, and raw SQL",
"source": "./plugins/saas-db-migrate",
"author": {
"name": "Leo Miranda",
"email": "leobmiranda@gmail.com"
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/saas-db-migrate/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"category": "development",
"tags": [
"database",
"migrations",
"alembic",
"prisma",
"sql",
"schema"
],
"license": "MIT",
"domain": "saas"
},
{
"name": "saas-react-platform",
"version": "0.1.0",
"description": "React frontend development toolkit for Next.js and Vite projects",
"source": "./plugins/saas-react-platform",
"author": {
"name": "Leo Miranda",
"email": "leobmiranda@gmail.com"
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/saas-react-platform/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"category": "development",
"tags": [
"react",
"nextjs",
"vite",
"typescript",
"frontend",
"components"
],
"license": "MIT",
"domain": "saas"
},
{
"name": "saas-test-pilot",
"version": "0.1.0",
"description": "Test automation toolkit for pytest, Jest, Vitest, and Playwright",
"source": "./plugins/saas-test-pilot",
"author": {
"name": "Leo Miranda",
"email": "leobmiranda@gmail.com"
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/saas-test-pilot/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"category": "development",
"tags": [
"testing",
"pytest",
"jest",
"vitest",
"playwright",
"coverage"
],
"license": "MIT",
"domain": "saas"
},
{
"name": "data-seed",
"version": "0.1.0",
"description": "Test data generation and database seeding with relationship-aware profiles",
"source": "./plugins/data-seed",
"author": {
"name": "Leo Miranda",
"email": "leobmiranda@gmail.com"
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/data-seed/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"category": "data",
"tags": [
"seed-data",
"test-data",
"faker",
"fixtures",
"database"
],
"license": "MIT",
"domain": "data"
},
{
"name": "ops-release-manager",
"version": "0.1.0",
"description": "Release management with semantic versioning, changelogs, and tag automation",
"source": "./plugins/ops-release-manager",
"author": {
"name": "Leo Miranda",
"email": "leobmiranda@gmail.com"
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/ops-release-manager/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"category": "development",
"tags": [
"release",
"semver",
"changelog",
"versioning",
"tags"
],
"license": "MIT",
"domain": "ops"
},
{
"name": "ops-deploy-pipeline",
"version": "0.1.0",
"description": "CI/CD deployment pipeline management for Docker Compose and systemd services",
"source": "./plugins/ops-deploy-pipeline",
"author": {
"name": "Leo Miranda",
"email": "leobmiranda@gmail.com"
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/ops-deploy-pipeline/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"category": "infrastructure",
"tags": [
"deploy",
"docker-compose",
"systemd",
"caddy",
"cicd"
],
"license": "MIT",
"domain": "ops"
},
{
"name": "debug-mcp",
"version": "0.1.0",
"description": "MCP server debugging, inspection, and development toolkit",
"source": "./plugins/debug-mcp",
"author": {
"name": "Leo Miranda",
"email": "leobmiranda@gmail.com"
},
"homepage": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace/src/branch/main/plugins/debug-mcp/README.md",
"repository": "https://gitea.hotserv.cloud/personal-projects/leo-claude-mktplace.git",
"category": "development",
"tags": [
"mcp",
"debugging",
"diagnostics",
"server",
"development"
],
"license": "MIT",
"domain": "debug"
}
]
}

View File

@@ -6,6 +6,112 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
## [Unreleased]
## [9.0.1] - 2026-02-06
### Fixed
- **claude-config-maintainer:** `claude-config-audit-settings.md` Step 4 referenced deleted hooks.json files (doc-guardian, project-hygiene, data-platform, contract-validator) — updated to current hook inventory (code-sentinel, git-flow, cmdb-assistant, clarity-assist)
- **claude-config-maintainer:** `maintainer.md` agent referenced project-hygiene PostToolUse hooks — updated to current hook types
- **claude-config-maintainer:** `claude-config-audit-settings.md` output format referenced doc-guardian review layer — updated to git-flow, cmdb-assistant, clarity-assist
- **claude-config-maintainer:** `claude-config-audit-settings.md` Mermaid diagram referenced doc-guardian — updated to git-flow
- **claude-config-maintainer:** `claude-config-optimize-settings.md` reviewed profile prerequisites referenced doc-guardian PostToolUse — updated to git-flow PreToolUse
- **project-hygiene:** `claude-md-integration.md` described PostToolUse hook behavior that was removed in v8.1.0 — rewritten for manual `/hygiene check` command
- **doc-guardian:** `doc-sync.md` referenced doc-guardian hooks — updated to reference `/doc audit`
- **doc-guardian:** `sync-workflow.md` referenced PostToolUse hook — updated to note removal per Decision #29
- **projman:** `task-sizing.md` example referenced PostToolUse — updated to PreToolUse
- **docs:** `MIGRATION-v9.md` listed `/pm-debug`, `/suggest-version`, `/proposal-status` as renamed to `/projman` sub-commands — corrected to show as **Removed** (these were deleted in v8.1.0, not renamed in v9.0.0)
- **docs:** `CONFIGURATION.md` listed doc-guardian as "Commands and hooks only" — corrected to "Commands only"
- **scripts:** `setup.sh` referenced old `/labels-sync` command — updated to `/labels sync`
## [9.0.0] - 2026-02-06
### Added
- **Phase 3: 8 new plugin scaffolds**
- `saas-api-platform` (domain: saas) — REST/GraphQL API scaffolding for FastAPI and Express. 6 commands, 2 agents, 5 skills
- `saas-db-migrate` (domain: saas) — Database migration management for Alembic, Prisma, and raw SQL. 6 commands, 2 agents, 5 skills
- `saas-react-platform` (domain: saas) — React frontend toolkit for Next.js and Vite projects. 6 commands, 2 agents, 6 skills
- `saas-test-pilot` (domain: saas) — Test automation for pytest, Jest, Vitest, and Playwright. 6 commands, 2 agents, 6 skills
- `data-seed` (domain: data) — Test data generation and database seeding. 5 commands, 2 agents, 5 skills
- `ops-release-manager` (domain: ops) — Release management with SemVer, changelogs, and tag automation. 6 commands, 2 agents, 5 skills
- `ops-deploy-pipeline` (domain: ops) — CI/CD deployment pipeline for Docker Compose and systemd. 6 commands, 2 agents, 6 skills
- `debug-mcp` (domain: debug) — MCP server debugging, inspection, and development toolkit. 5 commands, 1 agent, 5 skills
- 8 design documents in `docs/designs/` for all new plugins
---
## [9.0.0] - 2026-02-06
### BREAKING CHANGES
#### Command Consolidation (v9.0.0)
All commands renamed to `/<noun> <action>` sub-command pattern. Every command across all 12 plugins now follows this convention. See [MIGRATION-v9.md](./docs/MIGRATION-v9.md) for the complete old-to-new mapping.
**Key changes:**
- **projman:** `/sprint-plan``/sprint plan`, `/pm-setup``/projman setup`, `/pm-review``/sprint review`, `/pm-test``/sprint test`, `/labels-sync``/labels sync`
- **git-flow:** 8→5 commands. `/git-commit``/gitflow commit`. Three commit variants (`-push`, `-merge`, `-sync`) consolidated into `--push`/`--merge`/`--sync` flags. `/branch-start``/gitflow branch-start`, `/git-status``/gitflow status`, `/git-config``/gitflow config`
- **pr-review:** `/pr-review``/pr review`, `/project-init``/pr init`, `/project-sync``/pr sync`
- **clarity-assist:** `/clarify``/clarity clarify`, `/quick-clarify``/clarity quick-clarify`
- **doc-guardian:** `/doc-audit``/doc audit`, `/changelog-gen``/doc changelog-gen`, `/stale-docs``/doc stale-docs`
- **code-sentinel:** `/security-scan``/sentinel scan`, `/refactor``/sentinel refactor`
- **claude-config-maintainer:** `/config-analyze``/claude-config analyze` (all 8 commands prefixed)
- **contract-validator:** `/validate-contracts``/cv validate`, `/check-agent``/cv check-agent`
- **cmdb-assistant:** `/cmdb-search``/cmdb search`, `/change-audit``/cmdb change-audit`, `/ip-conflicts``/cmdb ip-conflicts`
- **data-platform:** `/data-ingest``/data ingest`, `/dbt-test``/data dbt-test`, `/lineage-viz``/data lineage-viz`
- **viz-platform:** `/accessibility-check``/viz accessibility-check`, `/design-gate``/viz design-gate`, `/design-review``/viz design-review`
### Added
- Dispatch files for all 12 plugins — each plugin now has a `<noun>.md` routing table listing all sub-commands
- `name:` frontmatter field added to all command files for sub-command resolution
- `docs/MIGRATION-v9.md` — Complete old-to-new command mapping for consumer migration
- `docs/COMMANDS-CHEATSHEET.md` — Full rewrite with v9.0.0 command names
### Changed
- All documentation updated with new command names: CLAUDE.md, README.md, CONFIGURATION.md, UPDATING.md, agent-workflow.spec.md, netbox/README.md
- All cross-plugin references updated (skills, agents, integration files)
- `marketplace.json` version bumped to 9.0.0
---
## [8.1.0] - 2026-02-06
### BREAKING CHANGES
#### Hook Migration (v8.1.0)
All `SessionStart` and `PostToolUse` hooks removed. Only `PreToolUse` safety hooks and `UserPromptSubmit` quality hooks remain. Plugins that relied on automatic startup checks or post-write automation must use manual commands instead.
### Added
- **projman:** 7 new skills — `source-analysis`, `project-charter`, `adr-conventions`, `epic-conventions`, `wbs`, `risk-register`, `sprint-roadmap`
- **projman:** `/project` command family — `initiation`, `plan`, `status`, `close` for full project lifecycle management
- **projman:** `/adr` command family — `create`, `list`, `update`, `supersede` for Architecture Decision Records
- **projman:** Expanded `wiki-conventions.md` with dependency headers, R&D notes, page naming patterns
- **projman:** Epic/* labels (5) and RnD/* labels (4) added to label taxonomy
- **project-hygiene:** `/hygiene check` manual command replacing PostToolUse hook
- **contract-validator:** `/cv status` marketplace-wide health check command
### Changed
- `verify-hooks.sh` rewritten to validate post-migration hook inventory (4 plugins, 5 hooks)
- `config-permissions-map.md` updated to reflect reduced hook inventory
- `settings-optimization.md` updated for current hook landscape
- `sprint-plan.md` no longer loads `token-budget-report.md` skill
- `sprint-close.md` loads `rfc-workflow.md` conditionally; manual CHANGELOG review replaces `/suggest-version`
- `planner.md` and `orchestrator.md` no longer reference domain consultation or domain gates
- Label taxonomy updated from 43 to 58 labels (added Status/4, Domain/2, Epic/5, RnD/4)
### Removed
- **hooks:** 8 hooks.json files deleted (projman, pr-review, doc-guardian, project-hygiene, claude-config-maintainer, viz-platform, data-platform, contract-validator SessionStart/PostToolUse hooks)
- **hooks:** Orphaned shell scripts deleted (startup-check.sh, notify.sh, cleanup.sh, enforce-rules.sh, schema-diff-check.sh, auto-validate.sh, breaking-change-check.sh)
- **projman:** `/pm-debug`, `/suggest-version`, `/proposal-status` commands deleted
- **projman:** `domain-consultation.md` skill deleted
- **cmdb-assistant:** SessionStart hook removed (PreToolUse hook retained)
---
## [8.0.0] - 2026-02-06

103
CLAUDE.md
View File

@@ -128,25 +128,33 @@ These plugins exist in source but are **NOT relevant** to this project's workflo
| **data-platform** | For data engineering projects (pandas, PostgreSQL, dbt) |
| **viz-platform** | For dashboard projects (Dash, Plotly) |
| **cmdb-assistant** | For infrastructure projects (NetBox) |
| **saas-api-platform** | For REST/GraphQL API projects (FastAPI, Express) |
| **saas-db-migrate** | For database migration projects (Alembic, Prisma) |
| **saas-react-platform** | For React frontend projects (Next.js, Vite) |
| **saas-test-pilot** | For test automation projects (pytest, Jest, Playwright) |
| **data-seed** | For test data generation and seeding |
| **ops-release-manager** | For release management workflows |
| **ops-deploy-pipeline** | For deployment pipeline management |
| **debug-mcp** | For MCP server debugging and development |
**Do NOT suggest** `/data-ingest`, `/data-profile`, `/viz-chart`, `/cmdb-*` commands - they don't apply here.
**Do NOT suggest** `/data ingest`, `/data profile`, `/viz chart`, `/cmdb *`, `/api *`, `/db-migrate *`, `/react *`, `/test *`, `/seed *`, `/release *`, `/deploy *`, `/debug-mcp *` commands - they don't apply here.
### Key Distinction
| Context | Path | What To Do |
|---------|------|------------|
| **Editing plugin source** | `~/claude-plugins-work/plugins/` | Modify code, add features |
| **Using installed plugins** | `~/.claude/plugins/marketplaces/` | Run commands like `/sprint-plan` |
| **Using installed plugins** | `~/.claude/plugins/marketplaces/` | Run commands like `/sprint plan` |
When user says "run /sprint-plan", use the INSTALLED plugin.
When user says "fix the sprint-plan command", edit the SOURCE code.
When user says "run /sprint plan", use the INSTALLED plugin.
When user says "fix the sprint plan command", edit the SOURCE code.
---
## Project Overview
**Repository:** leo-claude-mktplace
**Version:** 7.0.0
**Version:** 9.0.1
**Status:** Production Ready
A plugin marketplace for Claude Code containing:
@@ -164,7 +172,15 @@ A plugin marketplace for Claude Code containing:
| `data-platform` | pandas, PostgreSQL, and dbt integration for data engineering | 1.3.0 |
| `viz-platform` | DMC validation, Plotly charts, and theming for dashboards | 1.1.0 |
| `contract-validator` | Cross-plugin compatibility validation and agent verification | 1.1.0 |
| `project-hygiene` | Post-task cleanup automation via hooks | 0.1.0 |
| `project-hygiene` | Project file organization and cleanup checks | 0.1.0 |
| `saas-api-platform` | REST/GraphQL API scaffolding for FastAPI and Express | 0.1.0 |
| `saas-db-migrate` | Database migration management for Alembic, Prisma, raw SQL | 0.1.0 |
| `saas-react-platform` | React frontend toolkit for Next.js and Vite | 0.1.0 |
| `saas-test-pilot` | Test automation for pytest, Jest, Vitest, Playwright | 0.1.0 |
| `data-seed` | Test data generation and database seeding | 0.1.0 |
| `ops-release-manager` | Release management with SemVer and changelog automation | 0.1.0 |
| `ops-deploy-pipeline` | Deployment pipeline for Docker Compose and systemd | 0.1.0 |
| `debug-mcp` | MCP server debugging and development toolkit | 0.1.0 |
## Quick Start
@@ -180,16 +196,17 @@ A plugin marketplace for Claude Code containing:
| Category | Commands |
|----------|----------|
| **Setup** | `/pm-setup` (modes: `--full`, `--quick`, `--sync`) |
| **Sprint** | `/sprint-plan`, `/sprint-start`, `/sprint-status` (with `--diagram`), `/sprint-close` |
| **Quality** | `/pm-review`, `/pm-test` (modes: `run`, `gen`) |
| **Versioning** | `/suggest-version` |
| **PR Review** | `/pr-review`, `/pr-summary`, `/pr-findings`, `/pr-diff` |
| **Docs** | `/doc-audit`, `/doc-sync`, `/changelog-gen`, `/doc-coverage`, `/stale-docs` |
| **Security** | `/security-scan`, `/refactor`, `/refactor-dry` |
| **Config** | `/config-analyze`, `/config-optimize`, `/config-diff`, `/config-lint` |
| **Validation** | `/validate-contracts`, `/check-agent`, `/list-interfaces`, `/dependency-graph` |
| **Debug** | `/pm-debug` (modes: `report`, `review`) |
| **Setup** | `/projman setup` (modes: `--full`, `--quick`, `--sync`) |
| **Sprint** | `/sprint plan`, `/sprint start`, `/sprint status` (with `--diagram`), `/sprint close` |
| **Quality** | `/sprint review`, `/sprint test` (modes: `run`, `gen`) |
| **Project** | `/project initiation\|plan\|status\|close` |
| **ADR** | `/adr create\|list\|update\|supersede` |
| **PR Review** | `/pr review`, `/pr summary`, `/pr findings`, `/pr diff` |
| **Docs** | `/doc audit`, `/doc sync`, `/doc changelog-gen`, `/doc coverage`, `/doc stale-docs` |
| **Security** | `/sentinel scan`, `/sentinel refactor`, `/sentinel refactor-dry` |
| **Config** | `/claude-config analyze`, `/claude-config optimize`, `/claude-config diff`, `/claude-config lint` |
| **Validation** | `/cv validate`, `/cv check-agent`, `/cv list-interfaces`, `/cv dependency-graph`, `/cv status` |
| **Maintenance** | `/hygiene check` |
### Plugin Commands - NOT RELEVANT to This Project
@@ -197,9 +214,17 @@ These commands are being developed but don't apply to this project's workflow:
| Category | Commands | For Projects Using |
|----------|----------|-------------------|
| **Data** | `/data-ingest`, `/data-profile`, `/data-schema`, `/data-lineage`, `/dbt-test` | pandas, PostgreSQL, dbt |
| **Visualization** | `/viz-component`, `/viz-chart`, `/viz-dashboard`, `/viz-theme` | Dash, Plotly dashboards |
| **CMDB** | `/cmdb-search`, `/cmdb-device`, `/cmdb-sync` | NetBox infrastructure |
| **Data** | `/data ingest`, `/data profile`, `/data schema`, `/data lineage`, `/data dbt-test` | pandas, PostgreSQL, dbt |
| **Visualization** | `/viz component`, `/viz chart`, `/viz dashboard`, `/viz theme` | Dash, Plotly dashboards |
| **CMDB** | `/cmdb search`, `/cmdb device`, `/cmdb sync` | NetBox infrastructure |
| **API** | `/api scaffold`, `/api validate`, `/api docs`, `/api middleware` | FastAPI, Express |
| **DB Migrate** | `/db-migrate generate`, `/db-migrate validate`, `/db-migrate plan` | Alembic, Prisma |
| **React** | `/react component`, `/react route`, `/react state`, `/react hook` | Next.js, Vite |
| **Testing** | `/test generate`, `/test coverage`, `/test fixtures`, `/test e2e` | pytest, Jest, Playwright |
| **Seeding** | `/seed generate`, `/seed profile`, `/seed apply` | Faker, test data |
| **Release** | `/release prepare`, `/release validate`, `/release tag` | SemVer releases |
| **Deploy** | `/deploy generate`, `/deploy validate`, `/deploy check` | Docker Compose, systemd |
| **Debug MCP** | `/debug-mcp status`, `/debug-mcp test`, `/debug-mcp logs` | MCP server development |
## Repository Structure
@@ -217,18 +242,16 @@ leo-claude-mktplace/
├── plugins/
│ ├── projman/ # Sprint management
│ │ ├── .claude-plugin/plugin.json
│ │ ├── commands/ # 12 commands
│ │ ├── hooks/ # SessionStart: mismatch detection
│ │ ├── commands/ # 19 commands
│ │ ├── agents/ # 4 agents
│ │ └── skills/ # 17 reusable skill files
│ │ └── skills/ # 23 reusable skill files
│ ├── git-flow/ # Git workflow automation
│ │ ├── .claude-plugin/plugin.json
│ │ ├── commands/ # 8 commands
│ │ ├── commands/ # 5 commands
│ │ └── agents/
│ ├── pr-review/ # Multi-agent PR review
│ │ ├── .claude-plugin/plugin.json
│ │ ├── commands/ # 6 commands
│ │ ├── hooks/ # SessionStart mismatch detection
│ │ ├── commands/ # 8 commands
│ │ └── agents/ # 5 agents
│ ├── clarity-assist/ # Prompt optimization
│ │ ├── .claude-plugin/plugin.json
@@ -237,12 +260,10 @@ leo-claude-mktplace/
│ ├── data-platform/ # Data engineering
│ │ ├── .claude-plugin/plugin.json
│ │ ├── commands/ # 7 commands
│ │ ├── hooks/ # SessionStart PostgreSQL check
│ │ └── agents/ # 2 agents
│ ├── viz-platform/ # Visualization
│ │ ├── .claude-plugin/plugin.json
│ │ ├── commands/ # 7 commands
│ │ ├── hooks/ # SessionStart DMC check
│ │ └── agents/ # 3 agents
│ ├── doc-guardian/ # Documentation drift detection
│ ├── code-sentinel/ # Security scanning & refactoring
@@ -366,17 +387,17 @@ Wiki-based Request for Comments system for tracking feature ideas from proposal
**Lifecycle:** Draft → Review → Approved → Implementing → Implemented
**Integration with Sprint Planning:**
- `/sprint-plan` detects approved RFCs and offers selection
- `/sprint-close` updates RFC status on completion
- `/sprint plan` detects approved RFCs and offers selection
- `/sprint close` updates RFC status on completion
## Label Taxonomy
43 labels total: 27 organization + 16 repository
58 labels total: 31 organization + 27 repository
**Organization:** Agent/2, Complexity/3, Efforts/5, Priority/4, Risk/3, Source/4, Type/6
**Repository:** Component/9, Tech/7
**Organization:** Agent/2, Complexity/3, Efforts/5, Priority/4, Risk/3, Source/4, Status/4, Type/6
**Repository:** Component/9, Tech/7, Domain/2, Epic/5, RnD/4
Sync with `/labels-sync` command.
Sync with `/labels sync` command.
## Lessons Learned System
@@ -414,8 +435,10 @@ Stored in Gitea Wiki under `lessons-learned/sprints/`.
| Domain | Plugins |
|--------|---------|
| `core` | projman, git-flow, pr-review, code-sentinel, doc-guardian, clarity-assist, contract-validator, claude-config-maintainer, project-hygiene |
| `data` | data-platform, viz-platform |
| `ops` | cmdb-assistant |
| `data` | data-platform, viz-platform, data-seed |
| `saas` | saas-api-platform, saas-db-migrate, saas-react-platform, saas-test-pilot |
| `ops` | cmdb-assistant, ops-release-manager, ops-deploy-pipeline |
| `debug` | debug-mcp |
### Adding a Command to projman
@@ -468,12 +491,12 @@ See `docs/DEBUGGING-CHECKLIST.md` for systematic troubleshooting.
| Symptom | Likely Cause | Fix |
|---------|--------------|-----|
| "X MCP servers failed" | Missing venv in installed path | `cd ~/.claude/plugins/marketplaces/leo-claude-mktplace && ./scripts/setup.sh` |
| MCP tools not available | Venv missing or .mcp.json misconfigured | Run `/pm-debug report` to diagnose |
| MCP tools not available | Venv missing or .mcp.json misconfigured | Run `/cv status` to diagnose |
| Changes not taking effect | Editing source, not installed | Reinstall plugin or edit installed path |
**Debug Commands:**
- `/pm-debug report` - Run full diagnostics, create issue if needed
- `/pm-debug review` - Investigate and propose fixes
**Diagnostic Commands:**
- `/cv status` - Marketplace-wide health check (installation, MCP, configuration)
- `/hygiene check` - Project file organization and cleanup check
## Versioning Workflow
@@ -527,4 +550,4 @@ The script will:
---
**Last Updated:** 2026-02-03
**Last Updated:** 2026-02-06

150
README.md
View File

@@ -1,4 +1,4 @@
# Leo Claude Marketplace - v8.0.0
# Leo Claude Marketplace - v9.0.1
A collection of Claude Code plugins for project management, infrastructure automation, and development workflows.
@@ -16,7 +16,7 @@ Use the launcher script to load only the plugins you need, reducing token overhe
| `review` | pr-review, code-sentinel | Lightweight code review |
| `data` | data-platform, viz-platform | Data engineering and visualization |
| `infra` | cmdb-assistant | Infrastructure/CMDB management |
| `full` | All 12 plugins via marketplace.json | When you need everything |
| `full` | All 20 plugins via marketplace.json | When you need everything |
**Examples:**
```bash
@@ -45,7 +45,7 @@ AI-guided sprint planning with full Gitea integration. Transforms a proven 15-sp
- Branch-aware security (development/staging/production)
- Pre-sprint-close code quality review and test verification
**Commands:** `/sprint-plan`, `/sprint-start`, `/sprint-status`, `/sprint-close`, `/labels-sync`, `/pm-setup`, `/pm-review`, `/pm-test`, `/pm-debug`, `/suggest-version`, `/proposal-status`, `/rfc`
**Commands:** `/sprint plan`, `/sprint start`, `/sprint status`, `/sprint close`, `/labels sync`, `/projman setup`, `/sprint review`, `/sprint test`, `/projman debug`, `/projman suggest-version`, `/projman proposal-status`, `/rfc`
#### [git-flow](./plugins/git-flow)
**Git Workflow Automation**
@@ -58,7 +58,7 @@ Smart git operations with intelligent commit messages and branch management.
- Merge and cleanup automation
- Protected branch awareness
**Commands:** `/git-commit`, `/git-commit-push`, `/git-commit-merge`, `/git-commit-sync`, `/branch-start`, `/branch-cleanup`, `/git-status`, `/git-config`
**Commands:** `/gitflow commit` (with `--push`, `--merge`, `--sync` flags), `/gitflow branch-start`, `/gitflow branch-cleanup`, `/gitflow status`, `/gitflow config`
#### [pr-review](./plugins/pr-review)
**Multi-Agent PR Review**
@@ -70,14 +70,14 @@ Comprehensive pull request review using specialized agents.
- Actionable feedback with suggested fixes
- Gitea integration for automated review submission
**Commands:** `/pr-review`, `/pr-summary`, `/pr-findings`, `/pr-diff`, `/pr-setup`, `/project-init`, `/project-sync`
**Commands:** `/pr review`, `/pr summary`, `/pr findings`, `/pr diff`, `/pr setup`, `/pr init`, `/pr sync`
#### [claude-config-maintainer](./plugins/claude-config-maintainer)
**CLAUDE.md and Settings Optimization**
Analyze, optimize, and create CLAUDE.md configuration files. Audit and optimize settings.local.json permissions.
**Commands:** `/analyze`, `/optimize`, `/init`, `/config-diff`, `/config-lint`, `/config-audit-settings`, `/config-optimize-settings`, `/config-permissions-map`
**Commands:** `/claude-config analyze`, `/claude-config optimize`, `/claude-config init`, `/claude-config diff`, `/claude-config lint`, `/claude-config audit-settings`, `/claude-config optimize-settings`, `/claude-config permissions-map`
#### [contract-validator](./plugins/contract-validator)
**Cross-Plugin Compatibility Validation**
@@ -90,7 +90,7 @@ Validate plugin marketplaces for command conflicts, tool overlaps, and broken ag
- Data flow validation for agent sequences
- Markdown or JSON reports with actionable suggestions
**Commands:** `/validate-contracts`, `/check-agent`, `/list-interfaces`, `/dependency-graph`, `/cv-setup`
**Commands:** `/cv validate`, `/cv check-agent`, `/cv list-interfaces`, `/cv dependency-graph`, `/cv setup`
### Productivity
@@ -103,14 +103,14 @@ Transform vague requests into clear specifications using structured methodology.
- ND-friendly question patterns (option-based, chunked)
- Conflict detection and escalation protocols
**Commands:** `/clarify`, `/quick-clarify`
**Commands:** `/clarity clarify`, `/clarity quick-clarify`
#### [doc-guardian](./plugins/doc-guardian)
**Documentation Lifecycle Management**
Automatic documentation drift detection and synchronization.
**Commands:** `/doc-audit`, `/doc-sync`, `/changelog-gen`, `/doc-coverage`, `/stale-docs`
**Commands:** `/doc audit`, `/doc sync`, `/doc changelog-gen`, `/doc coverage`, `/doc stale-docs`
#### [project-hygiene](./plugins/project-hygiene)
**Post-Task Cleanup Automation**
@@ -124,7 +124,7 @@ Hook-based cleanup that runs after Claude completes work.
Security vulnerability detection and code refactoring tools.
**Commands:** `/security-scan`, `/refactor`, `/refactor-dry`
**Commands:** `/sentinel scan`, `/sentinel refactor`, `/sentinel refactor-dry`
### Infrastructure
@@ -133,7 +133,7 @@ Security vulnerability detection and code refactoring tools.
Full CRUD operations for network infrastructure management directly from Claude Code.
**Commands:** `/cmdb-setup`, `/cmdb-search`, `/cmdb-device`, `/cmdb-ip`, `/cmdb-site`, `/cmdb-audit`, `/cmdb-register`, `/cmdb-sync`, `/cmdb-topology`, `/change-audit`, `/ip-conflicts`
**Commands:** `/cmdb setup`, `/cmdb search`, `/cmdb device`, `/cmdb ip`, `/cmdb site`, `/cmdb audit`, `/cmdb register`, `/cmdb sync`, `/cmdb topology`, `/cmdb change-audit`, `/cmdb ip-conflicts`
### Data Engineering
@@ -148,7 +148,7 @@ Comprehensive data engineering toolkit with persistent DataFrame storage.
- 100k row limit with chunking support
- Auto-detection of dbt projects
**Commands:** `/data-ingest`, `/data-profile`, `/data-schema`, `/data-explain`, `/data-lineage`, `/lineage-viz`, `/data-run`, `/dbt-test`, `/data-quality`, `/data-review`, `/data-gate`, `/data-setup`
**Commands:** `/data ingest`, `/data profile`, `/data schema`, `/data explain`, `/data lineage`, `/data lineage-viz`, `/data run`, `/data dbt-test`, `/data quality`, `/data review`, `/data gate`, `/data setup`
### Visualization
@@ -164,7 +164,109 @@ Visualization toolkit with version-locked component validation and design token
- 5 Page tools for multi-page app structure
- Dual theme storage: user-level and project-level
**Commands:** `/viz-chart`, `/viz-chart-export`, `/viz-dashboard`, `/viz-theme`, `/viz-theme-new`, `/viz-theme-css`, `/viz-component`, `/accessibility-check`, `/viz-breakpoints`, `/design-review`, `/design-gate`, `/viz-setup`
**Commands:** `/viz chart`, `/viz chart-export`, `/viz dashboard`, `/viz theme`, `/viz theme-new`, `/viz theme-css`, `/viz component`, `/viz accessibility-check`, `/viz breakpoints`, `/viz design-review`, `/viz design-gate`, `/viz setup`
#### [data-seed](./plugins/data-seed)
**Test Data Generation and Database Seeding**
Relationship-aware test data generation with reusable seed profiles.
- Schema inference from existing databases
- Faker-based data generation with locale support
- Foreign key relationship resolution
- Reusable seed profiles for consistent test environments
**Commands:** `/seed setup`, `/seed generate`, `/seed profile`, `/seed validate`, `/seed apply`
### SaaS Development
#### [saas-api-platform](./plugins/saas-api-platform)
**REST and GraphQL API Scaffolding**
API development toolkit for FastAPI and Express projects with OpenAPI integration.
- Framework-aware scaffolding (FastAPI, Express)
- OpenAPI spec generation and validation
- Middleware catalog with authentication, CORS, rate limiting
- Route pattern enforcement and test generation
**Commands:** `/api setup`, `/api scaffold`, `/api validate`, `/api docs`, `/api middleware`, `/api test-routes`
#### [saas-db-migrate](./plugins/saas-db-migrate)
**Database Migration Management**
Migration toolkit for Alembic, Prisma, and raw SQL with safety validation.
- ORM/tool auto-detection
- Migration safety analysis (data loss, locks, rollback)
- Execution planning with rollback strategies
- Migration history tracking
**Commands:** `/db-migrate setup`, `/db-migrate generate`, `/db-migrate validate`, `/db-migrate plan`, `/db-migrate history`, `/db-migrate rollback`
#### [saas-react-platform](./plugins/saas-react-platform)
**React Frontend Development Toolkit**
Component scaffolding, routing, and state management for Next.js and Vite projects.
- Framework detection (Next.js App Router/Pages, Vite, CRA, Remix)
- TypeScript-first component generation with co-located tests
- State management pattern selection (Context, Zustand, Redux Toolkit)
- Anti-pattern detection and component tree analysis
**Commands:** `/react setup`, `/react component`, `/react route`, `/react state`, `/react hook`, `/react lint`
#### [saas-test-pilot](./plugins/saas-test-pilot)
**Test Automation Toolkit**
Test generation and coverage analysis for pytest, Jest, Vitest, and Playwright.
- Framework auto-detection and configuration
- Test case generation from code analysis
- Coverage gap detection with risk prioritization
- E2E test scenario generation from user stories
**Commands:** `/test setup`, `/test generate`, `/test coverage`, `/test fixtures`, `/test e2e`, `/test run`
### Operations
#### [ops-release-manager](./plugins/ops-release-manager)
**Release Management Automation**
Semantic versioning, changelog generation, and tag management.
- Version location auto-detection across manifests
- Conventional commit-based bump suggestions
- Keep a Changelog format automation
- Release branch/tag creation and rollback
**Commands:** `/release setup`, `/release prepare`, `/release validate`, `/release tag`, `/release rollback`, `/release status`
#### [ops-deploy-pipeline](./plugins/ops-deploy-pipeline)
**Deployment Pipeline Management**
CI/CD for Docker Compose and systemd-based services on self-hosted infrastructure.
- Docker Compose configuration generation
- Caddy reverse proxy patterns
- Environment-specific config management
- Pre-deployment health checks and rollback planning
**Commands:** `/deploy setup`, `/deploy generate`, `/deploy validate`, `/deploy env`, `/deploy check`, `/deploy rollback`
### Debugging
#### [debug-mcp](./plugins/debug-mcp)
**MCP Server Debugging Toolkit**
Diagnostic tools for MCP server health, testing, and development.
- MCP server health status dashboard
- Individual tool call testing
- Server log analysis with error pattern recognition
- MCP server scaffold generation
**Commands:** `/debug-mcp status`, `/debug-mcp test`, `/debug-mcp logs`, `/debug-mcp inspect`, `/debug-mcp scaffold`
## Domain Advisory Pattern
@@ -172,14 +274,14 @@ The marketplace supports cross-plugin domain advisory integration:
- **Domain Detection**: projman automatically detects when issues involve specialized domains (frontend/viz, data engineering)
- **Acceptance Criteria**: Domain-specific acceptance criteria are added to issues during planning
- **Execution Gates**: Domain validation gates (`/design-gate`, `/data-gate`) run before issue completion
- **Execution Gates**: Domain validation gates (`/viz design-gate`, `/data gate`) run before issue completion
- **Extensible**: New domains can be added by creating advisory agents and gate commands
**Current Domains:**
| Domain | Plugin | Gate Command |
|--------|--------|--------------|
| Visualization | viz-platform | `/design-gate` |
| Data | data-platform | `/data-gate` |
| Visualization | viz-platform | `/viz design-gate` |
| Data | data-platform | `/data gate` |
## MCP Servers
@@ -280,7 +382,7 @@ Add to `.claude/settings.json` in your target project:
After installing plugins, run the setup wizard:
```
/pm-setup
/projman setup
```
The wizard handles everything:
@@ -292,12 +394,12 @@ The wizard handles everything:
**For new projects** (when system is already configured):
```
/project-init
/pr init
```
**After moving a repository:**
```
/project-sync
/pr sync
```
See [docs/CONFIGURATION.md](./docs/CONFIGURATION.md) for manual setup and advanced options.
@@ -332,17 +434,17 @@ After installing plugins, the `/plugin` command may show `(no content)` - this i
| Plugin | Test Command |
|--------|--------------|
| git-flow | `/git-flow:git-status` |
| git-flow | `/git-flow:gitflow-status` |
| projman | `/projman:sprint-status` |
| pr-review | `/pr-review:pr-summary` |
| clarity-assist | `/clarity-assist:clarify` |
| clarity-assist | `/clarity-assist:clarity-clarify` |
| doc-guardian | `/doc-guardian:doc-audit` |
| code-sentinel | `/code-sentinel:security-scan` |
| claude-config-maintainer | `/claude-config-maintainer:analyze` |
| code-sentinel | `/code-sentinel:sentinel-scan` |
| claude-config-maintainer | `/claude-config-maintainer:claude-config-analyze` |
| cmdb-assistant | `/cmdb-assistant:cmdb-search` |
| data-platform | `/data-platform:data-ingest` |
| viz-platform | `/viz-platform:viz-chart` |
| contract-validator | `/contract-validator:validate-contracts` |
| contract-validator | `/contract-validator:cv-validate` |
## Repository Structure

View File

@@ -1,6 +1,8 @@
# Plugin Commands Cheat Sheet
Quick reference for all commands in the Leo Claude Marketplace.
Quick reference for all commands in the Leo Claude Marketplace (v9.0.0+).
All commands follow the `/<noun> <action>` sub-command pattern.
---
@@ -8,98 +10,96 @@ Quick reference for all commands in the Leo Claude Marketplace.
| Plugin | Command | Auto | Manual | Description |
|--------|---------|:----:|:------:|-------------|
| **projman** | `/sprint-plan` | | X | Start sprint planning with AI-guided architecture analysis and issue creation |
| **projman** | `/sprint-start` | | X | Begin sprint execution with dependency analysis and parallel task coordination (requires approval or `--force`) |
| **projman** | `/sprint-status` | | X | Check current sprint progress (add `--diagram` for Mermaid visualization) |
| **projman** | `/pm-review` | | X | Pre-sprint-close code quality review (debug artifacts, security, error handling) |
| **projman** | `/pm-test` | | X | Run tests (`/pm-test run`) or generate tests (`/pm-test gen <target>`) |
| **projman** | `/sprint-close` | | X | Complete sprint and capture lessons learned to Gitea Wiki |
| **projman** | `/labels-sync` | | X | Synchronize label taxonomy from Gitea |
| **projman** | `/pm-setup` | | X | Auto-detect mode or use `--full`, `--quick`, `--sync`, `--clear-cache` |
| **projman** | *SessionStart hook* | X | | Detects git remote vs .env mismatch, warns to run `/pm-setup --sync` |
| **projman** | `/pm-debug` | | X | Diagnostics (`/pm-debug report`) or investigate (`/pm-debug review`) |
| **projman** | `/suggest-version` | | X | Analyze CHANGELOG and recommend semantic version bump |
| **projman** | `/proposal-status` | | X | View proposal and implementation hierarchy with status |
| **projman** | `/rfc` | | X | RFC lifecycle management (`/rfc create\|list\|review\|approve\|reject`) |
| **git-flow** | `/git-commit` | | X | Create commit with auto-generated conventional message |
| **git-flow** | `/git-commit-push` | | X | Commit and push to remote in one operation |
| **git-flow** | `/git-commit-merge` | | X | Commit current changes, then merge into target branch |
| **git-flow** | `/git-commit-sync` | | X | Full sync: commit, push, and sync with upstream/base branch |
| **git-flow** | `/branch-start` | | X | Create new feature/fix/chore branch with naming conventions |
| **git-flow** | `/branch-cleanup` | | X | Remove merged branches locally and optionally on remote |
| **git-flow** | `/git-status` | | X | Enhanced git status with recommendations |
| **git-flow** | `/git-config` | | X | Configure git-flow settings for the project |
| **pr-review** | `/pr-setup` | | X | Setup wizard for pr-review (shares Gitea MCP with projman) |
| **pr-review** | `/project-init` | | X | Quick project setup for PR reviews |
| **pr-review** | `/project-sync` | | X | Sync config with git remote after repo move/rename |
| **pr-review** | *SessionStart hook* | X | | Detects git remote vs .env mismatch |
| **pr-review** | `/pr-review` | | X | Full multi-agent PR review with confidence scoring |
| **pr-review** | `/pr-summary` | | X | Quick summary of PR changes |
| **pr-review** | `/pr-findings` | | X | List and filter review findings by category/severity |
| **pr-review** | `/pr-diff` | | X | Formatted diff with inline review comments and annotations |
| **clarity-assist** | `/clarify` | | X | Full 4-D prompt optimization with ND accommodations |
| **clarity-assist** | `/quick-clarify` | | X | Rapid single-pass clarification for simple requests |
| **doc-guardian** | `/doc-audit` | | X | Full documentation audit - scans for doc drift |
| **doc-guardian** | `/doc-sync` | | X | Synchronize pending documentation updates |
| **doc-guardian** | `/changelog-gen` | | X | Generate changelog from conventional commits |
| **doc-guardian** | `/doc-coverage` | | X | Documentation coverage metrics by function/class |
| **doc-guardian** | `/stale-docs` | | X | Flag documentation behind code changes |
| **doc-guardian** | *PostToolUse hook* | X | | Silently detects doc drift on Write/Edit |
| **code-sentinel** | `/security-scan` | | X | Full security audit (SQL injection, XSS, secrets, etc.) |
| **code-sentinel** | `/refactor` | | X | Apply refactoring patterns to improve code |
| **code-sentinel** | `/refactor-dry` | | X | Preview refactoring without applying changes |
| **projman** | `/sprint plan` | | X | Start sprint planning with AI-guided architecture analysis and issue creation |
| **projman** | `/sprint start` | | X | Begin sprint execution with dependency analysis and parallel task coordination (requires approval or `--force`) |
| **projman** | `/sprint status` | | X | Check current sprint progress (add `--diagram` for Mermaid visualization) |
| **projman** | `/sprint review` | | X | Pre-sprint-close code quality review (debug artifacts, security, error handling) |
| **projman** | `/sprint test` | | X | Run tests (`/sprint test run`) or generate tests (`/sprint test gen <target>`) |
| **projman** | `/sprint close` | | X | Complete sprint and capture lessons learned to Gitea Wiki |
| **projman** | `/labels sync` | | X | Synchronize label taxonomy from Gitea |
| **projman** | `/projman setup` | | X | Auto-detect mode or use `--full`, `--quick`, `--sync`, `--clear-cache` |
| **projman** | `/rfc create\|list\|review\|approve\|reject` | | X | RFC lifecycle management |
| **projman** | `/project initiation\|plan\|status\|close` | | X | Project lifecycle management |
| **projman** | `/adr create\|list\|update\|supersede` | | X | Architecture Decision Records |
| **git-flow** | `/gitflow commit` | | X | Create commit with auto-generated conventional message. Flags: `--push`, `--merge`, `--sync` |
| **git-flow** | `/gitflow branch-start` | | X | Create new feature/fix/chore branch with naming conventions |
| **git-flow** | `/gitflow branch-cleanup` | | X | Remove merged branches locally and optionally on remote |
| **git-flow** | `/gitflow status` | | X | Enhanced git status with recommendations |
| **git-flow** | `/gitflow config` | | X | Configure git-flow settings for the project |
| **pr-review** | `/pr setup` | | X | Setup wizard for pr-review (shares Gitea MCP with projman) |
| **pr-review** | `/pr init` | | X | Quick project setup for PR reviews |
| **pr-review** | `/pr sync` | | X | Sync config with git remote after repo move/rename |
| **pr-review** | `/pr review` | | X | Full multi-agent PR review with confidence scoring |
| **pr-review** | `/pr summary` | | X | Quick summary of PR changes |
| **pr-review** | `/pr findings` | | X | List and filter review findings by category/severity |
| **pr-review** | `/pr diff` | | X | Formatted diff with inline review comments and annotations |
| **clarity-assist** | `/clarity clarify` | | X | Full 4-D prompt optimization with ND accommodations |
| **clarity-assist** | `/clarity quick-clarify` | | X | Rapid single-pass clarification for simple requests |
| **doc-guardian** | `/doc audit` | | X | Full documentation audit - scans for doc drift |
| **doc-guardian** | `/doc sync` | | X | Synchronize pending documentation updates |
| **doc-guardian** | `/doc changelog-gen` | | X | Generate changelog from conventional commits |
| **doc-guardian** | `/doc coverage` | | X | Documentation coverage metrics by function/class |
| **doc-guardian** | `/doc stale-docs` | | X | Flag documentation behind code changes |
| **code-sentinel** | `/sentinel scan` | | X | Full security audit (SQL injection, XSS, secrets, etc.) |
| **code-sentinel** | `/sentinel refactor` | | X | Apply refactoring patterns to improve code |
| **code-sentinel** | `/sentinel refactor-dry` | | X | Preview refactoring without applying changes |
| **code-sentinel** | *PreToolUse hook* | X | | Scans code before writing; blocks critical issues |
| **claude-config-maintainer** | `/config-analyze` | | X | Analyze CLAUDE.md for optimization opportunities |
| **claude-config-maintainer** | `/config-optimize` | | X | Optimize CLAUDE.md structure with preview/backup |
| **claude-config-maintainer** | `/config-init` | | X | Initialize new CLAUDE.md for a project |
| **claude-config-maintainer** | `/config-diff` | | X | Track CLAUDE.md changes over time with behavioral impact |
| **claude-config-maintainer** | `/config-lint` | | X | Lint CLAUDE.md for anti-patterns and best practices |
| **claude-config-maintainer** | `/config-audit-settings` | | X | Audit settings.local.json permissions (100-point score) |
| **claude-config-maintainer** | `/config-optimize-settings` | | X | Optimize permissions (profiles, consolidation, dry-run) |
| **claude-config-maintainer** | `/config-permissions-map` | | X | Visual review layer + permission coverage map |
| **cmdb-assistant** | `/cmdb-setup` | | X | Setup wizard for NetBox MCP server |
| **cmdb-assistant** | `/cmdb-search` | | X | Search NetBox for devices, IPs, sites |
| **cmdb-assistant** | `/cmdb-device` | | X | Manage network devices (create, view, update, delete) |
| **cmdb-assistant** | `/cmdb-ip` | | X | Manage IP addresses and prefixes |
| **cmdb-assistant** | `/cmdb-site` | | X | Manage sites, locations, racks, and regions |
| **cmdb-assistant** | `/cmdb-audit` | | X | Data quality analysis (VMs, devices, naming, roles) |
| **cmdb-assistant** | `/cmdb-register` | | X | Register current machine into NetBox with running apps |
| **cmdb-assistant** | `/cmdb-sync` | | X | Sync machine state with NetBox (detect drift, update) |
| **cmdb-assistant** | `/cmdb-topology` | | X | Infrastructure topology diagrams (rack, network, site views) |
| **cmdb-assistant** | `/change-audit` | | X | NetBox audit trail queries with filtering |
| **cmdb-assistant** | `/ip-conflicts` | | X | Detect IP conflicts and overlapping prefixes |
| **project-hygiene** | *PostToolUse hook* | X | | Removes temp files, warns about unexpected root files |
| **data-platform** | `/data-ingest` | | X | Load data from CSV, Parquet, JSON into DataFrame |
| **data-platform** | `/data-profile` | | X | Generate data profiling report with statistics |
| **data-platform** | `/data-schema` | | X | Explore database schemas, tables, columns |
| **data-platform** | `/data-explain` | | X | Explain query execution plan |
| **data-platform** | `/data-lineage` | | X | Show dbt model lineage and dependencies |
| **data-platform** | `/data-run` | | X | Run dbt models with validation |
| **data-platform** | `/lineage-viz` | | X | dbt lineage visualization as Mermaid diagrams |
| **data-platform** | `/dbt-test` | | X | Formatted dbt test runner with summary and failure details |
| **data-platform** | `/data-quality` | | X | DataFrame quality checks (nulls, duplicates, types, outliers) |
| **data-platform** | `/data-setup` | | X | Setup wizard for data-platform MCP servers |
| **data-platform** | *SessionStart hook* | X | | Checks PostgreSQL connection (non-blocking warning) |
| **viz-platform** | `/viz-setup` | | X | Setup wizard for viz-platform MCP server |
| **viz-platform** | `/viz-chart` | | X | Create Plotly charts with theme integration |
| **viz-platform** | `/viz-dashboard` | | X | Create dashboard layouts with filters and grids |
| **viz-platform** | `/viz-theme` | | X | Apply existing theme to visualizations |
| **viz-platform** | `/viz-theme-new` | | X | Create new custom theme with design tokens |
| **viz-platform** | `/viz-theme-css` | | X | Export theme as CSS custom properties |
| **viz-platform** | `/viz-component` | | X | Inspect DMC component props and validation |
| **viz-platform** | `/viz-chart-export` | | X | Export charts to PNG, SVG, PDF via kaleido |
| **viz-platform** | `/accessibility-check` | | X | Color blind validation (WCAG contrast ratios) |
| **viz-platform** | `/viz-breakpoints` | | X | Configure responsive layout breakpoints |
| **viz-platform** | `/design-review` | | X | Detailed design system audits |
| **viz-platform** | `/design-gate` | | X | Binary pass/fail design system validation gates |
| **viz-platform** | *SessionStart hook* | X | | Checks DMC version (non-blocking warning) |
| **data-platform** | `/data-review` | | X | Comprehensive data integrity audits |
| **data-platform** | `/data-gate` | | X | Binary pass/fail data integrity gates |
| **contract-validator** | `/validate-contracts` | | X | Full marketplace compatibility validation |
| **contract-validator** | `/check-agent` | | X | Validate single agent definition |
| **contract-validator** | `/list-interfaces` | | X | Show all plugin interfaces |
| **contract-validator** | `/dependency-graph` | | X | Mermaid visualization of plugin dependencies |
| **contract-validator** | `/cv-setup` | | X | Setup wizard for contract-validator MCP |
| **claude-config-maintainer** | `/claude-config analyze` | | X | Analyze CLAUDE.md for optimization opportunities |
| **claude-config-maintainer** | `/claude-config optimize` | | X | Optimize CLAUDE.md structure with preview/backup |
| **claude-config-maintainer** | `/claude-config init` | | X | Initialize new CLAUDE.md for a project |
| **claude-config-maintainer** | `/claude-config diff` | | X | Track CLAUDE.md changes over time with behavioral impact |
| **claude-config-maintainer** | `/claude-config lint` | | X | Lint CLAUDE.md for anti-patterns and best practices |
| **claude-config-maintainer** | `/claude-config audit-settings` | | X | Audit settings.local.json permissions (100-point score) |
| **claude-config-maintainer** | `/claude-config optimize-settings` | | X | Optimize permissions (profiles, consolidation, dry-run) |
| **claude-config-maintainer** | `/claude-config permissions-map` | | X | Visual review layer + permission coverage map |
| **cmdb-assistant** | `/cmdb setup` | | X | Setup wizard for NetBox MCP server |
| **cmdb-assistant** | `/cmdb search` | | X | Search NetBox for devices, IPs, sites |
| **cmdb-assistant** | `/cmdb device` | | X | Manage network devices (create, view, update, delete) |
| **cmdb-assistant** | `/cmdb ip` | | X | Manage IP addresses and prefixes |
| **cmdb-assistant** | `/cmdb site` | | X | Manage sites, locations, racks, and regions |
| **cmdb-assistant** | `/cmdb audit` | | X | Data quality analysis (VMs, devices, naming, roles) |
| **cmdb-assistant** | `/cmdb register` | | X | Register current machine into NetBox with running apps |
| **cmdb-assistant** | `/cmdb sync` | | X | Sync machine state with NetBox (detect drift, update) |
| **cmdb-assistant** | `/cmdb topology` | | X | Infrastructure topology diagrams (rack, network, site views) |
| **cmdb-assistant** | `/cmdb change-audit` | | X | NetBox audit trail queries with filtering |
| **cmdb-assistant** | `/cmdb ip-conflicts` | | X | Detect IP conflicts and overlapping prefixes |
| **project-hygiene** | `/hygiene check` | | X | Project file organization and cleanup check |
| **data-platform** | `/data ingest` | | X | Load data from CSV, Parquet, JSON into DataFrame |
| **data-platform** | `/data profile` | | X | Generate data profiling report with statistics |
| **data-platform** | `/data schema` | | X | Explore database schemas, tables, columns |
| **data-platform** | `/data explain` | | X | Explain query execution plan |
| **data-platform** | `/data lineage` | | X | Show dbt model lineage and dependencies |
| **data-platform** | `/data run` | | X | Run dbt models with validation |
| **data-platform** | `/data lineage-viz` | | X | dbt lineage visualization as Mermaid diagrams |
| **data-platform** | `/data dbt-test` | | X | Formatted dbt test runner with summary and failure details |
| **data-platform** | `/data quality` | | X | DataFrame quality checks (nulls, duplicates, types, outliers) |
| **data-platform** | `/data review` | | X | Comprehensive data integrity audits |
| **data-platform** | `/data gate` | | X | Binary pass/fail data integrity gates |
| **data-platform** | `/data setup` | | X | Setup wizard for data-platform MCP servers |
| **viz-platform** | `/viz setup` | | X | Setup wizard for viz-platform MCP server |
| **viz-platform** | `/viz chart` | | X | Create Plotly charts with theme integration |
| **viz-platform** | `/viz chart-export` | | X | Export charts to PNG, SVG, PDF via kaleido |
| **viz-platform** | `/viz dashboard` | | X | Create dashboard layouts with filters and grids |
| **viz-platform** | `/viz theme` | | X | Apply existing theme to visualizations |
| **viz-platform** | `/viz theme-new` | | X | Create new custom theme with design tokens |
| **viz-platform** | `/viz theme-css` | | X | Export theme as CSS custom properties |
| **viz-platform** | `/viz component` | | X | Inspect DMC component props and validation |
| **viz-platform** | `/viz accessibility-check` | | X | Color blind validation (WCAG contrast ratios) |
| **viz-platform** | `/viz breakpoints` | | X | Configure responsive layout breakpoints |
| **viz-platform** | `/viz design-review` | | X | Detailed design system audits |
| **viz-platform** | `/viz design-gate` | | X | Binary pass/fail design system validation gates |
| **contract-validator** | `/cv validate` | | X | Full marketplace compatibility validation |
| **contract-validator** | `/cv check-agent` | | X | Validate single agent definition |
| **contract-validator** | `/cv list-interfaces` | | X | Show all plugin interfaces |
| **contract-validator** | `/cv dependency-graph` | | X | Mermaid visualization of plugin dependencies |
| **contract-validator** | `/cv setup` | | X | Setup wizard for contract-validator MCP |
| **contract-validator** | `/cv status` | | X | Marketplace-wide health check (installation, MCP, configuration) |
---
## Migration from v8.x
All commands were renamed in v9.0.0 to follow `/<noun> <action>` pattern. See [MIGRATION-v9.md](./MIGRATION-v9.md) for the complete old-to-new mapping.
---
@@ -107,7 +107,7 @@ Quick reference for all commands in the Leo Claude Marketplace.
| Category | Plugins | Primary Use |
|----------|---------|-------------|
| **Setup** | projman, pr-review, cmdb-assistant, data-platform, viz-platform, contract-validator | `/pm-setup`, `/pr-setup`, `/cmdb-setup`, `/data-setup`, `/viz-setup`, `/cv-setup` |
| **Setup** | projman, pr-review, cmdb-assistant, data-platform, viz-platform, contract-validator | `/projman setup`, `/pr setup`, `/cmdb setup`, `/data setup`, `/viz setup`, `/cv setup` |
| **Task Planning** | projman, clarity-assist | Sprint management, requirement clarification |
| **Code Quality** | code-sentinel, pr-review | Security scanning, PR reviews |
| **Documentation** | doc-guardian, claude-config-maintainer | Doc sync, CLAUDE.md maintenance |
@@ -116,7 +116,7 @@ Quick reference for all commands in the Leo Claude Marketplace.
| **Data Engineering** | data-platform | pandas, PostgreSQL, dbt operations |
| **Visualization** | viz-platform | DMC validation, Plotly charts, theming |
| **Validation** | contract-validator | Cross-plugin compatibility checks |
| **Maintenance** | project-hygiene | Automatic cleanup |
| **Maintenance** | project-hygiene | Manual cleanup via `/hygiene check` |
---
@@ -124,13 +124,10 @@ Quick reference for all commands in the Leo Claude Marketplace.
| Plugin | Hook Event | Behavior |
|--------|------------|----------|
| **projman** | SessionStart | Checks git remote vs .env; warns if mismatch detected; suggests sprint planning if issues exist |
| **pr-review** | SessionStart | Checks git remote vs .env; warns if mismatch detected |
| **doc-guardian** | PostToolUse (Write/Edit) | Tracks documentation drift; auto-updates dependent docs |
| **code-sentinel** | PreToolUse (Write/Edit) | Scans for security issues; blocks critical vulnerabilities |
| **project-hygiene** | PostToolUse (Write/Edit) | Cleans temp files, warns about misplaced files |
| **data-platform** | SessionStart | Checks PostgreSQL connection; non-blocking warning if unavailable |
| **viz-platform** | SessionStart | Checks DMC version; non-blocking warning if mismatch detected |
| **code-sentinel** | PreToolUse (Write/Edit/MultiEdit) | Scans code before writing; blocks critical security issues |
| **git-flow** | PreToolUse (Bash) | Validates branch naming and commit message conventions |
| **cmdb-assistant** | PreToolUse (MCP create/update) | Validates input data before NetBox writes |
| **clarity-assist** | UserPromptSubmit | Detects vague prompts and suggests clarification |
---
@@ -141,15 +138,15 @@ Quick reference for all commands in the Leo Claude Marketplace.
Full workflow from idea to implementation using RFCs:
```
1. /clarify # Clarify the feature idea
2. /rfc create # Create RFC from clarified spec
1. /clarity clarify # Clarify the feature idea
2. /rfc create # Create RFC from clarified spec
... refine RFC content ...
3. /rfc review 0001 # Submit RFC for review
3. /rfc review 0001 # Submit RFC for review
... review discussion ...
4. /rfc approve 0001 # Approve RFC for implementation
5. /sprint-plan # Select approved RFC for sprint
4. /rfc approve 0001 # Approve RFC for implementation
5. /sprint plan # Select approved RFC for sprint
... implement feature ...
6. /sprint-close # Complete sprint, RFC marked Implemented
6. /sprint close # Complete sprint, RFC marked Implemented
```
### Example 1: Starting a New Feature Sprint
@@ -157,17 +154,17 @@ Full workflow from idea to implementation using RFCs:
A typical workflow for planning and executing a feature sprint:
```
1. /clarify # Clarify requirements if vague
2. /sprint-plan # Plan the sprint with architecture analysis
3. /labels-sync # Ensure labels are up-to-date
4. /sprint-start # Begin execution with dependency ordering
5. /branch-start feat/... # Create feature branch
1. /clarity clarify # Clarify requirements if vague
2. /sprint plan # Plan the sprint with architecture analysis
3. /labels sync # Ensure labels are up-to-date
4. /sprint start # Begin execution with dependency ordering
5. /gitflow branch-start feat/... # Create feature branch
... implement features ...
6. /git-commit # Commit with conventional message
7. /sprint-status --diagram # Check progress with visualization
8. /pm-review # Pre-close quality review
9. /pm-test run # Verify test coverage
10. /sprint-close # Capture lessons learned
6. /gitflow commit # Commit with conventional message
7. /sprint status --diagram # Check progress with visualization
8. /sprint review # Pre-close quality review
9. /sprint test run # Verify test coverage
10. /sprint close # Capture lessons learned
```
### Example 2: Daily Development Cycle
@@ -175,12 +172,12 @@ A typical workflow for planning and executing a feature sprint:
Quick daily workflow with git-flow:
```
1. /git-status # Check current state
2. /branch-start fix/... # Start bugfix branch
1. /gitflow status # Check current state
2. /gitflow branch-start fix/... # Start bugfix branch
... make changes ...
3. /git-commit # Auto-generate commit message
4. /git-commit-push # Push to remote
5. /branch-cleanup # Clean merged branches
3. /gitflow commit # Auto-generate commit message
4. /gitflow commit --push # Commit and push to remote
5. /gitflow branch-cleanup # Clean merged branches
```
### Example 3: Pull Request Review Workflow
@@ -188,10 +185,10 @@ Quick daily workflow with git-flow:
Reviewing a PR before merge:
```
1. /pr-summary # Quick overview of changes
2. /pr-review # Full multi-agent review
3. /pr-findings # Filter findings by severity
4. /security-scan # Deep security audit if needed
1. /pr summary # Quick overview of changes
2. /pr review # Full multi-agent review
3. /pr findings # Filter findings by severity
4. /sentinel scan # Deep security audit if needed
```
### Example 4: Documentation Maintenance
@@ -199,10 +196,10 @@ Reviewing a PR before merge:
Keeping docs in sync:
```
1. /doc-audit # Scan for documentation drift
2. /doc-sync # Apply pending updates
3. /config-analyze # Check CLAUDE.md health
4. /config-optimize # Optimize if needed
1. /doc audit # Scan for documentation drift
2. /doc sync # Apply pending updates
3. /claude-config analyze # Check CLAUDE.md health
4. /claude-config optimize # Optimize if needed
```
### Example 5: Code Refactoring Session
@@ -210,11 +207,11 @@ Keeping docs in sync:
Safe refactoring with preview:
```
1. /refactor-dry # Preview opportunities
2. /security-scan # Baseline security check
3. /refactor # Apply improvements
4. /pm-test run # Verify nothing broke
5. /git-commit # Commit with descriptive message
1. /sentinel refactor-dry # Preview opportunities
2. /sentinel scan # Baseline security check
3. /sentinel refactor # Apply improvements
4. /sprint test run # Verify nothing broke
5. /gitflow commit # Commit with descriptive message
```
### Example 6: Infrastructure Documentation
@@ -222,10 +219,10 @@ Safe refactoring with preview:
Managing infrastructure with CMDB:
```
1. /cmdb-search "server" # Find existing devices
2. /cmdb-device view X # Check device details
3. /cmdb-ip list # List available IPs
4. /cmdb-site view Y # Check site info
1. /cmdb search "server" # Find existing devices
2. /cmdb device view X # Check device details
3. /cmdb ip list # List available IPs
4. /cmdb site view Y # Check site info
```
### Example 6b: Data Engineering Workflow
@@ -233,12 +230,12 @@ Managing infrastructure with CMDB:
Working with data pipelines:
```
1. /data-ingest file.csv # Load data into DataFrame
2. /data-profile # Generate data profiling report
3. /data-schema # Explore database schemas
4. /data-lineage model_name # View dbt model dependencies
5. /data-run model_name # Execute dbt models
6. /data-explain "SELECT ..." # Analyze query execution plan
1. /data ingest file.csv # Load data into DataFrame
2. /data profile # Generate data profiling report
3. /data schema # Explore database schemas
4. /data lineage model_name # View dbt model dependencies
5. /data run model_name # Execute dbt models
6. /data explain "SELECT ..." # Analyze query execution plan
```
### Example 7: First-Time Setup (New Machine)
@@ -246,13 +243,13 @@ Working with data pipelines:
Setting up the marketplace for the first time:
```
1. /pm-setup --full # Full setup: MCP + system config + project
1. /projman setup --full # Full setup: MCP + system config + project
# → Follow prompts for Gitea URL, org
# → Add token manually when prompted
# → Confirm repository name
2. # Restart Claude Code session
3. /labels-sync # Sync Gitea labels
4. /sprint-plan # Plan first sprint
3. /labels sync # Sync Gitea labels
4. /sprint plan # Plan first sprint
```
### Example 8: New Project Setup (System Already Configured)
@@ -260,22 +257,23 @@ Setting up the marketplace for the first time:
Adding a new project when system config exists:
```
1. /pm-setup --quick # Quick project setup (auto-detected)
1. /projman setup --quick # Quick project setup (auto-detected)
# → Confirms detected repo name
# → Creates .env
2. /labels-sync # Sync Gitea labels
3. /sprint-plan # Plan first sprint
2. /labels sync # Sync Gitea labels
3. /sprint plan # Plan first sprint
```
---
## Quick Tips
- **Hooks run automatically** - doc-guardian and code-sentinel protect you without manual invocation
- **Use `/git-commit` over `git commit`** - generates better commit messages following conventions
- **Run `/pm-review` before `/sprint-close`** - catches issues before closing the sprint
- **Use `/clarify` for vague requests** - especially helpful for complex requirements
- **`/refactor-dry` is safe** - always preview before applying refactoring changes
- **Hooks run automatically** - code-sentinel and git-flow protect you without manual invocation
- **Use `/gitflow commit` over `git commit`** - generates better commit messages following conventions
- **Run `/sprint review` before `/sprint close`** - catches issues before closing the sprint
- **Use `/clarity clarify` for vague requests** - especially helpful for complex requirements
- **`/sentinel refactor-dry` is safe** - always preview before applying refactoring changes
- **`/gitflow commit --push`** replaces the old `/git-commit-push` - fewer commands to remember
---
@@ -296,4 +294,4 @@ Ensure credentials are configured in `~/.config/claude/gitea.env`, `~/.config/cl
---
*Last Updated: 2026-02-02*
*Last Updated: 2026-02-06*

View File

@@ -9,7 +9,7 @@ Centralized configuration documentation for all plugins and MCP servers in the L
**After installing the marketplace and plugins via Claude Code:**
```
/pm-setup
/projman setup
```
The interactive wizard auto-detects what's needed and handles everything except manually adding your API tokens.
@@ -25,8 +25,8 @@ The interactive wizard auto-detects what's needed and handles everything except
└─────────────────────────────────────────────────────────────────────────────┘
/pm-setup --full
(or /pm-setup auto-detects)
/projman setup --full
(or /projman setup auto-detects)
┌──────────────────────────────┼──────────────────────────────┐
▼ ▼ ▼
@@ -79,7 +79,7 @@ The interactive wizard auto-detects what's needed and handles everything except
┌───────────────┴───────────────┐
▼ ▼
/pm-setup --quick /pm-setup
/projman setup --quick /projman setup
(explicit mode) (auto-detects mode)
│ │
│ ┌──────────┴──────────┐
@@ -109,7 +109,7 @@ The interactive wizard auto-detects what's needed and handles everything except
## What Runs Automatically vs User Interaction
### `/pm-setup --full` - Full Setup
### `/projman setup --full` - Full Setup
| Phase | Type | What Happens |
|-------|------|--------------|
@@ -121,7 +121,7 @@ The interactive wizard auto-detects what's needed and handles everything except
| **6. Project Config** | Automated | Creates `.env` file, checks `.gitignore` |
| **7. Validation** | Automated | Tests API connectivity, shows summary |
### `/pm-setup --quick` - Quick Project Setup
### `/projman setup --quick` - Quick Project Setup
| Phase | Type | What Happens |
|-------|------|--------------|
@@ -136,10 +136,10 @@ The interactive wizard auto-detects what's needed and handles everything except
| Mode | When to Use | What It Does |
|------|-------------|--------------|
| `/pm-setup` | Any time | Auto-detects: runs full, quick, or sync as needed |
| `/pm-setup --full` | First time on a machine | Full setup: MCP server + system config + project config |
| `/pm-setup --quick` | Starting a new project | Quick setup: project config only (assumes system is ready) |
| `/pm-setup --sync` | After repo move/rename | Updates .env to match current git remote |
| `/projman setup` | Any time | Auto-detects: runs full, quick, or sync as needed |
| `/projman setup --full` | First time on a machine | Full setup: MCP server + system config + project config |
| `/projman setup --quick` | Starting a new project | Quick setup: project config only (assumes system is ready) |
| `/projman setup --sync` | After repo move/rename | Updates .env to match current git remote |
**Auto-detection logic:**
1. No system config → **full** mode
@@ -148,9 +148,9 @@ The interactive wizard auto-detects what's needed and handles everything except
4. Both exist, match → already configured, offer to reconfigure
**Typical workflow:**
1. Install plugin → run `/pm-setup` (auto-runs full mode)
2. Start new project → run `/pm-setup` (auto-runs quick mode)
3. Repository moved? → run `/pm-setup` (auto-runs sync mode)
1. Install plugin → run `/projman setup` (auto-runs full mode)
2. Start new project → run `/projman setup` (auto-runs quick mode)
3. Repository moved? → run `/projman setup` (auto-runs sync mode)
---
@@ -182,7 +182,7 @@ This marketplace uses a **hybrid configuration** approach:
**Benefits:**
- Single token per service (update once, use everywhere)
- Easy multi-project setup (just run `/pm-setup` in each project)
- Easy multi-project setup (just run `/projman setup` in each project)
- Security (tokens never committed to git, never typed into AI chat)
- Project isolation (each project can override defaults)
@@ -190,7 +190,7 @@ This marketplace uses a **hybrid configuration** approach:
## Prerequisites
Before running `/pm-setup`:
Before running `/projman setup`:
1. **Python 3.10+** installed
```bash
@@ -213,7 +213,7 @@ Before running `/pm-setup`:
Run the setup wizard in Claude Code:
```
/pm-setup
/projman setup
```
The wizard will guide you through each step interactively and auto-detect the appropriate mode.
@@ -387,18 +387,18 @@ PR_REVIEW_AUTO_SUBMIT=false
| Plugin | System Config | Project Config | Setup Command |
|--------|---------------|----------------|---------------|
| **projman** | gitea.env | .env (GITEA_REPO=owner/repo) | `/pm-setup` |
| **pr-review** | gitea.env | .env (GITEA_REPO=owner/repo) | `/pr-setup` |
| **projman** | gitea.env | .env (GITEA_REPO=owner/repo) | `/projman setup` |
| **pr-review** | gitea.env | .env (GITEA_REPO=owner/repo) | `/pr setup` |
| **git-flow** | git-flow.env (optional) | .env (optional) | None needed |
| **clarity-assist** | None | None | None needed |
| **cmdb-assistant** | netbox.env | None | `/cmdb-setup` |
| **data-platform** | postgres.env | .env (optional) | `/data-setup` |
| **viz-platform** | None | .env (optional DMC_VERSION) | `/viz-setup` |
| **cmdb-assistant** | netbox.env | None | `/cmdb setup` |
| **data-platform** | postgres.env | .env (optional) | `/data setup` |
| **viz-platform** | None | .env (optional DMC_VERSION) | `/viz setup` |
| **doc-guardian** | None | None | None needed |
| **code-sentinel** | None | None | None needed |
| **project-hygiene** | None | None | None needed |
| **claude-config-maintainer** | None | None | None needed |
| **contract-validator** | None | None | `/cv-setup` |
| **contract-validator** | None | None | `/cv setup` |
---
@@ -408,7 +408,7 @@ Once system-level config is set up, adding new projects is simple:
```
cd ~/projects/new-project
/pm-setup
/projman setup
```
The command auto-detects that system config exists and runs quick project setup.
@@ -485,7 +485,7 @@ Not all plugins have MCP servers. The install script handles this automatically:
| projman | ✓ (via gitea) | Issue, wiki, PR tools |
| pr-review | ✓ (via gitea) | PR review tools |
| git-flow | ✗ | Commands only |
| doc-guardian | ✗ | Commands and hooks only |
| doc-guardian | ✗ | Commands only |
| code-sentinel | ✗ | Commands and hooks only |
| clarity-assist | ✗ | Commands only |
@@ -631,7 +631,7 @@ For agents with 8+ skills, use **phase-based loading** in the agent body text. T
### API Validation
When running `/pm-setup`, the command:
When running `/projman setup`, the command:
1. **Detects** organization and repository from git remote URL
2. **Validates** via Gitea API: `GET /api/v1/repos/{org}/{repo}`
@@ -646,7 +646,7 @@ When you start a Claude Code session, a hook automatically:
1. Reads `GITEA_REPO` (in `owner/repo` format) from `.env`
2. Compares with current `git remote get-url origin`
3. **Warns** if mismatch detected: "Repository location mismatch. Run `/pm-setup --sync` to update."
3. **Warns** if mismatch detected: "Repository location mismatch. Run `/projman setup --sync` to update."
This helps when you:
- Move a repository to a different organization
@@ -668,7 +668,7 @@ curl -H "Authorization: token $GITEA_API_TOKEN" "$GITEA_API_URL/user"
In Claude Code, after restarting your session:
```
/labels-sync
/labels sync
```
If this works, your setup is complete.
@@ -741,7 +741,7 @@ cat .env
3. **Never type tokens into AI chat**
- Always edit config files directly in your editor
- The `/pm-setup` wizard respects this
- The `/projman setup` wizard respects this
4. **Rotate tokens periodically**
- Every 6-12 months

View File

@@ -279,8 +279,8 @@ Error: Could not find a suitable TLS CA certificate bundle, invalid path:
Use these commands for automated checking:
- `/pm-debug report` - Run full diagnostics, create issue if problems found
- `/pm-debug review` - Investigate existing diagnostic issues and propose fixes
- `/cv status` - Marketplace-wide health check (installation, MCP, configuration)
- `/hygiene check` - Project file organization and cleanup check
---

215
docs/MIGRATION-v9.md Normal file
View File

@@ -0,0 +1,215 @@
# Migration Guide: v8.x → v9.0.0
## Overview
v9.0.0 standardizes all commands to the `/<noun> <action>` sub-command pattern. Every command in the marketplace now follows this convention.
**Breaking change:** All old command names are removed. Update your workflows, scripts, and CLAUDE.md references.
---
## Complete Command Mapping
### projman
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/sprint-plan` | `/sprint plan` | |
| `/sprint-start` | `/sprint start` | |
| `/sprint-status` | `/sprint status` | |
| `/sprint-close` | `/sprint close` | |
| `/pm-review` | `/sprint review` | Moved under `/sprint` |
| `/pm-test` | `/sprint test` | Moved under `/sprint` |
| `/pm-setup` | `/projman setup` | Moved under `/projman` |
| `/pm-debug` | **Removed** | Deleted in v8.1.0 — migrated to `debug-mcp` plugin (Decision #11) |
| `/labels-sync` | `/labels sync` | |
| `/suggest-version` | **Removed** | Deleted in v8.1.0 — migrated to `ops-release-manager` plugin (Decision #18) |
| `/proposal-status` | **Removed** | Deleted in v8.1.0 — absorbed into `/project status` (Decision #19) |
| `/rfc <sub>` | `/rfc <sub>` | Unchanged |
| `/project <sub>` | `/project <sub>` | Unchanged |
| `/adr <sub>` | `/adr <sub>` | Unchanged |
### git-flow
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/git-commit` | `/gitflow commit` | |
| `/git-commit-push` | `/gitflow commit --push` | **Consolidated** into flag |
| `/git-commit-merge` | `/gitflow commit --merge` | **Consolidated** into flag |
| `/git-commit-sync` | `/gitflow commit --sync` | **Consolidated** into flag |
| `/branch-start` | `/gitflow branch-start` | |
| `/branch-cleanup` | `/gitflow branch-cleanup` | |
| `/git-status` | `/gitflow status` | |
| `/git-config` | `/gitflow config` | |
**Note:** The three commit variants (`-push`, `-merge`, `-sync`) are now flags on `/gitflow commit`. This reduces 8 commands to 5.
### pr-review
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/pr-review` | `/pr review` | |
| `/pr-summary` | `/pr summary` | |
| `/pr-findings` | `/pr findings` | |
| `/pr-diff` | `/pr diff` | |
| `/pr-setup` | `/pr setup` | |
| `/project-init` | `/pr init` | Renamed |
| `/project-sync` | `/pr sync` | Renamed |
### clarity-assist
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/clarify` | `/clarity clarify` | |
| `/quick-clarify` | `/clarity quick-clarify` | |
### doc-guardian
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/doc-audit` | `/doc audit` | |
| `/doc-sync` | `/doc sync` | |
| `/changelog-gen` | `/doc changelog-gen` | Moved under `/doc` |
| `/doc-coverage` | `/doc coverage` | |
| `/stale-docs` | `/doc stale-docs` | Moved under `/doc` |
### code-sentinel
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/security-scan` | `/sentinel scan` | |
| `/refactor` | `/sentinel refactor` | |
| `/refactor-dry` | `/sentinel refactor-dry` | |
### claude-config-maintainer
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/config-analyze` (or `/analyze`) | `/claude-config analyze` | |
| `/config-optimize` (or `/optimize`) | `/claude-config optimize` | |
| `/config-init` (or `/init`) | `/claude-config init` | |
| `/config-diff` | `/claude-config diff` | |
| `/config-lint` | `/claude-config lint` | |
| `/config-audit-settings` | `/claude-config audit-settings` | |
| `/config-optimize-settings` | `/claude-config optimize-settings` | |
| `/config-permissions-map` | `/claude-config permissions-map` | |
### contract-validator
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/validate-contracts` | `/cv validate` | |
| `/check-agent` | `/cv check-agent` | |
| `/list-interfaces` | `/cv list-interfaces` | |
| `/dependency-graph` | `/cv dependency-graph` | |
| `/cv-setup` | `/cv setup` | |
| `/cv status` | `/cv status` | Unchanged |
### cmdb-assistant
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/cmdb-setup` | `/cmdb setup` | |
| `/cmdb-search` | `/cmdb search` | |
| `/cmdb-device` | `/cmdb device` | |
| `/cmdb-ip` | `/cmdb ip` | |
| `/cmdb-site` | `/cmdb site` | |
| `/cmdb-audit` | `/cmdb audit` | |
| `/cmdb-register` | `/cmdb register` | |
| `/cmdb-sync` | `/cmdb sync` | |
| `/cmdb-topology` | `/cmdb topology` | |
| `/change-audit` | `/cmdb change-audit` | Moved under `/cmdb` |
| `/ip-conflicts` | `/cmdb ip-conflicts` | Moved under `/cmdb` |
### data-platform
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/data-ingest` | `/data ingest` | |
| `/data-profile` | `/data profile` | |
| `/data-schema` | `/data schema` | |
| `/data-explain` | `/data explain` | |
| `/data-lineage` | `/data lineage` | |
| `/data-run` | `/data run` | |
| `/lineage-viz` | `/data lineage-viz` | Moved under `/data` |
| `/dbt-test` | `/data dbt-test` | Moved under `/data` |
| `/data-quality` | `/data quality` | |
| `/data-review` | `/data review` | |
| `/data-gate` | `/data gate` | |
| `/data-setup` | `/data setup` | |
### viz-platform
| Old (v8.x) | New (v9.0.0) | Notes |
|-------------|--------------|-------|
| `/viz-setup` | `/viz setup` | |
| `/viz-chart` | `/viz chart` | |
| `/viz-chart-export` | `/viz chart-export` | |
| `/viz-dashboard` | `/viz dashboard` | |
| `/viz-theme` | `/viz theme` | |
| `/viz-theme-new` | `/viz theme-new` | |
| `/viz-theme-css` | `/viz theme-css` | |
| `/viz-component` | `/viz component` | |
| `/accessibility-check` | `/viz accessibility-check` | Moved under `/viz` |
| `/viz-breakpoints` | `/viz breakpoints` | |
| `/design-review` | `/viz design-review` | Moved under `/viz` |
| `/design-gate` | `/viz design-gate` | Moved under `/viz` |
### project-hygiene
No changes — already used `/<noun> <action>` pattern.
| Command | Status |
|---------|--------|
| `/hygiene check` | Unchanged |
---
## Verifying Plugin Installation (v9.0.0)
Test commands use the new format:
| Plugin | Test Command |
|--------|--------------|
| git-flow | `/git-flow:gitflow-status` |
| projman | `/projman:sprint-status` |
| pr-review | `/pr-review:pr-summary` |
| clarity-assist | `/clarity-assist:clarity-clarify` |
| doc-guardian | `/doc-guardian:doc-audit` |
| code-sentinel | `/code-sentinel:sentinel-scan` |
| claude-config-maintainer | `/claude-config-maintainer:claude-config-analyze` |
| cmdb-assistant | `/cmdb-assistant:cmdb-search` |
| data-platform | `/data-platform:data-ingest` |
| viz-platform | `/viz-platform:viz-chart` |
| contract-validator | `/contract-validator:cv-validate` |
---
## CLAUDE.md Updates
If your project's CLAUDE.md references old command names, update them:
**Find old references:**
```bash
grep -rn '/sprint-plan\|/pm-setup\|/git-commit\|/pr-review\|/security-scan\|/config-analyze\|/validate-contracts\|/cmdb-search\|/data-ingest\|/viz-chart\b\|/clarify\b\|/doc-audit' CLAUDE.md
```
**Key patterns to search and replace:**
- `/sprint-plan``/sprint plan`
- `/pm-setup``/projman setup`
- `/pm-review``/sprint review`
- `/git-commit``/gitflow commit`
- `/pr-review``/pr review`
- `/security-scan``/sentinel scan`
- `/refactor``/sentinel refactor`
- `/config-analyze``/claude-config analyze`
- `/validate-contracts``/cv validate`
- `/clarify``/clarity clarify`
- `/doc-audit``/doc audit`
- `/cmdb-search``/cmdb search`
- `/data-ingest``/data ingest`
- `/viz-chart``/viz chart`
---
*Last Updated: 2026-02-06*

View File

@@ -48,7 +48,7 @@ cd ~/.claude/plugins/marketplaces/leo-claude-mktplace && ./scripts/setup.sh
### When to Re-run Setup
You typically **don't need** to re-run setup after updates. However, re-run your plugin's setup command (e.g., `/pm-setup`, `/pr-setup`, `/cmdb-setup`) if:
You typically **don't need** to re-run setup after updates. However, re-run your plugin's setup command (e.g., `/projman setup`, `/pr setup`, `/cmdb setup`) if:
- Changelog mentions **new required environment variables**
- Changelog mentions **breaking changes** to configuration
@@ -59,7 +59,7 @@ You typically **don't need** to re-run setup after updates. However, re-run your
If an update requires new project-level configuration:
```
/project-init
/pr init
```
This will detect existing settings and only add what's missing.
@@ -98,8 +98,8 @@ When updating, review if changes affect the setup workflow:
1. **Check for setup command changes:**
```bash
git diff HEAD~1 plugins/*/commands/*-setup.md
git diff HEAD~1 plugins/*/commands/project-init.md
git diff HEAD~1 plugins/*/commands/project-sync.md
git diff HEAD~1 plugins/*/commands/pr-init.md
git diff HEAD~1 plugins/*/commands/pr-sync.md
```
2. **Check for hook changes:**
@@ -114,7 +114,7 @@ When updating, review if changes affect the setup workflow:
**If setup commands changed:**
- Review what's new (new validation steps, new prompts, etc.)
- Consider re-running your plugin's setup command or `/project-init` to benefit from improvements
- Consider re-running your plugin's setup command or `/pr init` to benefit from improvements
- Existing configurations remain valid unless changelog notes breaking changes
**If hooks changed:**
@@ -123,7 +123,7 @@ When updating, review if changes affect the setup workflow:
**If configuration structure changed:**
- Check if new variables are required
- Run `/project-sync` if repository detection logic improved
- Run `/pr sync` if repository detection logic improved
---
@@ -142,7 +142,7 @@ deactivate
### Configuration no longer works
1. Check CHANGELOG.md for breaking changes
2. Run your plugin's setup command (e.g., `/pm-setup`) to re-validate and fix configuration
2. Run your plugin's setup command (e.g., `/projman setup`) to re-validate and fix configuration
3. Compare your config files with documentation in `docs/CONFIGURATION.md`
### MCP server won't start after update

View File

@@ -27,7 +27,7 @@
| ID | Label | Type | Lane | Sequence |
|----|-------|------|------|----------|
| p1-start | /sprint-plan | rounded-rect | user-lane | 1 |
| p1-start | /sprint plan | rounded-rect | user-lane | 1 |
| p1-activate | Planner Activates | rectangle | planner-lane | 2 |
| p1-search-lessons | Search Lessons Learned | rectangle | planner-lane | 3 |
| p1-gitea-wiki-query | Query Past Lessons (Wiki) | rectangle | gitea-lane | 4 |
@@ -61,7 +61,7 @@
| ID | Label | Type | Lane | Sequence |
|----|-------|------|------|----------|
| p2-start | /sprint-start | rounded-rect | user-lane | 11 |
| p2-start | /sprint start | rounded-rect | user-lane | 11 |
| p2-orch-activate | Orchestrator Activates | rectangle | orchestrator-lane | 12 |
| p2-fetch-issues | Fetch Sprint Issues | rectangle | orchestrator-lane | 13 |
| p2-gitea-list | List Open Issues | rectangle | gitea-lane | 14 |
@@ -128,7 +128,7 @@
| ID | Label | Type | Lane | Sequence |
|----|-------|------|------|----------|
| p3-start | /sprint-close | rounded-rect | user-lane | 31 |
| p3-start | /sprint close | rounded-rect | user-lane | 31 |
| p3-orch-activate | Orchestrator Activates | rectangle | orchestrator-lane | 32 |
| p3-review | Review Sprint | rectangle | orchestrator-lane | 33 |
| p3-gitea-status | Get Final Status | rectangle | gitea-lane | 34 |

70
docs/designs/data-seed.md Normal file
View File

@@ -0,0 +1,70 @@
# Design: data-seed
**Domain:** `data`
**Target Version:** v9.3.0
## Purpose
Test data generation and database seeding. Generates realistic fake data based on schema definitions, supports reproducible seeds, and manages seed files for development and testing environments.
## Target Users
- Developers needing test data for local development
- QA teams requiring reproducible datasets
- Projects with complex relational data models
## Commands
| Command | Description |
|---------|-------------|
| `/seed setup` | Setup wizard — detect schema source, configure output paths |
| `/seed generate` | Generate seed data from schema or model definitions |
| `/seed apply` | Apply seed data to database or create fixture files |
| `/seed profile` | Define reusable data profiles (small, medium, large, edge-cases) |
| `/seed validate` | Validate seed data against schema constraints and foreign keys |
## Agent Architecture
| Agent | Model | Mode | Role |
|-------|-------|------|------|
| `seed-generator` | sonnet | acceptEdits | Data generation, profile management |
| `seed-validator` | haiku | plan | Read-only validation of seed data integrity |
## Skills
| Skill | Purpose |
|-------|---------|
| `schema-inference` | Infer data types and constraints from models/migrations |
| `faker-patterns` | Realistic data generation patterns (names, emails, addresses, etc.) |
| `relationship-resolution` | Foreign key and relationship-aware data generation |
| `profile-management` | Seed profile definitions and sizing |
| `visual-header` | Standard command output headers |
## MCP Server
**Not required.** Seed data is generated as files (JSON, SQL, CSV). Database insertion is handled by the application's own tooling.
## Integration Points
| Plugin | Integration |
|--------|-------------|
| saas-db-migrate | Schema models used as seed generation input |
| data-platform | Generated data can be loaded via `/data ingest` |
| saas-test-pilot | Seed data used in integration test fixtures |
| projman | Issue labels: `Component/Data`, `Tech/Faker` |
## Token Budget
| Component | Estimated Tokens |
|-----------|-----------------|
| `claude-md-integration.md` | ~500 |
| Dispatch file (`seed.md`) | ~200 |
| 5 commands (avg) | ~3,000 |
| 2 agents | ~1,000 |
| 5 skills | ~2,000 |
| **Total** | **~6,700** |
## Open Questions
- Should we support database-specific seed formats (pg_dump, mysqldump)?
- Integration with Faker library or custom generation?

70
docs/designs/debug-mcp.md Normal file
View File

@@ -0,0 +1,70 @@
# Design: debug-mcp
**Domain:** `debug`
**Target Version:** v9.8.0
## Purpose
MCP server debugging and development toolkit. Provides tools for inspecting MCP server health, testing tool calls, viewing server logs, and developing new MCP servers. Essential for marketplace developers building or troubleshooting MCP integrations.
## Target Users
- Plugin developers building MCP servers
- Users troubleshooting MCP connectivity issues
- Marketplace maintainers validating MCP configurations
## Commands
| Command | Description |
|---------|-------------|
| `/debug-mcp status` | Show all MCP servers: running/failed, tool count, last error |
| `/debug-mcp test` | Test a specific MCP tool call with sample input |
| `/debug-mcp logs` | View recent MCP server stderr/stdout logs |
| `/debug-mcp inspect` | Inspect MCP server config (.mcp.json entry, venv, dependencies) |
| `/debug-mcp scaffold` | Generate MCP server skeleton (Python, stdio transport) |
## Agent Architecture
| Agent | Model | Mode | Role |
|-------|-------|------|------|
| `mcp-debugger` | sonnet | default | Server inspection, log analysis, scaffold generation |
Single agent is sufficient — this plugin is primarily diagnostic with one generative command.
## Skills
| Skill | Purpose |
|-------|---------|
| `mcp-protocol` | MCP stdio protocol, tool/resource/prompt schemas |
| `server-patterns` | Python MCP server patterns (FastMCP, raw protocol) |
| `venv-diagnostics` | Virtual environment health checks, dependency validation |
| `log-analysis` | MCP server error pattern recognition |
| `visual-header` | Standard command output headers |
## MCP Server
**Not required.** This plugin inspects other MCP servers via file system (reading .mcp.json, checking venvs, reading logs). It does not need its own MCP server.
## Integration Points
| Plugin | Integration |
|--------|-------------|
| contract-validator | `/cv status` delegates to debug-mcp for detailed MCP diagnostics |
| projman | `/projman setup` can invoke `/debug-mcp status` for post-setup verification |
| All plugins with MCP | Debug-mcp can diagnose any MCP server in the marketplace |
## Token Budget
| Component | Estimated Tokens |
|-----------|-----------------|
| `claude-md-integration.md` | ~500 |
| Dispatch file (`debug-mcp.md`) | ~200 |
| 5 commands (avg) | ~3,000 |
| 1 agent | ~600 |
| 5 skills | ~2,000 |
| **Total** | **~6,300** |
## Open Questions
- Should this plugin have a hook that auto-runs on MCP failure (SessionStart)?
- Should `/debug-mcp scaffold` generate both Python and TypeScript templates?

View File

@@ -0,0 +1,72 @@
# Design: ops-deploy-pipeline
**Domain:** `ops`
**Target Version:** v9.7.0
## Purpose
CI/CD deployment pipeline management for Docker Compose and systemd-based services. Generates deployment configurations, validates pipeline definitions, and manages environment-specific settings. Tailored for self-hosted infrastructure (not cloud-native).
## Target Users
- Self-hosted service operators (Raspberry Pi, VPS, bare-metal)
- Teams deploying via Docker Compose
- Projects needing environment-specific configuration management
## Commands
| Command | Description |
|---------|-------------|
| `/deploy setup` | Setup wizard — detect deployment method, configure targets |
| `/deploy generate` | Generate docker-compose.yml, Caddyfile entries, systemd units |
| `/deploy validate` | Validate deployment configs (ports, volumes, networks, env vars) |
| `/deploy env` | Manage environment-specific config files (.env.production, etc.) |
| `/deploy check` | Pre-deployment health check (disk, memory, port conflicts) |
| `/deploy rollback` | Generate rollback plan for a deployment |
## Agent Architecture
| Agent | Model | Mode | Role |
|-------|-------|------|------|
| `deploy-planner` | sonnet | default | Configuration generation, rollback planning |
| `deploy-validator` | haiku | plan | Read-only validation of configs and pre-flight checks |
## Skills
| Skill | Purpose |
|-------|---------|
| `compose-patterns` | Docker Compose best practices, multi-service patterns |
| `caddy-conventions` | Caddyfile reverse proxy patterns, subdomain routing |
| `env-management` | Environment variable management across environments |
| `health-checks` | Pre-deployment system health validation |
| `rollback-patterns` | Deployment rollback strategies |
| `visual-header` | Standard command output headers |
## MCP Server
**Not required initially.** Could add SSH-based remote execution MCP server in the future for remote deployment.
## Integration Points
| Plugin | Integration |
|--------|-------------|
| cmdb-assistant | Deployment targets pulled from NetBox device inventory |
| ops-release-manager | Release tags trigger deployment preparation |
| projman | Issue labels: `Component/Infra`, `Tech/Docker`, `Tech/Caddy` |
| code-sentinel | Security scan of deployment configs (exposed ports, secrets in env) |
## Token Budget
| Component | Estimated Tokens |
|-----------|-----------------|
| `claude-md-integration.md` | ~700 |
| Dispatch file (`deploy.md`) | ~200 |
| 6 commands (avg) | ~3,600 |
| 2 agents | ~1,200 |
| 6 skills | ~2,500 |
| **Total** | **~8,200** |
## Open Questions
- Should this support Kubernetes/Helm for users who need it?
- SSH-based remote execution via MCP server for actual deployments?

View File

@@ -0,0 +1,71 @@
# Design: ops-release-manager
**Domain:** `ops`
**Target Version:** v9.6.0
## Purpose
Release management automation including semantic versioning, changelog generation, release branch creation, and tag management. Coordinates the release process across git, changelogs, and package manifests.
## Target Users
- Project maintainers managing releases
- Teams following SemVer and conventional commits
- Projects with multiple version locations to keep in sync
## Commands
| Command | Description |
|---------|-------------|
| `/release setup` | Setup wizard — detect version locations, configure release flow |
| `/release prepare` | Prepare release: bump versions, update changelog, create branch |
| `/release validate` | Pre-release checks (clean tree, tests pass, changelog has content) |
| `/release tag` | Create and push git tag with release notes |
| `/release rollback` | Revert a release (delete tag, revert version bump commit) |
| `/release status` | Show current version, unreleased changes, next version suggestion |
## Agent Architecture
| Agent | Model | Mode | Role |
|-------|-------|------|------|
| `release-coordinator` | sonnet | acceptEdits | Version bumping, changelog updates, branch/tag creation |
| `release-validator` | haiku | plan | Pre-release validation, dependency checks |
## Skills
| Skill | Purpose |
|-------|---------|
| `version-detection` | Find version locations (package.json, pyproject.toml, marketplace.json, etc.) |
| `semver-rules` | SemVer bump logic based on conventional commits |
| `changelog-conventions` | Keep a Changelog format, unreleased section management |
| `release-workflow` | Branch-based vs tag-based release patterns |
| `visual-header` | Standard command output headers |
## MCP Server
**Not required.** All operations are git and file-based.
## Integration Points
| Plugin | Integration |
|--------|-------------|
| git-flow | `/release prepare` uses gitflow conventions for branch creation |
| doc-guardian | `/release validate` checks documentation is up to date |
| projman | Sprint close can trigger `/release prepare` for sprint-based releases |
| ops-deploy-pipeline | Release tags trigger deployment pipeline |
## Token Budget
| Component | Estimated Tokens |
|-----------|-----------------|
| `claude-md-integration.md` | ~600 |
| Dispatch file (`release.md`) | ~200 |
| 6 commands (avg) | ~3,600 |
| 2 agents | ~1,200 |
| 5 skills | ~2,000 |
| **Total** | **~7,600** |
## Open Questions
- Should this subsume the existing `release.sh` script in this repo?
- Support for GitHub Releases / Gitea Releases API via MCP?

View File

@@ -0,0 +1,71 @@
# Design: saas-api-platform
**Domain:** `saas`
**Target Version:** v9.1.0
## Purpose
Provides scaffolding, validation, and development workflow tools for REST and GraphQL API backends. Supports FastAPI (Python) and Express (Node.js) with OpenAPI spec generation, route validation, and middleware management.
## Target Users
- Backend developers building API services
- Teams using FastAPI or Express frameworks
- Projects requiring OpenAPI/Swagger documentation
## Commands
| Command | Description |
|---------|-------------|
| `/api setup` | Setup wizard — detect framework, configure MCP server |
| `/api scaffold` | Generate API routes, models, schemas from spec or description |
| `/api validate` | Validate routes against OpenAPI spec, check missing endpoints |
| `/api docs` | Generate/update OpenAPI spec from code annotations |
| `/api test-routes` | Generate request/response test cases for API endpoints |
| `/api middleware` | Add/configure middleware (auth, CORS, rate-limiting, logging) |
## Agent Architecture
| Agent | Model | Mode | Role |
|-------|-------|------|------|
| `api-architect` | sonnet | default | Route design, schema generation, middleware planning |
| `api-validator` | haiku | plan | Read-only validation of routes against spec |
## Skills
| Skill | Purpose |
|-------|---------|
| `framework-detection` | Detect FastAPI vs Express, identify project structure |
| `openapi-conventions` | OpenAPI 3.x spec generation rules and patterns |
| `route-patterns` | RESTful route naming, versioning, pagination conventions |
| `middleware-catalog` | Common middleware patterns per framework |
| `visual-header` | Standard command output headers |
## MCP Server
**Not required.** All operations are file-based (reading/writing code and specs). No external API needed.
## Integration Points
| Plugin | Integration |
|--------|-------------|
| projman | Issue labels: `Component/API`, `Tech/FastAPI`, `Tech/Express` |
| code-sentinel | PreToolUse hook scans generated routes for security issues |
| saas-test-pilot | `/api test-routes` generates stubs consumable by test-pilot |
| saas-db-migrate | Schema models shared between API models and migrations |
## Token Budget
| Component | Estimated Tokens |
|-----------|-----------------|
| `claude-md-integration.md` | ~800 |
| Dispatch file (`api.md`) | ~200 |
| 6 commands (avg) | ~3,600 |
| 2 agents | ~1,200 |
| 5 skills | ~2,500 |
| **Total** | **~8,300** |
## Open Questions
- Should MCP server be added later for live API testing (curl-like requests)?
- Support for gRPC/tRPC in addition to REST/GraphQL?

View File

@@ -0,0 +1,71 @@
# Design: saas-db-migrate
**Domain:** `saas`
**Target Version:** v9.2.0
## Purpose
Database migration management for SQL databases. Supports Alembic (Python/SQLAlchemy), Prisma (Node.js), and raw SQL migrations. Provides migration generation, validation, rollback planning, and drift detection.
## Target Users
- Backend developers managing database schemas
- Teams using SQLAlchemy/Alembic or Prisma
- Projects needing migration safety checks before deployment
## Commands
| Command | Description |
|---------|-------------|
| `/db-migrate setup` | Setup wizard — detect ORM/migration tool, configure paths |
| `/db-migrate generate` | Generate migration from model diff or description |
| `/db-migrate validate` | Check migration safety (destructive ops, data loss risk, locking) |
| `/db-migrate plan` | Show migration execution plan with rollback strategy |
| `/db-migrate history` | Display migration history and current state |
| `/db-migrate rollback` | Generate rollback migration for a given migration |
## Agent Architecture
| Agent | Model | Mode | Role |
|-------|-------|------|------|
| `migration-planner` | sonnet | default | Migration generation, rollback planning |
| `migration-auditor` | haiku | plan | Read-only safety validation (destructive op detection) |
## Skills
| Skill | Purpose |
|-------|---------|
| `orm-detection` | Detect Alembic vs Prisma vs raw SQL, identify config |
| `migration-safety` | Rules for detecting destructive operations (DROP, ALTER, data loss) |
| `rollback-patterns` | Standard rollback generation patterns per tool |
| `naming-conventions` | Migration file naming and ordering conventions |
| `visual-header` | Standard command output headers |
## MCP Server
**Not required.** Migrations are file-based. Database connectivity is handled by the ORM tool itself, not by Claude.
## Integration Points
| Plugin | Integration |
|--------|-------------|
| projman | Issue labels: `Component/Database`, `Tech/SQLAlchemy`, `Tech/Prisma` |
| saas-api-platform | Schema models shared between API and migration layers |
| code-sentinel | Migration validation as part of security scan |
| data-platform | PostgreSQL tools can inspect live schema for drift detection |
## Token Budget
| Component | Estimated Tokens |
|-----------|-----------------|
| `claude-md-integration.md` | ~600 |
| Dispatch file (`db-migrate.md`) | ~200 |
| 6 commands (avg) | ~3,600 |
| 2 agents | ~1,200 |
| 5 skills | ~2,000 |
| **Total** | **~7,600** |
## Open Questions
- Should this integrate with data-platform's PostgreSQL MCP server for live schema comparison?
- Support for NoSQL migration tools (Mongoose, etc.)?

View File

@@ -0,0 +1,73 @@
# Design: saas-react-platform
**Domain:** `saas`
**Target Version:** v9.4.0
## Purpose
React frontend development toolkit with component scaffolding, routing setup, state management patterns, and build configuration. Supports Next.js and Vite-based React projects with TypeScript.
## Target Users
- Frontend developers building React applications
- Teams using Next.js or Vite + React
- Projects needing consistent component architecture
## Commands
| Command | Description |
|---------|-------------|
| `/react setup` | Setup wizard — detect framework (Next.js/Vite), configure paths |
| `/react component` | Scaffold React component with props, types, tests, stories |
| `/react route` | Add route with page component, loader, and error boundary |
| `/react state` | Set up state management pattern (Context, Zustand, Redux Toolkit) |
| `/react hook` | Generate custom hook with TypeScript types and tests |
| `/react lint` | Validate component tree, check prop drilling, detect anti-patterns |
## Agent Architecture
| Agent | Model | Mode | Role |
|-------|-------|------|------|
| `react-architect` | sonnet | default | Component design, routing, state management |
| `react-auditor` | haiku | plan | Read-only lint and anti-pattern detection |
## Skills
| Skill | Purpose |
|-------|---------|
| `framework-detection` | Detect Next.js vs Vite, App Router vs Pages Router |
| `component-patterns` | Standard component structure, naming, file organization |
| `state-patterns` | State management patterns and when to use each |
| `routing-conventions` | Route naming, dynamic routes, middleware patterns |
| `typescript-patterns` | TypeScript utility types, generics, prop typing |
| `visual-header` | Standard command output headers |
## MCP Server
**Not required.** All operations are file-based (component generation, route configuration).
## Integration Points
| Plugin | Integration |
|--------|-------------|
| projman | Issue labels: `Component/Frontend`, `Tech/React`, `Tech/Next.js` |
| viz-platform | DMC components integrate with React component architecture |
| saas-api-platform | API client generation from OpenAPI spec |
| saas-test-pilot | Component test generation via `/react component` |
| code-sentinel | Security scan for XSS, unsafe HTML, client-side secrets |
## Token Budget
| Component | Estimated Tokens |
|-----------|-----------------|
| `claude-md-integration.md` | ~800 |
| Dispatch file (`react.md`) | ~200 |
| 6 commands (avg) | ~3,600 |
| 2 agents | ~1,200 |
| 6 skills | ~3,000 |
| **Total** | **~8,800** |
## Open Questions
- Should we support Vue.js/Svelte as alternative frameworks?
- Integration with Storybook for component documentation?

View File

@@ -0,0 +1,73 @@
# Design: saas-test-pilot
**Domain:** `saas`
**Target Version:** v9.5.0
## Purpose
Test automation toolkit supporting unit, integration, and end-to-end testing. Generates test cases from code analysis, manages test fixtures, and provides coverage analysis with gap detection.
## Target Users
- Developers writing tests for Python or JavaScript/TypeScript projects
- Teams enforcing test coverage requirements
- Projects needing test generation from existing code
## Commands
| Command | Description |
|---------|-------------|
| `/test setup` | Setup wizard — detect test framework, configure paths |
| `/test generate` | Generate test cases for functions/classes/modules |
| `/test coverage` | Analyze test coverage and identify untested code paths |
| `/test fixtures` | Generate or manage test fixtures and mocks |
| `/test e2e` | Generate end-to-end test scenarios from user stories |
| `/test run` | Run tests with formatted output and failure analysis |
## Agent Architecture
| Agent | Model | Mode | Role |
|-------|-------|------|------|
| `test-architect` | sonnet | acceptEdits | Test generation, fixture creation, e2e scenarios |
| `coverage-analyst` | haiku | plan | Read-only coverage analysis and gap detection |
## Skills
| Skill | Purpose |
|-------|---------|
| `framework-detection` | Detect pytest/Jest/Vitest/Playwright, identify config |
| `test-patterns` | Unit/integration/e2e test patterns and best practices |
| `mock-patterns` | Mocking strategies for different dependency types |
| `coverage-analysis` | Coverage gap detection and prioritization |
| `fixture-management` | Fixture organization, factories, builders |
| `visual-header` | Standard command output headers |
## MCP Server
**Not required.** Test generation is file-based. Test execution uses the project's own test runner via Bash.
## Integration Points
| Plugin | Integration |
|--------|-------------|
| projman | `/sprint test` delegates to test-pilot when installed |
| saas-api-platform | API route tests generated from `/api test-routes` |
| saas-react-platform | Component tests generated alongside components |
| data-seed | Test fixtures use seed data profiles |
| code-sentinel | Security test patterns included in generation |
## Token Budget
| Component | Estimated Tokens |
|-----------|-----------------|
| `claude-md-integration.md` | ~700 |
| Dispatch file (`test.md`) | ~200 |
| 6 commands (avg) | ~3,600 |
| 2 agents | ~1,200 |
| 6 skills | ~2,500 |
| **Total** | **~8,200** |
## Open Questions
- Should `/test run` replace projman's `/sprint test run` or supplement it?
- Support for property-based testing (Hypothesis, fast-check)?

View File

@@ -0,0 +1,9 @@
# Prompt Index
Tracks execution status of structured prompts used for marketplace evolution and maintenance.
| ID | Title | Status | Date | Version |
|----|-------|--------|------|---------|
| 001 | Phase 1 Evolution — Domain Metadata + Hook Migration | executed | 2026-02-06 | 8.0.0 → 8.1.0 |
| 002 | Phase 1b — Command Consolidation + 8 New Plugins | executed | 2026-02-06 | 8.1.0 → 9.0.0 |
| 003 | Post-Evolution Cleanup — Stale References and Migration Guide Fixes | executed | 2026-02-06 | 9.0.0 → 9.0.1 |

View File

@@ -98,10 +98,10 @@ If unset, all modules are enabled (backward compatible).
| Module | Tool Count | Description | cmdb-assistant Commands |
|--------|------------|-------------|------------------------|
| `dcim` | ~60 | Sites, devices, racks, interfaces, cables | `/cmdb-device`, `/cmdb-site`, `/cmdb-search`, `/cmdb-topology` |
| `ipam` | ~40 | IP addresses, prefixes, VLANs, VRFs | `/cmdb-ip`, `/ip-conflicts`, `/cmdb-search` |
| `virtualization` | ~20 | Clusters, VMs, VM interfaces | `/cmdb-search`, `/cmdb-audit`, `/cmdb-register` |
| `extras` | ~12 | Tags, journal entries, audit log | `/change-audit`, `/cmdb-register` |
| `dcim` | ~60 | Sites, devices, racks, interfaces, cables | `/cmdb device`, `/cmdb site`, `/cmdb search`, `/cmdb topology` |
| `ipam` | ~40 | IP addresses, prefixes, VLANs, VRFs | `/cmdb ip`, `/cmdb ip-conflicts`, `/cmdb search` |
| `virtualization` | ~20 | Clusters, VMs, VM interfaces | `/cmdb search`, `/cmdb audit`, `/cmdb register` |
| `extras` | ~12 | Tags, journal entries, audit log | `/cmdb change-audit`, `/cmdb register` |
| `circuits` | ~15 | Providers, circuits, terminations | — |
| `tenancy` | ~12 | Tenants, contacts | — |
| `vpn` | ~15 | Tunnels, IKE/IPSec policies, L2VPN | — |

View File

@@ -119,7 +119,7 @@ Track gathered information in a mental model:
### After Clarification
Produce a clear specification (see /clarify command for format).
Produce a clear specification (see /clarity clarify command for format).
## Example Session

View File

@@ -18,8 +18,8 @@ This project uses the clarity-assist plugin for requirement gathering.
| Command | Use Case |
|---------|----------|
| `/clarify` | Full 4-D methodology for complex requests |
| `/quick-clarify` | Rapid mode for simple disambiguation |
| `/clarity clarify` | Full 4-D methodology for complex requests |
| `/clarity quick-clarify` | Rapid mode for simple disambiguation |
### Communication Style

View File

@@ -1,4 +1,8 @@
# /clarify - Full Prompt Optimization
---
name: clarity clarify
---
# /clarity clarify - Full Prompt Optimization
## Visual Output

View File

@@ -1,4 +1,8 @@
# /quick-clarify - Rapid Clarification Mode
---
name: clarity quick-clarify
---
# /clarity quick-clarify - Rapid Clarification Mode
## Visual Output
@@ -23,7 +27,7 @@ Single-pass clarification for requests that are mostly clear but need minor disa
- `skills/nd-accommodations.md` - ND-friendly question patterns
- `skills/clarification-techniques.md` - Echo and micro-summary techniques
- `skills/escalation-patterns.md` - When to escalate to full /clarify
- `skills/escalation-patterns.md` - When to escalate to full `/clarity clarify`
## Workflow
@@ -37,7 +41,7 @@ No formal specification document needed. Proceed after brief confirmation, docum
## Escalation
If complexity emerges, offer to switch to full `/clarify`:
If complexity emerges, offer to switch to full `/clarity clarify`:
```
"This is more involved than it first appeared. Want me to switch

View File

@@ -0,0 +1,14 @@
---
description: Prompt optimization and requirement clarification
---
# /clarity
Prompt optimization and requirement clarification with ND-friendly accommodations.
## Sub-commands
| Sub-command | Description |
|-------------|-------------|
| `/clarity clarify` | Full 4-D methodology for complex requests |
| `/clarity quick-clarify` | Rapid mode for simple disambiguation |

View File

@@ -58,8 +58,8 @@ Our design philosophy centers on three principles:
### 3. Customizable Verbosity
**Detail Levels**
- `/clarify` - Full methodology for complex requests (more thorough, more questions)
- `/quick-clarify` - Rapid mode for simple disambiguation (fewer questions, faster)
- `/clarity clarify` - Full methodology for complex requests (more thorough, more questions)
- `/clarity quick-clarify` - Rapid mode for simple disambiguation (fewer questions, faster)
**User Control**
- Users can always say "that's enough detail" to end questioning early
@@ -68,7 +68,7 @@ Our design philosophy centers on three principles:
### 4. Vagueness Detection
The `UserPromptSubmit` hook automatically detects prompts that might benefit from clarification and gently suggests using `/clarify`.
The `UserPromptSubmit` hook automatically detects prompts that might benefit from clarification and gently suggests using `/clarity clarify`.
**Detection Signals**
- Short prompts (< 10 words) without specific technical terms
@@ -156,10 +156,10 @@ This triggers vagueness detection because:
- No specific technical context
- No measurable outcome
### After: Clarified with /clarify
### After: Clarified with /clarity clarify
```
User: /clarify Make the app faster
User: /clarity clarify Make the app faster
Claude: Let me help clarify what kind of performance improvements you're looking for.
@@ -235,7 +235,7 @@ Optimize initial page load time to under 2 seconds by addressing bundle size and
For simpler requests that just need minor disambiguation:
```
User: /quick-clarify Add a delete button to the user list
User: /clarity quick-clarify Add a delete button to the user list
Claude: I'll add a delete button to each row in the user list.
@@ -286,14 +286,14 @@ export CLARITY_ASSIST_VAGUENESS_THRESHOLD=0.8
### If You're Feeling Overwhelmed
- Use `/quick-clarify` instead of `/clarify` for faster interactions
- Use `/clarity quick-clarify` instead of `/clarity clarify` for faster interactions
- Say "let's focus on just one thing" to narrow scope
- Ask to "pause and summarize" at any point
- It's OK to say "I don't know" - the plugin will offer concrete alternatives
### If You Have Executive Function Challenges
- Start with `/clarify` even for tasks you think are simple - it helps with planning
- Start with `/clarity clarify` even for tasks you think are simple - it helps with planning
- The structured specification can serve as a checklist
- Use the scope boundaries to prevent scope creep

View File

@@ -240,7 +240,7 @@ if (( $(echo "$SCORE >= $THRESHOLD" | bc -l) )); then
# Gentle, non-blocking suggestion
echo "$PREFIX Your prompt could benefit from more clarity."
echo "$PREFIX Consider running /clarify to refine your request."
echo "$PREFIX Consider running /clarity clarify to refine your request."
echo "$PREFIX (Vagueness score: ${SCORE_PCT}% - this is a suggestion, not a block)"
# Additional RFC suggestion if feature request detected

View File

@@ -40,7 +40,7 @@ add the other parts. Sound good?"
## Choosing Initial Mode
### Use /quick-clarify When
### Use /clarity quick-clarify When
- Request is fairly clear, just one or two ambiguities
- User is in a hurry
@@ -48,7 +48,7 @@ add the other parts. Sound good?"
- Simple feature additions or bug fixes
- Confidence is high (>90%)
### Use /clarify When
### Use /clarity clarify When
- Complex multi-step requests
- Requirements with multiple possible interpretations

View File

@@ -96,13 +96,13 @@ Use this mapping to identify active plugins:
| `gitea` | projman |
| `netbox` | cmdb-assistant |
Also check for hook-based plugins (project-hygiene uses `PostToolUse` hooks).
Also check for hook-based plugins (code-sentinel, git-flow, cmdb-assistant use `PreToolUse` safety hooks; clarity-assist uses `UserPromptSubmit` quality hook).
**Step 2: Check CLAUDE.md for Plugin References**
For each detected plugin, search CLAUDE.md for:
- Plugin name mention (e.g., "projman", "cmdb-assistant")
- Command references (e.g., `/sprint-plan`, `/cmdb-search`)
- Command references (e.g., `/sprint plan`, `/cmdb search`)
- MCP tool mentions (e.g., `list_issues`, `dcim_list_devices`)
**Step 3: Load Integration Snippets**
@@ -151,7 +151,7 @@ Evaluate using `skills/settings-optimization.md`:
Before recommending auto-allow patterns, verify active review layers:
1. Read `plugins/*/hooks/hooks.json` for each installed plugin
2. Map hook types (PreToolUse, PostToolUse) to tool matchers (Write, Edit, Bash)
2. Map hook types (PreToolUse, UserPromptSubmit) to tool matchers (Write, Edit, MultiEdit, Bash, MCP patterns)
3. Confirm plugins are listed in `.claude-plugin/marketplace.json`
4. Only recommend auto-allow for scopes covered by ≥2 verified review layers

View File

@@ -6,14 +6,14 @@ This project uses the **claude-config-maintainer** plugin to analyze and optimiz
| Command | Description |
|---------|-------------|
| `/config-analyze` | Analyze CLAUDE.md for optimization opportunities with 100-point scoring |
| `/config-optimize` | Automatically optimize CLAUDE.md structure and content |
| `/config-init` | Initialize a new CLAUDE.md file for a project |
| `/config-diff` | Track CLAUDE.md changes over time with behavioral impact analysis |
| `/config-lint` | Lint CLAUDE.md for anti-patterns and best practices (31 rules) |
| `/config-audit-settings` | Audit settings.local.json permissions with 100-point scoring |
| `/config-optimize-settings` | Optimize permission patterns and apply named profiles |
| `/config-permissions-map` | Visual map of review layers and permission coverage |
| `/claude-config analyze` | Analyze CLAUDE.md for optimization opportunities with 100-point scoring |
| `/claude-config optimize` | Automatically optimize CLAUDE.md structure and content |
| `/claude-config init` | Initialize a new CLAUDE.md file for a project |
| `/claude-config diff` | Track CLAUDE.md changes over time with behavioral impact analysis |
| `/claude-config lint` | Lint CLAUDE.md for anti-patterns and best practices (31 rules) |
| `/claude-config audit-settings` | Audit settings.local.json permissions with 100-point scoring |
| `/claude-config optimize-settings` | Optimize permission patterns and apply named profiles |
| `/claude-config permissions-map` | Visual map of review layers and permission coverage |
### CLAUDE.md Scoring System
@@ -47,10 +47,10 @@ The settings audit uses a 100-point scoring system across four categories:
### Usage Guidelines
- Run `/config-analyze` periodically to assess CLAUDE.md quality
- Run `/config-audit-settings` to check permission efficiency
- Run `/claude-config analyze` periodically to assess CLAUDE.md quality
- Run `/claude-config audit-settings` to check permission efficiency
- Target a score of **70+/100** for effective Claude Code operation
- Address HIGH priority issues first when optimizing
- Use `/config-init` when setting up new projects to start with best practices
- Use `/config-permissions-map` to visualize review layer coverage
- Use `/claude-config init` when setting up new projects to start with best practices
- Use `/claude-config permissions-map` to visualize review layer coverage
- Re-analyze after making changes to verify improvements

View File

@@ -1,8 +1,9 @@
---
name: claude-config analyze
description: Analyze CLAUDE.md for optimization opportunities and plugin integration
---
# Analyze CLAUDE.md
# /claude-config analyze
Analyze your CLAUDE.md and provide a scored report with recommendations.
@@ -20,7 +21,7 @@ Display: `CONFIG-MAINTAINER - CLAUDE.md Analysis`
## Usage
```
/config-analyze
/claude-config analyze
```
## Workflow

View File

@@ -1,9 +1,9 @@
---
name: config-audit-settings
name: claude-config audit-settings
description: Audit settings.local.json for permission optimization opportunities
---
# /config-audit-settings
# /claude-config audit-settings
Audit Claude Code `settings.local.json` permissions with 100-point scoring across redundancy, coverage, safety alignment, and profile fit.
@@ -24,8 +24,8 @@ Before executing, load:
## Usage
```
/config-audit-settings # Full audit with recommendations
/config-audit-settings --diagram # Include Mermaid diagram of review layer coverage
/claude-config audit-settings # Full audit with recommendations
/claude-config audit-settings --diagram # Include Mermaid diagram of review layer coverage
```
## Workflow
@@ -62,21 +62,20 @@ Using `settings-optimization.md` Section 3, detect:
### Step 4: Detect Active Marketplace Hooks
Read `plugins/*/hooks/hooks.json` files:
Read `plugins/*/hooks/hooks.json` files (post-Decision #29 — only PreToolUse safety hooks and UserPromptSubmit quality hooks exist):
```bash
# Check each plugin's hooks
plugins/code-sentinel/hooks/hooks.json # PreToolUse security
plugins/doc-guardian/hooks/hooks.json # PostToolUse drift detection
plugins/project-hygiene/hooks/hooks.json # PostToolUse cleanup
plugins/data-platform/hooks/hooks.json # PostToolUse schema diff
plugins/contract-validator/hooks/hooks.json # Plugin validation
# Check each plugin's hooks (exhaustive post-v8.1.0 inventory)
plugins/code-sentinel/hooks/hooks.json # PreToolUse: Write|Edit|MultiEdit → security-check.sh
plugins/git-flow/hooks/hooks.json # PreToolUse: Bash → branch-check.sh, commit-msg-check.sh
plugins/cmdb-assistant/hooks/hooks.json # PreToolUse: MCP create/update → validate-input.sh
plugins/clarity-assist/hooks/hooks.json # UserPromptSubmit → vagueness-check.sh
```
Parse each to identify:
- Hook event type (PreToolUse, PostToolUse)
- Tool matchers (Write, Edit, MultiEdit, Bash)
- Whether hook is command type (reliable) or prompt type (unreliable)
- Hook event type (PreToolUse or UserPromptSubmit only — no other types should exist)
- Tool matchers (Write, Edit, MultiEdit, Bash, MCP patterns)
- Whether hook is command type (must be — prompt type is forbidden)
### Step 5: Map Review Layers to Directory Scopes
@@ -118,9 +117,9 @@ Issues Found:
Active Review Layers Detected:
✓ code-sentinel (PreToolUse: Write|Edit|MultiEdit)
doc-guardian (PostToolUse: Write|Edit|MultiEdit)
project-hygiene (PostToolUse: Write|Edit)
✗ data-platform schema-diff (not detected)
git-flow (PreToolUse: Bash — branch naming + commit format)
cmdb-assistant (PreToolUse: MCP create/update)
✓ clarity-assist (UserPromptSubmit: vagueness detection)
Recommendations:
1. [specific action with pattern]
@@ -128,9 +127,9 @@ Recommendations:
...
Follow-Up Actions:
1. Run /config-optimize-settings to apply recommendations
2. Run /config-optimize-settings --dry-run to preview first
3. Run /config-optimize-settings --profile=reviewed to apply profile
1. Run /claude-config optimize-settings to apply recommendations
2. Run /claude-config optimize-settings --dry-run to preview first
3. Run /claude-config optimize-settings --profile=reviewed to apply profile
```
## Diagram Output (--diagram flag)
@@ -146,7 +145,7 @@ When `--diagram` is specified, generate a Mermaid flowchart showing:
**Color coding:**
- PreToolUse hooks: Blue
- PostToolUse hooks: Green
- UserPromptSubmit hooks: Green
- Sprint Approval: Amber
- PR Review: Purple
@@ -161,7 +160,7 @@ flowchart LR
subgraph Review Layers
CS[code-sentinel]
DG[doc-guardian]
GF[git-flow]
PR[pr-review]
end
@@ -172,18 +171,17 @@ flowchart LR
end
W --> CS
W --> DG
E --> CS
E --> DG
B --> GF
CS --> A
DG --> A
GF --> A
B --> P
classDef preHook fill:#e3f2fd
classDef postHook fill:#e8f5e9
classDef userPrompt fill:#e8f5e9
classDef prReview fill:#f3e5f5
class CS preHook
class DG postHook
class GF preHook
class PR prReview
```

View File

@@ -1,8 +1,9 @@
---
name: claude-config diff
description: Show diff between current CLAUDE.md and last commit
---
# Compare CLAUDE.md Changes
# /claude-config diff
Show differences between CLAUDE.md versions to track configuration drift.
@@ -18,10 +19,10 @@ Display: `CONFIG-MAINTAINER - CLAUDE.md Diff`
## Usage
```
/config-diff # Working vs last commit
/config-diff --commit=abc1234 # Working vs specific commit
/config-diff --from=v1.0 --to=v2.0 # Compare two commits
/config-diff --section="Critical Rules" # Specific section only
/claude-config diff # Working vs last commit
/claude-config diff --commit=abc1234 # Working vs specific commit
/claude-config diff --from=v1.0 --to=v2.0 # Compare two commits
/claude-config diff --section="Critical Rules" # Specific section only
```
## Workflow

View File

@@ -1,8 +1,9 @@
---
name: claude-config init
description: Initialize a new CLAUDE.md file for a project
---
# Initialize CLAUDE.md
# /claude-config init
Create a new CLAUDE.md file tailored to your project.
@@ -19,9 +20,9 @@ Display: `CONFIG-MAINTAINER - CLAUDE.md Initialization`
## Usage
```
/config-init # Interactive
/config-init --minimal # Minimal version
/config-init --comprehensive # Detailed version
/claude-config init # Interactive
/claude-config init --minimal # Minimal version
/claude-config init --comprehensive # Detailed version
```
## Workflow

View File

@@ -1,8 +1,9 @@
---
name: claude-config lint
description: Lint CLAUDE.md for common anti-patterns and best practices
---
# Lint CLAUDE.md
# /claude-config lint
Check CLAUDE.md against best practices and detect common anti-patterns.
@@ -18,9 +19,9 @@ Display: `CONFIG-MAINTAINER - CLAUDE.md Lint`
## Usage
```
/config-lint # Full lint
/config-lint --fix # Auto-fix issues
/config-lint --rules=security # Check specific category
/claude-config lint # Full lint
/claude-config lint --fix # Auto-fix issues
/claude-config lint --rules=security # Check specific category
```
## Workflow

View File

@@ -1,9 +1,9 @@
---
name: config-optimize-settings
name: claude-config optimize-settings
description: Optimize settings.local.json permissions based on audit recommendations
---
# /config-optimize-settings
# /claude-config optimize-settings
Optimize Claude Code `settings.local.json` permission patterns and apply named profiles.
@@ -25,10 +25,10 @@ Before executing, load:
## Usage
```
/config-optimize-settings # Apply audit recommendations
/config-optimize-settings --dry-run # Preview only, no changes
/config-optimize-settings --profile=reviewed # Apply named profile
/config-optimize-settings --consolidate-only # Only merge/dedupe, no new rules
/claude-config optimize-settings # Apply audit recommendations
/claude-config optimize-settings --dry-run # Preview only, no changes
/claude-config optimize-settings --profile=reviewed # Apply named profile
/claude-config optimize-settings --consolidate-only # Only merge/dedupe, no new rules
```
## Options
@@ -44,7 +44,7 @@ Before executing, load:
### Step 1: Run Audit Analysis
Execute the same analysis as `/config-audit-settings`:
Execute the same analysis as `/claude-config audit-settings`:
1. Locate settings file
2. Parse permission arrays
3. Detect issues (duplicates, subsets, merge candidates, etc.)
@@ -171,7 +171,7 @@ Switching to reviewed profile...
Prerequisites verified:
✓ code-sentinel hook active (PreToolUse)
doc-guardian hook active (PostToolUse)
git-flow hook active (PreToolUse)
✓ 2+ review layers detected
This profile:
@@ -214,7 +214,7 @@ DRY RUN - No changes will be made
[... preview content ...]
To apply these changes, run:
/config-optimize-settings
/claude-config optimize-settings
```
### Applied Output

View File

@@ -1,8 +1,9 @@
---
name: claude-config optimize
description: Optimize CLAUDE.md structure and content
---
# Optimize CLAUDE.md
# /claude-config optimize
Automatically optimize CLAUDE.md based on best practices.
@@ -20,9 +21,9 @@ Display: `CONFIG-MAINTAINER - CLAUDE.md Optimization`
## Usage
```
/config-optimize # Full optimization
/config-optimize --condense # Reduce verbosity
/config-optimize --dry-run # Preview only
/claude-config optimize # Full optimization
/claude-config optimize --condense # Reduce verbosity
/claude-config optimize --dry-run # Preview only
```
## Workflow

View File

@@ -1,9 +1,9 @@
---
name: config-permissions-map
name: claude-config permissions-map
description: Generate visual map of review layers and permission coverage
---
# /config-permissions-map
# /claude-config permissions-map
Generate a Mermaid diagram showing the relationship between file operations, review layers, and permission status.
@@ -26,8 +26,8 @@ Also read: `/mnt/skills/user/mermaid-diagrams/SKILL.md` (for diagram requirement
## Usage
```
/config-permissions-map # Generate and display diagram
/config-permissions-map --save # Save diagram to .mermaid file
/claude-config permissions-map # Generate and display diagram
/claude-config permissions-map --save # Save diagram to .mermaid file
```
## Workflow
@@ -38,15 +38,13 @@ Read all plugin hooks from the marketplace:
```
plugins/code-sentinel/hooks/hooks.json
plugins/doc-guardian/hooks/hooks.json
plugins/project-hygiene/hooks/hooks.json
plugins/data-platform/hooks/hooks.json
plugins/contract-validator/hooks/hooks.json
plugins/git-flow/hooks/hooks.json
plugins/cmdb-assistant/hooks/hooks.json
plugins/clarity-assist/hooks/hooks.json
```
For each hook, extract:
- Event type (PreToolUse, PostToolUse, SessionStart, etc.)
- Event type (PreToolUse, UserPromptSubmit)
- Tool matchers (Write, Edit, MultiEdit, Bash patterns)
- Hook command/script
@@ -54,12 +52,13 @@ For each hook, extract:
Create a mapping of which review layers cover which operations:
| Operation | PreToolUse Hooks | PostToolUse Hooks | Other Gates |
|-----------|------------------|-------------------|-------------|
| Write | code-sentinel | doc-guardian, project-hygiene | PR review |
| Edit | code-sentinel | doc-guardian, project-hygiene | PR review |
| MultiEdit | code-sentinel | doc-guardian | PR review |
| Bash(git *) | git-flow | — | — |
| Operation | PreToolUse Hooks | Other Gates |
|-----------|------------------|-------------|
| Write | code-sentinel | PR review |
| Edit | code-sentinel | PR review |
| MultiEdit | code-sentinel | PR review |
| Bash(git *) | git-flow | — |
| MCP(netbox create/update) | cmdb-assistant | — |
### Step 3: Read Current Permissions
@@ -94,13 +93,7 @@ flowchart LR
direction TB
CS[code-sentinel<br/>Security Scan]
GF[git-flow<br/>Branch Check]
end
subgraph post[PostToolUse Hooks]
direction TB
DG[doc-guardian<br/>Drift Detection]
PH[project-hygiene<br/>Cleanup]
DP[data-platform<br/>Schema Diff]
CA[clarity-assist<br/>Prompt Quality]
end
subgraph perm[Permission Status]
@@ -111,26 +104,22 @@ flowchart LR
end
W -->|intercepted| CS
W -->|tracked| DG
E -->|intercepted| CS
E -->|tracked| DG
BG -->|checked| GF
CS -->|passed| AA
DG -->|logged| AA
GF -->|valid| AA
BO -->|no hook| PR
classDef preHook fill:#e3f2fd,stroke:#1976d2
classDef postHook fill:#e8f5e9,stroke:#388e3c
classDef sprint fill:#fff3e0,stroke:#f57c00
classDef quality fill:#fff3e0,stroke:#f57c00
classDef prReview fill:#f3e5f5,stroke:#7b1fa2
classDef allowed fill:#c8e6c9,stroke:#2e7d32
classDef prompted fill:#fff9c4,stroke:#f9a825
classDef denied fill:#ffcdd2,stroke:#c62828
class CS,GF preHook
class DG,PH,DP postHook
class CA quality
class AA allowed
class PR prompted
class DN denied
@@ -195,11 +184,10 @@ Review Layer Status
PreToolUse Hooks (intercept before operation):
✓ code-sentinel — Write, Edit, MultiEdit
✓ git-flow — Bash(git checkout *), Bash(git commit *)
✓ cmdb-assistant — MCP(netbox create/update)
PostToolUse Hooks (track after operation):
doc-guardian — Write, Edit, MultiEdit
✓ project-hygiene — Write, Edit
✗ data-platform — not detected
UserPromptSubmit Hooks (check prompt quality):
clarity-assist — vagueness detection
Other Review Gates:
✓ Sprint Approval (projman milestone workflow)
@@ -241,7 +229,6 @@ To view:
| Element | Color | Hex |
|---------|-------|-----|
| PreToolUse hooks | Blue | #e3f2fd |
| PostToolUse hooks | Green | #e8f5e9 |
| Sprint/Planning gates | Amber | #fff3e0 |
| PR Review | Purple | #f3e5f5 |
| Auto-allowed | Light green | #c8e6c9 |

View File

@@ -0,0 +1,20 @@
---
description: CLAUDE.md and settings optimization
---
# /claude-config
CLAUDE.md and settings.local.json optimization for Claude Code projects.
## Sub-commands
| Sub-command | Description |
|-------------|-------------|
| `/claude-config analyze` | Analyze CLAUDE.md for optimization opportunities |
| `/claude-config optimize` | Optimize CLAUDE.md structure with preview/backup |
| `/claude-config init` | Initialize new CLAUDE.md for a project |
| `/claude-config diff` | Track CLAUDE.md changes over time with behavioral impact |
| `/claude-config lint` | Lint CLAUDE.md for anti-patterns and best practices |
| `/claude-config audit-settings` | Audit settings.local.json permissions (100-point score) |
| `/claude-config optimize-settings` | Optimize permissions (profiles, consolidation, dry-run) |
| `/claude-config permissions-map` | Visual review layer + permission coverage map |

View File

@@ -1,68 +0,0 @@
#!/bin/bash
# claude-config-maintainer: enforce mandatory behavior rules
# Checks if CLAUDE.md has the rules, adds them if missing
PREFIX="[claude-config-maintainer]"
# Find CLAUDE.md in current directory or parent
CLAUDE_MD=""
if [ -f "./CLAUDE.md" ]; then
CLAUDE_MD="./CLAUDE.md"
elif [ -f "../CLAUDE.md" ]; then
CLAUDE_MD="../CLAUDE.md"
fi
# If no CLAUDE.md found, exit silently
if [ -z "$CLAUDE_MD" ]; then
exit 0
fi
# Check if mandatory rules exist
if grep -q "MANDATORY BEHAVIOR RULES" "$CLAUDE_MD" 2>/dev/null; then
# Rules exist, all good
exit 0
fi
# Rules missing - add them
RULES='## ⛔ MANDATORY BEHAVIOR RULES - READ FIRST
**These rules are NON-NEGOTIABLE. Violating them wastes the user'\''s time and money.**
### 1. WHEN USER ASKS YOU TO CHECK SOMETHING - CHECK EVERYTHING
- Search ALL locations, not just where you think it is
- Check cache directories: `~/.claude/plugins/cache/`
- Check installed: `~/.claude/plugins/marketplaces/`
- Check source directories
- **NEVER say "no" or "that'\''s not the issue" without exhaustive verification**
### 2. WHEN USER SAYS SOMETHING IS WRONG - BELIEVE THEM
- The user knows their system better than you
- Investigate thoroughly before disagreeing
- **Your confidence is often wrong. User'\''s instincts are often right.**
### 3. NEVER SAY "DONE" WITHOUT VERIFICATION
- Run the actual command/script to verify
- Show the output to the user
- **"Done" means VERIFIED WORKING, not "I made changes"**
### 4. SHOW EXACTLY WHAT USER ASKS FOR
- If user asks for messages, show the MESSAGES
- If user asks for code, show the CODE
- **Do not interpret or summarize unless asked**
**FAILURE TO FOLLOW THESE RULES = WASTED USER TIME = UNACCEPTABLE**
---
'
# Create temp file with rules + existing content
{
head -1 "$CLAUDE_MD"
echo ""
echo "$RULES"
tail -n +2 "$CLAUDE_MD"
} > "${CLAUDE_MD}.tmp"
mv "${CLAUDE_MD}.tmp" "$CLAUDE_MD"
echo "$PREFIX Added mandatory behavior rules to CLAUDE.md"

View File

@@ -1,15 +0,0 @@
{
"hooks": {
"SessionStart": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/enforce-rules.sh"
}
]
}
]
}
}

View File

@@ -6,7 +6,7 @@ This skill defines how to analyze and present CLAUDE.md differences.
| Mode | Command | Description |
|------|---------|-------------|
| Working vs HEAD | `/config-diff` | Uncommitted changes |
| Working vs HEAD | `/claude-config diff` | Uncommitted changes |
| Working vs Commit | `--commit=REF` | Changes since specific point |
| Commit to Commit | `--from=X --to=Y` | Historical comparison |
| Branch Comparison | `--branch=NAME` | Cross-branch differences |

View File

@@ -119,14 +119,14 @@ This is the key section. Map upstream review processes to directory scopes:
| Directory Scope | Active Review Layers | Auto-Allow Recommendation |
|----------------|---------------------|---------------------------|
| `plugins/*/commands/*.md` | Sprint approval, PR review, doc-guardian PostToolUse | `Write(plugins/*/commands/**)`3 layers cover this |
| `plugins/*/commands/*.md` | Sprint approval, PR review | `Write(plugins/*/commands/**)`2 layers cover this |
| `plugins/*/skills/*.md` | Sprint approval, PR review | `Write(plugins/*/skills/**)` — 2 layers |
| `plugins/*/agents/*.md` | Sprint approval, PR review, contract-validator | `Write(plugins/*/agents/**)`3 layers |
| `plugins/*/agents/*.md` | Sprint approval, PR review | `Write(plugins/*/agents/**)`2 layers |
| `mcp-servers/*/mcp_server/*.py` | Code-sentinel PreToolUse, sprint approval, PR review | `Write(mcp-servers/**)` + `Edit(mcp-servers/**)` — sentinel catches secrets |
| `docs/*.md` | Doc-guardian PostToolUse, PR review | `Write(docs/**)` + `Edit(docs/**)` |
| `docs/*.md` | PR review | `Write(docs/**)` + `Edit(docs/**)` — with caution flag |
| `.claude-plugin/*.json` | validate-marketplace.sh, PR review | `Write(.claude-plugin/**)` |
| `scripts/*.sh` | Code-sentinel, PR review | `Write(scripts/**)` — with caution flag |
| `CLAUDE.md`, `CHANGELOG.md`, `README.md` | Doc-guardian, PR review | `Write(CLAUDE.md)`, `Write(CHANGELOG.md)`, `Write(README.md)` |
| `CLAUDE.md`, `CHANGELOG.md`, `README.md` | PR review | `Write(CLAUDE.md)`, `Write(CHANGELOG.md)`, `Write(README.md)` |
### Critical Rule: Hook Verification
@@ -134,10 +134,11 @@ This is the key section. Map upstream review processes to directory scopes:
Read the relevant `plugins/*/hooks/hooks.json` file:
- If code-sentinel's hook is missing or disabled, do NOT recommend auto-allowing `mcp-servers/**` writes
- If doc-guardian's hook is missing, do NOT recommend auto-allowing `docs/**` without caution
- If git-flow's hook is missing, do NOT recommend auto-allowing `Bash(git *)` operations
- If cmdb-assistant's hook is missing, do NOT recommend auto-allowing MCP netbox create/update operations
- Count the number of verified review layers before making recommendations
**Minimum threshold:** Recommend auto-allow only for scopes covered by ≥2 verified review layers.
**Minimum threshold:** Only recommend auto-allow for scopes with ≥2 verified review layers.
---
@@ -333,10 +334,9 @@ To verify which review layers are active, read these files:
| File | Hook Type | Tool Matcher | Purpose |
|------|-----------|--------------|---------|
| `plugins/code-sentinel/hooks/hooks.json` | PreToolUse | Write\|Edit\|MultiEdit | Blocks hardcoded secrets |
| `plugins/doc-guardian/hooks/hooks.json` | PostToolUse | Write\|Edit\|MultiEdit | Tracks documentation drift |
| `plugins/project-hygiene/hooks/hooks.json` | PostToolUse | Write\|Edit | Cleanup tracking |
| `plugins/data-platform/hooks/hooks.json` | PostToolUse | Edit\|Write | Schema diff detection |
| `plugins/cmdb-assistant/hooks/hooks.json` | PreToolUse | (if exists) | Input validation |
| `plugins/git-flow/hooks/hooks.json` | PreToolUse | Bash | Branch naming + commit format |
| `plugins/cmdb-assistant/hooks/hooks.json` | PreToolUse | MCP create/update | NetBox input validation |
| `plugins/clarity-assist/hooks/hooks.json` | UserPromptSubmit | (all prompts) | Vagueness detection |
### Verification Process
@@ -351,14 +351,19 @@ To verify which review layers are active, read these files:
```json
{
"hooks": [
{
"event": "PreToolUse",
"type": "command",
"command": "./hooks/security-check.sh",
"tools": ["Write", "Edit", "MultiEdit"]
}
]
"hooks": {
"PreToolUse": [
{
"matcher": "Write|Edit|MultiEdit",
"hooks": [
{
"type": "command",
"command": "./hooks/security-check.sh"
}
]
}
]
}
}
```
@@ -370,8 +375,8 @@ Count verified review layers for each scope:
|-------|-------------|
| Sprint approval | Check if projman plugin is installed (milestone workflow) |
| PR review | Check if pr-review plugin is installed |
| code-sentinel PreToolUse | hooks.json exists with PreToolUse on Write/Edit |
| doc-guardian PostToolUse | hooks.json exists with PostToolUse on Write/Edit |
| contract-validator | Plugin installed + hooks present |
| code-sentinel PreToolUse | hooks.json exists with PreToolUse on Write/Edit/MultiEdit |
| git-flow PreToolUse | hooks.json exists with PreToolUse on Bash |
| cmdb-assistant PreToolUse | hooks.json exists with PreToolUse on MCP create/update |
**Recommendation threshold:** Only recommend auto-allow for scopes with ≥2 verified layers.

View File

@@ -12,56 +12,56 @@ This skill defines the standard visual header for claude-config-maintainer comma
## Command-Specific Headers
### /config-analyze
### /claude-config analyze
```
+-----------------------------------------------------------------+
| CONFIG-MAINTAINER - CLAUDE.md Analysis |
+-----------------------------------------------------------------+
```
### /config-optimize
### /claude-config optimize
```
+-----------------------------------------------------------------+
| CONFIG-MAINTAINER - CLAUDE.md Optimization |
+-----------------------------------------------------------------+
```
### /config-lint
### /claude-config lint
```
+-----------------------------------------------------------------+
| CONFIG-MAINTAINER - CLAUDE.md Lint |
+-----------------------------------------------------------------+
```
### /config-diff
### /claude-config diff
```
+-----------------------------------------------------------------+
| CONFIG-MAINTAINER - CLAUDE.md Diff |
+-----------------------------------------------------------------+
```
### /config-init
### /claude-config init
```
+-----------------------------------------------------------------+
| CONFIG-MAINTAINER - CLAUDE.md Initialization |
+-----------------------------------------------------------------+
```
### /config-audit-settings
### /claude-config audit-settings
```
+-----------------------------------------------------------------+
| CONFIG-MAINTAINER - Settings Audit |
+-----------------------------------------------------------------+
```
### /config-optimize-settings
### /claude-config optimize-settings
```
+-----------------------------------------------------------------+
| CONFIG-MAINTAINER - Settings Optimization |
+-----------------------------------------------------------------+
```
### /config-permissions-map
### /claude-config permissions-map
```
+-----------------------------------------------------------------+
| CONFIG-MAINTAINER - Permissions Map |

View File

@@ -97,13 +97,13 @@ ipam_list_prefixes prefix=<proposed-prefix>
| Command | Purpose |
|---------|---------|
| `/cmdb-search <query>` | Search across all CMDB objects |
| `/cmdb-device <action>` | Device CRUD operations |
| `/cmdb-ip <action>` | IP address and prefix management |
| `/cmdb-site <action>` | Site and location management |
| `/cmdb-audit [scope]` | Data quality analysis |
| `/cmdb-register` | Register current machine |
| `/cmdb-sync` | Sync machine state with NetBox |
| `/cmdb-topology <view>` | Generate infrastructure diagrams |
| `/change-audit [filters]` | Audit NetBox changes |
| `/ip-conflicts [scope]` | Detect IP conflicts |
| `/cmdb search <query>` | Search across all CMDB objects |
| `/cmdb device <action>` | Device CRUD operations |
| `/cmdb ip <action>` | IP address and prefix management |
| `/cmdb site <action>` | Site and location management |
| `/cmdb audit [scope]` | Data quality analysis |
| `/cmdb register` | Register current machine |
| `/cmdb sync` | Sync machine state with NetBox |
| `/cmdb topology <view>` | Generate infrastructure diagrams |
| `/cmdb change-audit [filters]` | Audit NetBox changes |
| `/cmdb ip-conflicts [scope]` | Detect IP conflicts |

View File

@@ -6,10 +6,10 @@ This project uses the **cmdb-assistant** plugin for NetBox CMDB integration to m
| Command | Description |
|---------|-------------|
| `/cmdb-search` | Search across all NetBox objects |
| `/cmdb-device` | Manage devices (create, update, list) |
| `/cmdb-ip` | Manage IP addresses and prefixes |
| `/cmdb-site` | Manage sites and locations |
| `/cmdb search` | Search across all NetBox objects |
| `/cmdb device` | Manage devices (create, update, list) |
| `/cmdb ip` | Manage IP addresses and prefixes |
| `/cmdb site` | Manage sites and locations |
### MCP Tools Available

View File

@@ -1,8 +1,9 @@
---
name: cmdb audit
description: Audit NetBox data quality and identify consistency issues
---
# CMDB Data Quality Audit
# /cmdb audit
Analyze NetBox data for quality issues and best practice violations.
@@ -16,7 +17,7 @@ Analyze NetBox data for quality issues and best practice violations.
## Usage
```
/cmdb-audit [scope]
/cmdb audit [scope]
```
**Scopes:**
@@ -49,9 +50,9 @@ Execute `skills/audit-workflow.md` which covers:
## Examples
- `/cmdb-audit` - Full audit
- `/cmdb-audit vms` - VM-specific checks
- `/cmdb-audit naming` - Naming conventions
- `/cmdb audit` - Full audit
- `/cmdb audit vms` - VM-specific checks
- `/cmdb audit naming` - Naming conventions
## User Request

View File

@@ -1,8 +1,9 @@
---
name: cmdb change-audit
description: Audit NetBox changes with filtering by date, user, or object type
---
# CMDB Change Audit
# /cmdb change-audit
Query and analyze the NetBox audit log for change tracking and compliance.
@@ -15,7 +16,7 @@ Query and analyze the NetBox audit log for change tracking and compliance.
## Usage
```
/change-audit [filters]
/cmdb change-audit [filters]
```
**Filters:**
@@ -46,11 +47,11 @@ If user asks for "security audit" or "compliance report":
## Examples
- `/change-audit` - Recent changes (last 24 hours)
- `/change-audit last 7 days` - Past week
- `/change-audit by admin` - All changes by admin
- `/change-audit type dcim.device` - Device changes only
- `/change-audit action delete` - All deletions
- `/cmdb change-audit` - Recent changes (last 24 hours)
- `/cmdb change-audit last 7 days` - Past week
- `/cmdb change-audit by admin` - All changes by admin
- `/cmdb change-audit type dcim.device` - Device changes only
- `/cmdb change-audit action delete` - All deletions
## User Request

View File

@@ -1,4 +1,8 @@
# CMDB Device Management
---
name: cmdb device
---
# /cmdb device
Manage network devices in NetBox.
@@ -10,7 +14,7 @@ Manage network devices in NetBox.
## Usage
```
/cmdb-device <action> [options]
/cmdb device <action> [options]
```
## Instructions
@@ -45,10 +49,10 @@ After creating a device, offer to:
## Examples
- `/cmdb-device list`
- `/cmdb-device show core-router-01`
- `/cmdb-device create web-server-03`
- `/cmdb-device at headquarters`
- `/cmdb device list`
- `/cmdb device show core-router-01`
- `/cmdb device create web-server-03`
- `/cmdb device at headquarters`
## User Request

View File

@@ -1,8 +1,9 @@
---
name: cmdb ip-conflicts
description: Detect IP address conflicts and overlapping prefixes in NetBox
---
# CMDB IP Conflict Detection
# /cmdb ip-conflicts
Scan NetBox IPAM data to identify IP address conflicts and overlapping prefixes.
@@ -15,7 +16,7 @@ Scan NetBox IPAM data to identify IP address conflicts and overlapping prefixes.
## Usage
```
/ip-conflicts [scope]
/cmdb ip-conflicts [scope]
```
**Scopes:**
@@ -49,9 +50,9 @@ Execute conflict detection from `skills/ip-management.md`:
## Examples
- `/ip-conflicts` - Full scan
- `/ip-conflicts addresses` - Duplicate IPs only
- `/ip-conflicts vrf Production` - Scan specific VRF
- `/cmdb ip-conflicts` - Full scan
- `/cmdb ip-conflicts addresses` - Duplicate IPs only
- `/cmdb ip-conflicts vrf Production` - Scan specific VRF
## User Request

View File

@@ -1,4 +1,8 @@
# CMDB IP Management
---
name: cmdb ip
---
# /cmdb ip
Manage IP addresses and prefixes in NetBox.
@@ -11,7 +15,7 @@ Manage IP addresses and prefixes in NetBox.
## Usage
```
/cmdb-ip <action> [options]
/cmdb ip <action> [options]
```
## Instructions
@@ -42,10 +46,10 @@ Execute operations from `skills/ip-management.md`.
## Examples
- `/cmdb-ip prefixes`
- `/cmdb-ip available in 10.0.1.0/24`
- `/cmdb-ip allocate from 10.0.1.0/24`
- `/cmdb-ip assign 10.0.1.50/24 to web-server-01 eth0`
- `/cmdb ip prefixes`
- `/cmdb ip available in 10.0.1.0/24`
- `/cmdb ip allocate from 10.0.1.0/24`
- `/cmdb ip assign 10.0.1.50/24 to web-server-01 eth0`
## User Request

View File

@@ -1,8 +1,9 @@
---
name: cmdb register
description: Register the current machine into NetBox with all running applications
---
# CMDB Machine Registration
# /cmdb register
Register the current machine into NetBox, including hardware info, network interfaces, and running applications.
@@ -17,7 +18,7 @@ Register the current machine into NetBox, including hardware info, network inter
## Usage
```
/cmdb-register [--site <site-name>] [--tenant <tenant-name>] [--role <role-name>]
/cmdb register [--site <site-name>] [--tenant <tenant-name>] [--role <role-name>]
```
**Options:**
@@ -41,7 +42,7 @@ Execute `skills/device-registration.md` which covers:
| Error | Action |
|-------|--------|
| Device already exists | Suggest `/cmdb-sync` or ask to proceed |
| Device already exists | Suggest `/cmdb sync` or ask to proceed |
| Site not found | List available sites, offer to create new |
| Docker not available | Skip container registration, note in summary |
| Permission denied | Note which operations failed, suggest fixes |

View File

@@ -1,4 +1,8 @@
# CMDB Search
---
name: cmdb search
---
# /cmdb search
## Visual Output
@@ -17,7 +21,7 @@ Search NetBox for devices, IPs, sites, or any CMDB object.
## Usage
```
/cmdb-search <query>
/cmdb search <query>
```
## Instructions
@@ -37,9 +41,9 @@ For broad searches, query multiple endpoints and consolidate results.
## Examples
- `/cmdb-search router` - Find all devices with "router" in the name
- `/cmdb-search 10.0.1.0/24` - Find prefix and IPs within it
- `/cmdb-search datacenter` - Find sites matching "datacenter"
- `/cmdb search router` - Find all devices with "router" in the name
- `/cmdb search 10.0.1.0/24` - Find prefix and IPs within it
- `/cmdb search datacenter` - Find sites matching "datacenter"
## User Query

View File

@@ -1,8 +1,9 @@
---
name: cmdb setup
description: Interactive setup wizard for cmdb-assistant plugin
---
# CMDB Assistant Setup Wizard
# /cmdb setup
Configure the cmdb-assistant plugin with NetBox integration.
@@ -18,7 +19,7 @@ Configure the cmdb-assistant plugin with NetBox integration.
## Usage
```
/cmdb-setup
/cmdb setup
```
## Instructions
@@ -63,10 +64,10 @@ System Config: ~/.config/claude/netbox.env
Restart your Claude Code session for MCP tools.
After restart, try:
- /cmdb-device <hostname>
- /cmdb-ip <address>
- /cmdb-site <name>
- /cmdb-search <query>
- /cmdb device <hostname>
- /cmdb ip <address>
- /cmdb site <name>
- /cmdb search <query>
```
## User Request

View File

@@ -1,4 +1,8 @@
# CMDB Site Management
---
name: cmdb site
---
# /cmdb site
Manage sites and locations in NetBox.
@@ -10,7 +14,7 @@ Manage sites and locations in NetBox.
## Usage
```
/cmdb-site <action> [options]
/cmdb site <action> [options]
```
## Instructions
@@ -40,10 +44,10 @@ Execute `skills/visual-header.md` with context "Site Management".
## Examples
- `/cmdb-site list`
- `/cmdb-site show headquarters`
- `/cmdb-site create branch-office-nyc`
- `/cmdb-site racks at headquarters`
- `/cmdb site list`
- `/cmdb site show headquarters`
- `/cmdb site create branch-office-nyc`
- `/cmdb site racks at headquarters`
## User Request

View File

@@ -1,8 +1,9 @@
---
name: cmdb sync
description: Synchronize current machine state with existing NetBox record
---
# CMDB Machine Sync
# /cmdb sync
Update an existing NetBox device record with the current machine state.
@@ -16,7 +17,7 @@ Update an existing NetBox device record with the current machine state.
## Usage
```
/cmdb-sync [--full] [--dry-run]
/cmdb sync [--full] [--dry-run]
```
**Options:**
@@ -48,7 +49,7 @@ Execute `skills/sync-workflow.md` which covers:
| Error | Action |
|-------|--------|
| Device not found | Suggest `/cmdb-register` |
| Device not found | Suggest `/cmdb register` |
| Permission denied | Note which failed, continue others |
| Cluster not found | Offer to create or skip container sync |

View File

@@ -1,8 +1,9 @@
---
name: cmdb topology
description: Generate infrastructure topology diagrams from NetBox data
---
# CMDB Topology Visualization
# /cmdb topology
Generate Mermaid diagrams showing infrastructure topology from NetBox.
@@ -15,7 +16,7 @@ Generate Mermaid diagrams showing infrastructure topology from NetBox.
## Usage
```
/cmdb-topology <view> [scope]
/cmdb topology <view> [scope]
```
**Views:**
@@ -43,11 +44,11 @@ Always provide:
## Examples
- `/cmdb-topology rack server-rack-01` - Rack elevation
- `/cmdb-topology network` - All network connections
- `/cmdb-topology network Home` - Network for Home site
- `/cmdb-topology site Headquarters` - Site overview
- `/cmdb-topology full` - Full infrastructure
- `/cmdb topology rack server-rack-01` - Rack elevation
- `/cmdb topology network` - All network connections
- `/cmdb topology network Home` - Network for Home site
- `/cmdb topology site Headquarters` - Site overview
- `/cmdb topology full` - Full infrastructure
## User Request

View File

@@ -0,0 +1,23 @@
---
description: NetBox CMDB infrastructure management
---
# /cmdb
NetBox CMDB integration for infrastructure management.
## Sub-commands
| Sub-command | Description |
|-------------|-------------|
| `/cmdb search` | Search NetBox for devices, IPs, sites |
| `/cmdb device` | Manage network devices (create, view, update, delete) |
| `/cmdb ip` | Manage IP addresses and prefixes |
| `/cmdb site` | Manage sites, locations, racks, and regions |
| `/cmdb audit` | Data quality analysis (VMs, devices, naming, roles) |
| `/cmdb register` | Register current machine into NetBox |
| `/cmdb sync` | Sync machine state with NetBox (detect drift) |
| `/cmdb topology` | Infrastructure topology diagrams |
| `/cmdb change-audit` | NetBox audit trail queries with filtering |
| `/cmdb ip-conflicts` | Detect IP conflicts and overlapping prefixes |
| `/cmdb setup` | Setup wizard for NetBox MCP server |

View File

@@ -1,16 +1,5 @@
{
"hooks": {
"SessionStart": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/startup-check.sh"
}
]
}
],
"PreToolUse": [
{
"matcher": "mcp__plugin_cmdb-assistant_netbox__virt_create|mcp__plugin_cmdb-assistant_netbox__virt_update|mcp__plugin_cmdb-assistant_netbox__dcim_create|mcp__plugin_cmdb-assistant_netbox__dcim_update",

View File

@@ -1,83 +0,0 @@
#!/bin/bash
# cmdb-assistant SessionStart hook
# Tests NetBox API connectivity and checks for data quality issues
# All output MUST have [cmdb-assistant] prefix
# Non-blocking: always exits 0
set -euo pipefail
PREFIX="[cmdb-assistant]"
# Load NetBox configuration
NETBOX_CONFIG="$HOME/.config/claude/netbox.env"
if [[ ! -f "$NETBOX_CONFIG" ]]; then
echo "$PREFIX NetBox not configured - run /cmdb-assistant:initial-setup"
exit 0
fi
# Source config
source "$NETBOX_CONFIG"
# Validate required variables
if [[ -z "${NETBOX_API_URL:-}" ]] || [[ -z "${NETBOX_API_TOKEN:-}" ]]; then
echo "$PREFIX Missing NETBOX_API_URL or NETBOX_API_TOKEN in config"
exit 0
fi
# Helper function to make authenticated API calls
# Token passed via curl config to avoid exposure in process listings
netbox_curl() {
local url="$1"
curl -s -K - <<EOF 2>/dev/null
-H "Authorization: Token ${NETBOX_API_TOKEN}"
-H "Accept: application/json"
url = "${url}"
EOF
}
# Quick API connectivity test (5s timeout)
HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -m 5 -K - <<EOF 2>/dev/null || echo "000"
-H "Authorization: Token ${NETBOX_API_TOKEN}"
-H "Accept: application/json"
url = "${NETBOX_API_URL}/"
EOF
)
if [[ "$HTTP_CODE" == "000" ]]; then
echo "$PREFIX NetBox API unreachable (timeout/connection error)"
exit 0
elif [[ "$HTTP_CODE" != "200" ]]; then
echo "$PREFIX NetBox API returned HTTP $HTTP_CODE - check credentials"
exit 0
fi
# Check for VMs without site assignment (data quality)
VMS_RESPONSE=$(curl -s -m 5 -K - <<EOF 2>/dev/null || echo '{"count":0}'
-H "Authorization: Token ${NETBOX_API_TOKEN}"
-H "Accept: application/json"
url = "${NETBOX_API_URL}/virtualization/virtual-machines/?site__isnull=true&limit=1"
EOF
)
VMS_NO_SITE=$(echo "$VMS_RESPONSE" | grep -o '"count":[0-9]*' | cut -d: -f2 || echo "0")
if [[ "$VMS_NO_SITE" -gt 0 ]]; then
echo "$PREFIX $VMS_NO_SITE VMs without site assignment - run /cmdb-audit for details"
fi
# Check for devices without platform
DEVICES_RESPONSE=$(curl -s -m 5 -K - <<EOF 2>/dev/null || echo '{"count":0}'
-H "Authorization: Token ${NETBOX_API_TOKEN}"
-H "Accept: application/json"
url = "${NETBOX_API_URL}/dcim/devices/?platform__isnull=true&limit=1"
EOF
)
DEVICES_NO_PLATFORM=$(echo "$DEVICES_RESPONSE" | grep -o '"count":[0-9]*' | cut -d: -f2 || echo "0")
if [[ "$DEVICES_NO_PLATFORM" -gt 0 ]]; then
echo "$PREFIX $DEVICES_NO_PLATFORM devices without platform - consider updating"
fi
exit 0

View File

@@ -147,8 +147,8 @@ dcim_update_device id=X platform=Y
### Next Steps
- Run `/cmdb-register` to properly register new machines
- Use `/cmdb-sync` to update existing registrations
- Run `/cmdb register` to properly register new machines
- Use `/cmdb sync` to update existing registrations
- Consider bulk updates via NetBox web UI for >10 items
```

View File

@@ -25,7 +25,7 @@ Use commands from `system-discovery` skill to gather:
```
dcim_list_devices name=<hostname>
```
If exists, suggest `/cmdb-sync` instead.
If exists, suggest `/cmdb sync` instead.
2. **Verify/Create site:**
```
@@ -131,7 +131,7 @@ Add journal entry:
extras_create_journal_entry
assigned_object_type="dcim.device"
assigned_object_id=<device_id>
comments="Device registered via /cmdb-register command\n\nDiscovered:\n- X network interfaces\n- Y IP addresses\n- Z Docker containers"
comments="Device registered via /cmdb register command\n\nDiscovered:\n- X network interfaces\n- Y IP addresses\n- Z Docker containers"
```
## Summary Report Template
@@ -162,8 +162,8 @@ extras_create_journal_entry
| media_jellyfin | Media Server | 2.0 | 2048MB | Active |
### Next Steps
- Run `/cmdb-sync` periodically to keep data current
- Run `/cmdb-audit` to check data quality
- Run `/cmdb sync` periodically to keep data current
- Run `/cmdb audit` to check data quality
- Add tags for classification
```
@@ -171,7 +171,7 @@ extras_create_journal_entry
| Error | Action |
|-------|--------|
| Device already exists | Suggest `/cmdb-sync` or ask to proceed |
| Device already exists | Suggest `/cmdb sync` or ask to proceed |
| Site not found | List available sites, offer to create new |
| Docker not available | Skip container registration, note in summary |
| Permission denied | Note which operations failed, suggest fixes |

View File

@@ -16,7 +16,7 @@ Load these skills:
dcim_list_devices name=<hostname>
```
If not found, suggest `/cmdb-register` first.
If not found, suggest `/cmdb register` first.
If found:
- Store device ID and current field values
@@ -167,7 +167,7 @@ virt_update_vm id=<id> status="offline"
extras_create_journal_entry
assigned_object_type="dcim.device"
assigned_object_id=<device_id>
comments="Device synced via /cmdb-sync command\n\nChanges applied:\n- <list>"
comments="Device synced via /cmdb sync command\n\nChanges applied:\n- <list>"
```
## Sync Modes
@@ -185,7 +185,7 @@ extras_create_journal_entry
| Error | Action |
|-------|--------|
| Device not found | Suggest `/cmdb-register` |
| Device not found | Suggest `/cmdb register` |
| Permission denied | Note which failed, continue others |
| Cluster not found | Offer to create or skip container sync |
| API errors | Log error, continue with remaining |

View File

@@ -14,17 +14,17 @@ Standard visual header for cmdb-assistant commands.
| Command | Context |
|---------|---------|
| `/cmdb-search` | Search |
| `/cmdb-device` | Device Management |
| `/cmdb-ip` | IP Management |
| `/cmdb-site` | Site Management |
| `/cmdb-audit` | Data Quality Audit |
| `/cmdb-register` | Machine Registration |
| `/cmdb-sync` | Machine Sync |
| `/cmdb-topology` | Topology |
| `/change-audit` | Change Audit |
| `/ip-conflicts` | IP Conflict Detection |
| `/cmdb-setup` | Setup Wizard |
| `/cmdb search` | Search |
| `/cmdb device` | Device Management |
| `/cmdb ip` | IP Management |
| `/cmdb site` | Site Management |
| `/cmdb audit` | Data Quality Audit |
| `/cmdb register` | Machine Registration |
| `/cmdb sync` | Machine Sync |
| `/cmdb topology` | Topology |
| `/cmdb change-audit` | Change Audit |
| `/cmdb ip-conflicts` | IP Conflict Detection |
| `/cmdb setup` | Setup Wizard |
| Agent mode | Infrastructure Management |
## Usage

View File

@@ -16,11 +16,11 @@ PreToolUse hooks scan all code changes for:
Critical issues are blocked. Warnings are noted but allowed.
### Commands
- `/security-scan` - Full project security audit
- `/refactor <target>` - Apply refactoring pattern
- `/refactor-dry <target>` - Preview refactoring opportunities
- `/sentinel scan` - Full project security audit
- `/sentinel refactor <target>` - Apply refactoring pattern
- `/sentinel refactor-dry <target>` - Preview refactoring opportunities
### Severity Levels
- 🔴 Critical: Must fix immediately
- 🟠 High: Fix before release
- 🟡 Medium: Improve when possible
- Critical: Must fix immediately
- High: Fix before release
- Medium: Improve when possible

View File

@@ -1,8 +1,9 @@
---
name: sentinel refactor-dry
description: Preview refactoring changes without applying them
---
# Refactor Dry Run
# /sentinel refactor-dry
Analyze and preview refactoring opportunities without making changes.
@@ -16,7 +17,7 @@ Analyze and preview refactoring opportunities without making changes.
## Usage
```
/refactor-dry <target> [--all]
/sentinel refactor-dry <target> [--all]
```
**Target:** File path, function name, or "." for current file
@@ -41,7 +42,7 @@ Analyze and preview refactoring opportunities without making changes.
### Recommended (High Impact, Low Risk)
1. **pattern** at lines X-Y
- Impact: High | Risk: Low
- Run: `/refactor <target> --pattern=<pattern>`
- Run: `/sentinel refactor <target> --pattern=<pattern>`
### Optional
- Lower priority items

View File

@@ -1,8 +1,9 @@
---
name: sentinel refactor
description: Apply refactoring patterns to improve code structure and maintainability
---
# Refactor
# /sentinel refactor
Apply refactoring transformations to specified code.
@@ -16,7 +17,7 @@ Apply refactoring transformations to specified code.
## Usage
```
/refactor <target> [--pattern=<pattern>]
/sentinel refactor <target> [--pattern=<pattern>]
```
**Target:** File path, function name, or "." for current context

View File

@@ -1,8 +1,9 @@
---
name: sentinel scan
description: Full security audit of codebase - scans all files for vulnerability patterns
---
# Security Scan
# /sentinel scan
Comprehensive security audit of the project.

View File

@@ -0,0 +1,15 @@
---
description: Security scanning and code refactoring
---
# /sentinel
Security scanning and safe code refactoring tools.
## Sub-commands
| Sub-command | Description |
|-------------|-------------|
| `/sentinel scan` | Full security audit (SQL injection, XSS, secrets, etc.) |
| `/sentinel refactor` | Apply refactoring patterns to improve code |
| `/sentinel refactor-dry` | Preview refactoring without applying changes |

View File

@@ -60,7 +60,7 @@ High impact, low risk opportunities:
- Description of the change
- Impact: High/Medium/Low (specific metric improvement)
- Risk: Low/Medium/High (why)
- Run: `/refactor <target> --pattern=<pattern>`
- Run: `/sentinel refactor <target> --pattern=<pattern>`
```
### Optional Section

View File

@@ -91,7 +91,7 @@ You are an agent definition validator. Your role is to verify that a specific ag
## Example Interaction
**User**: /check-agent Orchestrator
**User**: /cv check-agent Orchestrator
**Agent**:
1. Parses CLAUDE.md, finds Orchestrator agent
@@ -101,7 +101,7 @@ You are an agent definition validator. Your role is to verify that a specific ag
5. Validates data flow: no data producers/consumers used
6. Reports: "Agent Orchestrator: VALID - all 3 tool references found"
**User**: /check-agent InvalidAgent
**User**: /cv check-agent InvalidAgent
**Agent**:
1. Parses CLAUDE.md, agent not found

View File

@@ -93,7 +93,7 @@ You are a contract validation specialist. Your role is to perform comprehensive
## Example Interaction
**User**: /validate-contracts ~/claude-plugins-work
**User**: /cv validate ~/claude-plugins-work
**Agent**:
1. Discovers 12 plugins in marketplace

View File

@@ -13,15 +13,15 @@ This marketplace uses the contract-validator plugin for cross-plugin compatibili
| Command | Purpose |
|---------|---------|
| `/validate-contracts` | Full marketplace compatibility validation |
| `/check-agent` | Validate single agent definition |
| `/list-interfaces` | Show all plugin interfaces |
| `/cv validate` | Full marketplace compatibility validation |
| `/cv check-agent` | Validate single agent definition |
| `/cv list-interfaces` | Show all plugin interfaces |
### Validation Workflow
Run before merging plugin changes:
1. `/validate-contracts` - Check for conflicts
1. `/cv validate` - Check for conflicts
2. Review errors (must fix) and warnings (should review)
3. Fix issues before merging
@@ -91,7 +91,7 @@ Avoid generic names that may conflict:
| `/setup` | Setup wizard |
# GOOD - Plugin-specific prefix
| `/data-setup` | Data platform setup wizard |
| `/data setup` | Data platform setup wizard |
```
### Document All Tools
@@ -125,20 +125,20 @@ This agent uses tools from:
```
# Before merging new plugin
/validate-contracts
/cv validate
# Check specific agent after changes
/check-agent Orchestrator
/cv check-agent Orchestrator
```
### Plugin Development
```
# See what interfaces exist
/list-interfaces
/cv list-interfaces
# After adding new command, verify no conflicts
/validate-contracts
/cv validate
```
### CI/CD Integration
@@ -148,5 +148,5 @@ Add to your pipeline:
```yaml
- name: Validate Plugin Contracts
run: |
claude --skill contract-validator:validate-contracts --args "${{ github.workspace }}"
claude --skill contract-validator:cv-validate --args "${{ github.workspace }}"
```

View File

@@ -1,4 +1,8 @@
# /check-agent - Validate Agent Definition
---
name: cv check-agent
---
# /cv check-agent
## Skills to Load
- skills/visual-output.md
@@ -9,7 +13,7 @@
## Usage
```
/check-agent <agent_name> [claude_md_path]
/cv check-agent <agent_name> [claude_md_path]
```
## Parameters
@@ -38,7 +42,7 @@
## Examples
```
/check-agent Planner
/check-agent Orchestrator ./CLAUDE.md
/check-agent data-analysis ~/project/CLAUDE.md
/cv check-agent Planner
/cv check-agent Orchestrator ./CLAUDE.md
/cv check-agent data-analysis ~/project/CLAUDE.md
```

View File

@@ -1,4 +1,8 @@
# /dependency-graph - Generate Dependency Visualization
---
name: cv dependency-graph
---
# /cv dependency-graph
## Skills to Load
- skills/visual-output.md
@@ -10,7 +14,7 @@
## Usage
```
/dependency-graph [marketplace_path] [--format <mermaid|text>] [--show-tools]
/cv dependency-graph [marketplace_path] [--format <mermaid|text>] [--show-tools]
```
## Parameters
@@ -41,15 +45,15 @@
## Examples
```
/dependency-graph
/dependency-graph --show-tools
/dependency-graph --format text
/dependency-graph ~/claude-plugins-work
/cv dependency-graph
/cv dependency-graph --show-tools
/cv dependency-graph --format text
/cv dependency-graph ~/claude-plugins-work
```
## Integration
Use with `/validate-contracts`:
1. Run `/dependency-graph` to visualize
2. Run `/validate-contracts` to find issues
Use with `/cv validate`:
1. Run `/cv dependency-graph` to visualize
2. Run `/cv validate` to find issues
3. Fix and regenerate

View File

@@ -1,4 +1,8 @@
# /list-interfaces - Show Plugin Interfaces
---
name: cv list-interfaces
---
# /cv list-interfaces
## Skills to Load
- skills/visual-output.md
@@ -9,7 +13,7 @@
## Usage
```
/list-interfaces [marketplace_path]
/cv list-interfaces [marketplace_path]
```
## Parameters
@@ -41,6 +45,6 @@
## Examples
```
/list-interfaces
/list-interfaces ~/claude-plugins-work
/cv list-interfaces
/cv list-interfaces ~/claude-plugins-work
```

View File

@@ -1,8 +1,9 @@
---
name: cv setup
description: Interactive setup wizard for contract-validator plugin
---
# /cv-setup - Contract Validator Setup Wizard
# /cv setup
## Skills to Load
- skills/visual-output.md
@@ -40,9 +41,9 @@ description: Interactive setup wizard for contract-validator plugin
## Post-Setup Commands
- `/validate-contracts` - Full marketplace validation
- `/check-agent` - Validate single agent
- `/list-interfaces` - Show all plugin interfaces
- `/cv validate` - Full marketplace validation
- `/cv check-agent` - Validate single agent
- `/cv list-interfaces` - Show all plugin interfaces
## No Configuration Required

View File

@@ -0,0 +1,48 @@
---
name: cv status
description: Marketplace-wide health check across all installed plugins
---
# /cv status
## Purpose
Quick health check showing installed plugin status. For each marketplace plugin, reports installation state, MCP connectivity, and configuration status.
## Usage
```
/cv status # Full status table
/cv status --plugin projman # Single plugin check
```
## Workflow
### Step 1: Enumerate Plugins
Read `.claude-plugin/marketplace.json` to get the full plugin list.
### Step 2: Check Each Plugin
For each plugin, verify:
- **Installed:** `plugin.json` exists and is valid JSON
- **MCP Connected:** If plugin has MCP servers (check `metadata.json`), verify server is responding
- **Configured:** Required config files present
- **Version:** Read from `plugin.json`
- **Domain:** Read from `plugin.json`
### Step 3: Display Results
```
| Plugin | Domain | Version | Installed | MCP | Configured |
|--------------------------|--------|---------|-----------|-----|------------|
| projman | core | 3.4.0 | Y | Y | Y |
| git-flow | core | 1.2.0 | Y | - | Y |
| cmdb-assistant | ops | 1.2.0 | Y | N | N |
Summary: 12/12 installed, 4/5 MCP connected, 11/12 configured
```
## Notes
- MCP column shows `-` for plugins without MCP servers
- `N` in MCP means the server is defined but not responding
- `N` in Configured means the setup check found issues

View File

@@ -1,4 +1,8 @@
# /validate-contracts - Full Contract Validation
---
name: cv validate
---
# /cv validate
## Skills to Load
- skills/visual-output.md
@@ -10,7 +14,7 @@
## Usage
```
/validate-contracts [marketplace_path]
/cv validate [marketplace_path]
```
## Parameters
@@ -40,6 +44,6 @@
## Examples
```
/validate-contracts
/validate-contracts ~/claude-plugins-work
/cv validate
/cv validate ~/claude-plugins-work
```

View File

@@ -0,0 +1,18 @@
---
description: Cross-plugin compatibility validation
---
# /cv
Cross-plugin compatibility validation and agent verification.
## Sub-commands
| Sub-command | Description |
|-------------|-------------|
| `/cv validate` | Full marketplace compatibility validation |
| `/cv check-agent` | Validate single agent definition |
| `/cv list-interfaces` | Show all plugin interfaces |
| `/cv dependency-graph` | Mermaid visualization of plugin dependencies |
| `/cv setup` | Setup wizard for contract-validator MCP |
| `/cv status` | Marketplace-wide health check |

View File

@@ -1,195 +0,0 @@
#!/bin/bash
# contract-validator SessionStart auto-validate hook
# Validates plugin contracts only when plugin files have changed since last check
# All output MUST have [contract-validator] prefix
PREFIX="[contract-validator]"
# ============================================================================
# Configuration
# ============================================================================
# Enable/disable auto-check (default: true)
AUTO_CHECK="${CONTRACT_VALIDATOR_AUTO_CHECK:-true}"
# Cache location for storing last check hash
CACHE_DIR="$HOME/.cache/claude-plugins/contract-validator"
HASH_FILE="$CACHE_DIR/last-check.hash"
# Marketplace location (installed plugins)
MARKETPLACE_PATH="$HOME/.claude/plugins/marketplaces/leo-claude-mktplace"
# ============================================================================
# Early exit if disabled
# ============================================================================
if [[ "$AUTO_CHECK" != "true" ]]; then
exit 0
fi
# ============================================================================
# Smart mode: Check if plugin files have changed
# ============================================================================
# Function to compute hash of all plugin manifest files
compute_plugin_hash() {
local hash_input=""
if [[ -d "$MARKETPLACE_PATH/plugins" ]]; then
# Hash all plugin.json, hooks.json, and agent files
while IFS= read -r -d '' file; do
if [[ -f "$file" ]]; then
hash_input+="$(md5sum "$file" 2>/dev/null | cut -d' ' -f1)"
fi
done < <(find "$MARKETPLACE_PATH/plugins" \
\( -name "plugin.json" -o -name "hooks.json" -o -name "*.md" -path "*/agents/*" \) \
-print0 2>/dev/null | sort -z)
fi
# Also include marketplace.json
if [[ -f "$MARKETPLACE_PATH/.claude-plugin/marketplace.json" ]]; then
hash_input+="$(md5sum "$MARKETPLACE_PATH/.claude-plugin/marketplace.json" 2>/dev/null | cut -d' ' -f1)"
fi
# Compute final hash
echo "$hash_input" | md5sum | cut -d' ' -f1
}
# Ensure cache directory exists
mkdir -p "$CACHE_DIR" 2>/dev/null
# Compute current hash
CURRENT_HASH=$(compute_plugin_hash)
# Check if we have a previous hash
if [[ -f "$HASH_FILE" ]]; then
PREVIOUS_HASH=$(cat "$HASH_FILE" 2>/dev/null)
# If hashes match, no changes - skip validation
if [[ "$CURRENT_HASH" == "$PREVIOUS_HASH" ]]; then
exit 0
fi
fi
# ============================================================================
# Run validation (hashes differ or no cache)
# ============================================================================
ISSUES_FOUND=0
WARNINGS=""
# Function to add warning
add_warning() {
WARNINGS+=" - $1"$'\n'
((ISSUES_FOUND++))
}
# 1. Check all installed plugins have valid plugin.json
if [[ -d "$MARKETPLACE_PATH/plugins" ]]; then
for plugin_dir in "$MARKETPLACE_PATH/plugins"/*/; do
if [[ -d "$plugin_dir" ]]; then
plugin_name=$(basename "$plugin_dir")
plugin_json="$plugin_dir/.claude-plugin/plugin.json"
if [[ ! -f "$plugin_json" ]]; then
add_warning "$plugin_name: missing .claude-plugin/plugin.json"
continue
fi
# Basic JSON validation
if ! python3 -c "import json; json.load(open('$plugin_json'))" 2>/dev/null; then
add_warning "$plugin_name: invalid JSON in plugin.json"
continue
fi
# Check required fields
if ! python3 -c "
import json
with open('$plugin_json') as f:
data = json.load(f)
required = ['name', 'version', 'description']
missing = [r for r in required if r not in data]
if missing:
exit(1)
" 2>/dev/null; then
add_warning "$plugin_name: plugin.json missing required fields"
fi
fi
done
fi
# 2. Check hooks.json files are properly formatted
if [[ -d "$MARKETPLACE_PATH/plugins" ]]; then
while IFS= read -r -d '' hooks_file; do
plugin_name=$(basename "$(dirname "$(dirname "$hooks_file")")")
# Validate JSON
if ! python3 -c "import json; json.load(open('$hooks_file'))" 2>/dev/null; then
add_warning "$plugin_name: invalid JSON in hooks/hooks.json"
continue
fi
# Validate hook structure
if ! python3 -c "
import json
with open('$hooks_file') as f:
data = json.load(f)
if 'hooks' not in data:
exit(1)
valid_events = ['PreToolUse', 'PostToolUse', 'UserPromptSubmit', 'SessionStart', 'SessionEnd', 'Notification', 'Stop', 'SubagentStop', 'PreCompact']
for event in data['hooks']:
if event not in valid_events:
exit(1)
for hook in data['hooks'][event]:
# Support both flat structure (type at top) and nested structure (matcher + hooks array)
if 'type' in hook:
# Flat structure: {type: 'command', command: '...'}
pass
elif 'matcher' in hook and 'hooks' in hook:
# Nested structure: {matcher: '...', hooks: [{type: 'command', ...}]}
for nested_hook in hook['hooks']:
if 'type' not in nested_hook:
exit(1)
else:
exit(1)
" 2>/dev/null; then
add_warning "$plugin_name: hooks.json has invalid structure or events"
fi
done < <(find "$MARKETPLACE_PATH/plugins" -path "*/hooks/hooks.json" -print0 2>/dev/null)
fi
# 3. Check agent references are valid (agent files exist and are markdown)
if [[ -d "$MARKETPLACE_PATH/plugins" ]]; then
while IFS= read -r -d '' agent_file; do
plugin_name=$(basename "$(dirname "$(dirname "$agent_file")")")
agent_name=$(basename "$agent_file")
# Check file is not empty
if [[ ! -s "$agent_file" ]]; then
add_warning "$plugin_name: empty agent file $agent_name"
continue
fi
# Check file has markdown content (at least a header)
if ! grep -q '^#' "$agent_file" 2>/dev/null; then
add_warning "$plugin_name: agent $agent_name missing markdown header"
fi
done < <(find "$MARKETPLACE_PATH/plugins" -path "*/agents/*.md" -print0 2>/dev/null)
fi
# ============================================================================
# Store new hash and report results
# ============================================================================
# Always store the new hash (even if issues found - we don't want to recheck)
echo "$CURRENT_HASH" > "$HASH_FILE"
# Report any issues found (non-blocking warning)
if [[ $ISSUES_FOUND -gt 0 ]]; then
echo "$PREFIX Plugin contract validation found $ISSUES_FOUND issue(s):"
echo "$WARNINGS"
echo "$PREFIX Run /validate-contracts for full details"
fi
# Always exit 0 (non-blocking)
exit 0

View File

@@ -1,174 +0,0 @@
#!/bin/bash
# contract-validator breaking change detection hook
# Warns when plugin interface changes might break consumers
# This is a PostToolUse hook - non-blocking, warnings only
PREFIX="[contract-validator]"
# Check if warnings are enabled (default: true)
if [[ "${CONTRACT_VALIDATOR_BREAKING_WARN:-true}" != "true" ]]; then
exit 0
fi
# Read tool input from stdin
INPUT=$(cat)
# Extract file_path from JSON input
FILE_PATH=$(echo "$INPUT" | grep -o '"file_path"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/.*"file_path"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
# If no file_path found, exit silently
if [ -z "$FILE_PATH" ]; then
exit 0
fi
# Check if file is a plugin interface file
is_interface_file() {
local file="$1"
case "$file" in
*/plugin.json) return 0 ;;
*/.claude-plugin/plugin.json) return 0 ;;
*/hooks.json) return 0 ;;
*/hooks/hooks.json) return 0 ;;
*/.mcp.json) return 0 ;;
*/agents/*.md) return 0 ;;
*/commands/*.md) return 0 ;;
*/skills/*.md) return 0 ;;
esac
return 1
}
# Exit if not an interface file
if ! is_interface_file "$FILE_PATH"; then
exit 0
fi
# Check if file exists and is in a git repo
if [[ ! -f "$FILE_PATH" ]]; then
exit 0
fi
# Get the directory containing the file
FILE_DIR=$(dirname "$FILE_PATH")
FILE_NAME=$(basename "$FILE_PATH")
# Try to get the previous version from git
cd "$FILE_DIR" 2>/dev/null || exit 0
# Check if we're in a git repo
if ! git rev-parse --git-dir > /dev/null 2>&1; then
exit 0
fi
# Get previous version (HEAD version before current changes)
PREV_CONTENT=$(git show HEAD:"$FILE_PATH" 2>/dev/null || echo "")
# If no previous version, this is a new file - no breaking changes possible
if [ -z "$PREV_CONTENT" ]; then
exit 0
fi
# Read current content
CURR_CONTENT=$(cat "$FILE_PATH" 2>/dev/null || echo "")
if [ -z "$CURR_CONTENT" ]; then
exit 0
fi
BREAKING_CHANGES=()
# Detect breaking changes based on file type
case "$FILE_PATH" in
*/plugin.json|*/.claude-plugin/plugin.json)
# Check for removed or renamed fields in plugin.json
# Check if name changed
PREV_NAME=$(echo "$PREV_CONTENT" | grep -o '"name"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1)
CURR_NAME=$(echo "$CURR_CONTENT" | grep -o '"name"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1)
if [ -n "$PREV_NAME" ] && [ "$PREV_NAME" != "$CURR_NAME" ]; then
BREAKING_CHANGES+=("Plugin name changed - consumers may need updates")
fi
# Check if version had major bump (semantic versioning)
PREV_VER=$(echo "$PREV_CONTENT" | grep -o '"version"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"\([0-9]*\)\..*/\1/')
CURR_VER=$(echo "$CURR_CONTENT" | grep -o '"version"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"\([0-9]*\)\..*/\1/')
if [ -n "$PREV_VER" ] && [ -n "$CURR_VER" ] && [ "$CURR_VER" -gt "$PREV_VER" ] 2>/dev/null; then
BREAKING_CHANGES+=("Major version bump detected - verify breaking changes documented")
fi
;;
*/hooks.json|*/hooks/hooks.json)
# Check for removed hook events
PREV_EVENTS=$(echo "$PREV_CONTENT" | grep -oE '"(PreToolUse|PostToolUse|UserPromptSubmit|SessionStart|SessionEnd|Notification|Stop|SubagentStop|PreCompact)"' | sort -u)
CURR_EVENTS=$(echo "$CURR_CONTENT" | grep -oE '"(PreToolUse|PostToolUse|UserPromptSubmit|SessionStart|SessionEnd|Notification|Stop|SubagentStop|PreCompact)"' | sort -u)
# Find removed events
REMOVED_EVENTS=$(comm -23 <(echo "$PREV_EVENTS") <(echo "$CURR_EVENTS") 2>/dev/null)
if [ -n "$REMOVED_EVENTS" ]; then
BREAKING_CHANGES+=("Hook events removed: $(echo $REMOVED_EVENTS | tr '\n' ' ')")
fi
# Check for changed matchers
PREV_MATCHERS=$(echo "$PREV_CONTENT" | grep -o '"matcher"[[:space:]]*:[[:space:]]*"[^"]*"' | sort -u)
CURR_MATCHERS=$(echo "$CURR_CONTENT" | grep -o '"matcher"[[:space:]]*:[[:space:]]*"[^"]*"' | sort -u)
if [ "$PREV_MATCHERS" != "$CURR_MATCHERS" ]; then
BREAKING_CHANGES+=("Hook matchers changed - verify tool coverage")
fi
;;
*/.mcp.json)
# Check for removed MCP servers
PREV_SERVERS=$(echo "$PREV_CONTENT" | grep -o '"[^"]*"[[:space:]]*:' | grep -v "mcpServers" | sort -u)
CURR_SERVERS=$(echo "$CURR_CONTENT" | grep -o '"[^"]*"[[:space:]]*:' | grep -v "mcpServers" | sort -u)
REMOVED_SERVERS=$(comm -23 <(echo "$PREV_SERVERS") <(echo "$CURR_SERVERS") 2>/dev/null)
if [ -n "$REMOVED_SERVERS" ]; then
BREAKING_CHANGES+=("MCP servers removed - tools may be unavailable")
fi
;;
*/agents/*.md)
# Check if agent file was significantly reduced (might indicate removal of capabilities)
PREV_LINES=$(echo "$PREV_CONTENT" | wc -l)
CURR_LINES=$(echo "$CURR_CONTENT" | wc -l)
# If more than 50% reduction, warn
if [ "$PREV_LINES" -gt 10 ] && [ "$CURR_LINES" -lt $((PREV_LINES / 2)) ]; then
BREAKING_CHANGES+=("Agent definition significantly reduced - capabilities may be removed")
fi
# Check if agent name/description changed in frontmatter
PREV_DESC=$(echo "$PREV_CONTENT" | head -20 | grep -i "description" | head -1)
CURR_DESC=$(echo "$CURR_CONTENT" | head -20 | grep -i "description" | head -1)
if [ -n "$PREV_DESC" ] && [ "$PREV_DESC" != "$CURR_DESC" ]; then
BREAKING_CHANGES+=("Agent description changed - verify consumer expectations")
fi
;;
*/commands/*.md|*/skills/*.md)
# Check if command/skill was significantly changed
PREV_LINES=$(echo "$PREV_CONTENT" | wc -l)
CURR_LINES=$(echo "$CURR_CONTENT" | wc -l)
if [ "$PREV_LINES" -gt 10 ] && [ "$CURR_LINES" -lt $((PREV_LINES / 2)) ]; then
BREAKING_CHANGES+=("Command/skill significantly reduced - behavior may change")
fi
;;
esac
# Output warnings if any breaking changes detected
if [[ ${#BREAKING_CHANGES[@]} -gt 0 ]]; then
echo ""
echo "$PREFIX WARNING: Potential breaking changes in $(basename "$FILE_PATH")"
echo "$PREFIX ============================================"
for change in "${BREAKING_CHANGES[@]}"; do
echo "$PREFIX - $change"
done
echo "$PREFIX ============================================"
echo "$PREFIX Consider updating CHANGELOG and notifying consumers"
echo ""
fi
# Always exit 0 - non-blocking
exit 0

View File

@@ -1,26 +0,0 @@
{
"hooks": {
"SessionStart": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/auto-validate.sh"
}
]
}
],
"PostToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/breaking-change-check.sh"
}
]
}
]
}
}

View File

@@ -65,6 +65,6 @@ Available MCP tools for contract-validator operations.
## Error Handling
If MCP tools fail:
1. Check if `/cv-setup` has been run
1. Check if `/cv setup` has been run
2. Verify session was restarted after setup
3. Check MCP server venv exists and is valid

View File

@@ -23,8 +23,8 @@ You are a strict data integrity auditor. Your role is to review code for proper
## Trigger Conditions
Activate this agent when:
- User runs `/data-review <path>`
- User runs `/data-gate <path>`
- User runs `/data review <path>`
- User runs `/data gate <path>`
- Projman orchestrator requests data domain gate check
- Code review includes database operations, dbt models, or data pipelines
@@ -78,7 +78,7 @@ Activate this agent when:
### Review Mode (default)
Triggered by `/data-review <path>`
Triggered by `/data review <path>`
**Characteristics:**
- Produces detailed report with all findings
@@ -89,7 +89,7 @@ Triggered by `/data-review <path>`
### Gate Mode
Triggered by `/data-gate <path>` or projman orchestrator domain gate
Triggered by `/data gate <path>` or projman orchestrator domain gate
**Characteristics:**
- Binary PASS/FAIL output
@@ -203,7 +203,7 @@ Blocking Issues (2):
2. portfolio_app/toronto/loaders/census.py:67 - References table 'census_raw' which does not exist
Fix: Table was renamed to 'census_demographics' in migration 003.
Run /data-review for full audit report.
Run /data review for full audit report.
```
### Review Mode Output
@@ -292,7 +292,7 @@ When called as a domain gate by projman orchestrator:
## Example Interactions
**User**: `/data-review dbt/models/staging/`
**User**: `/data review dbt/models/staging/`
**Agent**:
1. Scans all .sql files in staging/
2. Runs dbt_parse to validate project
@@ -301,7 +301,7 @@ When called as a domain gate by projman orchestrator:
5. Cross-references test coverage
6. Returns detailed report
**User**: `/data-gate portfolio_app/toronto/`
**User**: `/data gate portfolio_app/toronto/`
**Agent**:
1. Scans for Python files with pg_query/pg_execute
2. Checks if referenced tables exist

View File

@@ -18,12 +18,12 @@ This project uses the data-platform plugin for data engineering workflows.
| Command | Purpose |
|---------|---------|
| `/data-ingest` | Load data from files or database |
| `/data-profile` | Generate statistical profile |
| `/data-schema` | Show schema information |
| `/data-explain` | Explain dbt model |
| `/data-lineage` | Show data lineage |
| `/data-run` | Execute dbt models |
| `/data ingest` | Load data from files or database |
| `/data profile` | Generate statistical profile |
| `/data schema` | Show schema information |
| `/data explain` | Explain dbt model |
| `/data lineage` | Show data lineage |
| `/data run` | Execute dbt models |
### data_ref Convention
@@ -36,9 +36,9 @@ DataFrames are stored with references. Use meaningful names:
### dbt Workflow
1. Always validate before running: `/data-run` includes automatic `dbt_parse`
1. Always validate before running: `/data run` includes automatic `dbt_parse`
2. For dbt 1.9+, check for deprecated syntax before commits
3. Use `/data-lineage` to understand impact of changes
3. Use `/data lineage` to understand impact of changes
### Database Access
@@ -69,22 +69,22 @@ DATA_PLATFORM_MAX_ROWS=100000
### Data Exploration
```
/data-ingest data/raw_customers.csv
/data-profile raw_customers
/data-schema
/data ingest data/raw_customers.csv
/data profile raw_customers
/data schema
```
### ETL Development
```
/data-schema orders # Understand source
/data-explain stg_orders # Understand transformation
/data-run stg_orders # Test the model
/data-lineage fct_orders # Check downstream impact
/data schema orders # Understand source
/data explain stg_orders # Understand transformation
/data run stg_orders # Test the model
/data lineage fct_orders # Check downstream impact
```
### Database Analysis
```
/data-schema # List all tables
/data schema # List all tables
pg_columns orders # Detailed schema
st_tables # Find spatial data
```

View File

@@ -1,4 +1,8 @@
# /dbt-test - Run dbt Tests
---
name: data dbt-test
---
# /data dbt-test - Run dbt Tests
## Skills to Load
- skills/dbt-workflow.md
@@ -12,7 +16,7 @@ Display header: `DATA-PLATFORM - dbt Tests`
## Usage
```
/dbt-test [selection] [--warn-only]
/data dbt-test [selection] [--warn-only]
```
## Workflow
@@ -32,9 +36,9 @@ Execute `skills/dbt-workflow.md` test workflow:
## Examples
```
/dbt-test # Run all tests
/dbt-test dim_customers # Tests for specific model
/dbt-test tag:critical # Run critical tests only
/data dbt-test # Run all tests
/data dbt-test dim_customers # Tests for specific model
/data dbt-test tag:critical # Run critical tests only
```
## Required MCP Tools

View File

@@ -1,4 +1,8 @@
# /data-explain - dbt Model Explanation
---
name: data explain
---
# /data explain - dbt Model Explanation
## Skills to Load
- skills/dbt-workflow.md
@@ -13,7 +17,7 @@ Display header: `DATA-PLATFORM - Model Explanation`
## Usage
```
/data-explain <model_name>
/data explain <model_name>
```
## Workflow
@@ -26,8 +30,8 @@ Display header: `DATA-PLATFORM - Model Explanation`
## Examples
```
/data-explain dim_customers
/data-explain fct_orders
/data explain dim_customers
/data explain fct_orders
```
## Required MCP Tools

View File

@@ -1,4 +1,5 @@
---
name: data gate
description: Data integrity compliance gate (pass/fail) for sprint execution
gate_contract: v1
arguments:
@@ -7,21 +8,21 @@ arguments:
required: true
---
# /data-gate
# /data gate
Binary pass/fail validation for data integrity compliance. Used by projman orchestrator during sprint execution to gate issue completion.
## Usage
```
/data-gate <path>
/data gate <path>
```
**Examples:**
```
/data-gate ./dbt/models/staging/
/data-gate ./portfolio_app/toronto/parsers/
/data-gate ./dbt/
/data gate ./dbt/models/staging/
/data gate ./portfolio_app/toronto/parsers/
/data gate ./dbt/
```
## What It Does
@@ -63,7 +64,7 @@ Blocking Issues (2):
2. portfolio_app/toronto/loaders/census.py:67 - References table 'census_raw' which does not exist
Fix: Table was renamed to 'census_demographics' in migration 003.
Run /data-review for full audit report.
Run /data review for full audit report.
```
## Integration with projman
@@ -78,9 +79,9 @@ This command is automatically invoked by the projman orchestrator when:
- PASS: Issue can be marked complete
- FAIL: Issue stays open, blocker comment added with failure details
## Differences from /data-review
## Differences from /data review
| Aspect | /data-gate | /data-review |
| Aspect | /data gate | /data review |
|--------|------------|--------------|
| Output | Binary PASS/FAIL | Detailed report with all severities |
| Severity | FAIL only | FAIL + WARN + INFO |
@@ -95,7 +96,7 @@ This command is automatically invoked by the projman orchestrator when:
- **Quick validation**: Fast pass/fail without full report
- **Pre-merge checks**: Verify data changes before integration
For detailed findings including warnings and suggestions, use `/data-review` instead.
For detailed findings including warnings and suggestions, use `/data review` instead.
## Requirements

View File

@@ -1,4 +1,8 @@
# /data-ingest - Data Ingestion
---
name: data ingest
---
# /data ingest - Data Ingestion
## Skills to Load
- skills/mcp-tools-reference.md
@@ -11,7 +15,7 @@ Display header: `DATA-PLATFORM - Ingest`
## Usage
```
/data-ingest [source]
/data ingest [source]
```
## Workflow
@@ -31,9 +35,9 @@ Display header: `DATA-PLATFORM - Ingest`
## Examples
```
/data-ingest data/sales.csv
/data-ingest data/customers.parquet
/data-ingest "SELECT * FROM orders WHERE created_at > '2024-01-01'"
/data ingest data/sales.csv
/data ingest data/customers.parquet
/data ingest "SELECT * FROM orders WHERE created_at > '2024-01-01'"
```
## Required MCP Tools

View File

@@ -1,4 +1,8 @@
# /lineage-viz - Mermaid Lineage Visualization
---
name: data lineage-viz
---
# /data lineage-viz - Mermaid Lineage Visualization
## Skills to Load
- skills/lineage-analysis.md
@@ -12,7 +16,7 @@ Display header: `DATA-PLATFORM - Lineage Visualization`
## Usage
```
/lineage-viz <model_name> [--direction TB|LR] [--depth N]
/data lineage-viz <model_name> [--direction TB|LR] [--depth N]
```
## Workflow
@@ -31,9 +35,9 @@ Display header: `DATA-PLATFORM - Lineage Visualization`
## Examples
```
/lineage-viz dim_customers
/lineage-viz fct_orders --direction TB
/lineage-viz rpt_revenue --depth 2
/data lineage-viz dim_customers
/data lineage-viz fct_orders --direction TB
/data lineage-viz rpt_revenue --depth 2
```
## Required MCP Tools

View File

@@ -1,4 +1,8 @@
# /data-lineage - Data Lineage Visualization
---
name: data lineage
---
# /data lineage - Data Lineage Visualization
## Skills to Load
- skills/lineage-analysis.md
@@ -12,7 +16,7 @@ Display header: `DATA-PLATFORM - Lineage`
## Usage
```
/data-lineage <model_name> [--depth N]
/data lineage <model_name> [--depth N]
```
## Workflow
@@ -25,8 +29,8 @@ Display header: `DATA-PLATFORM - Lineage`
## Examples
```
/data-lineage dim_customers
/data-lineage fct_orders --depth 3
/data lineage dim_customers
/data lineage fct_orders --depth 3
```
## Required MCP Tools

View File

@@ -1,4 +1,8 @@
# /data-profile - Data Profiling
---
name: data profile
---
# /data profile - Data Profiling
## Skills to Load
- skills/data-profiling.md
@@ -12,7 +16,7 @@ Display header: `DATA-PLATFORM - Data Profile`
## Usage
```
/data-profile <data_ref>
/data profile <data_ref>
```
## Workflow
@@ -27,8 +31,8 @@ Execute `skills/data-profiling.md` profiling workflow:
## Examples
```
/data-profile sales_data
/data-profile df_a1b2c3d4
/data profile sales_data
/data profile df_a1b2c3d4
```
## Required MCP Tools

View File

@@ -1,4 +1,8 @@
# /data-quality - Data Quality Assessment
---
name: data quality
---
# /data quality - Data Quality Assessment
## Skills to Load
- skills/data-profiling.md
@@ -12,7 +16,7 @@ Display header: `DATA-PLATFORM - Data Quality`
## Usage
```
/data-quality <data_ref> [--strict]
/data quality <data_ref> [--strict]
```
## Workflow
@@ -33,8 +37,8 @@ Execute `skills/data-profiling.md` quality assessment:
## Examples
```
/data-quality sales_data
/data-quality df_customers --strict
/data quality sales_data
/data quality df_customers --strict
```
## Quality Thresholds

View File

@@ -1,4 +1,5 @@
---
name: data review
description: Audit data integrity, schema validity, and dbt compliance
arguments:
- name: path
@@ -6,21 +7,21 @@ arguments:
required: true
---
# /data-review
# /data review
Comprehensive data integrity audit producing a detailed report with findings at all severity levels. For human review and standalone codebase auditing.
## Usage
```
/data-review <path>
/data review <path>
```
**Examples:**
```
/data-review ./dbt/
/data-review ./portfolio_app/toronto/
/data-review ./dbt/models/marts/
/data review ./dbt/
/data review ./portfolio_app/toronto/
/data review ./dbt/models/marts/
```
## What It Does
@@ -79,46 +80,46 @@ VERDICT: PASS | FAIL (N blocking issues)
### Before Sprint Planning
Audit data layer health to identify tech debt and inform sprint scope.
```
/data-review ./dbt/
/data review ./dbt/
```
### During Code Review
Get detailed data integrity findings alongside code review comments.
```
/data-review ./dbt/models/staging/stg_new_source.sql
/data review ./dbt/models/staging/stg_new_source.sql
```
### After Migrations
Verify schema changes didn't break anything downstream.
```
/data-review ./migrations/
/data review ./migrations/
```
### Periodic Health Checks
Regular data infrastructure audits for proactive maintenance.
```
/data-review ./data_pipeline/
/data review ./data_pipeline/
```
### New Project Onboarding
Understand the current state of data architecture.
```
/data-review .
/data review .
```
## Severity Levels
| Level | Meaning | Gate Impact |
|-------|---------|-------------|
| **FAIL** | Blocking issues that will cause runtime errors | Would block `/data-gate` |
| **FAIL** | Blocking issues that will cause runtime errors | Would block `/data gate` |
| **WARN** | Quality issues that should be addressed | Does not block gate |
| **INFO** | Suggestions for improvement | Does not block gate |
## Differences from /data-gate
## Differences from /data gate
`/data-review` gives you the full picture. `/data-gate` gives the orchestrator a yes/no.
`/data review` gives you the full picture. `/data gate` gives the orchestrator a yes/no.
| Aspect | /data-gate | /data-review |
| Aspect | /data gate | /data review |
|--------|------------|--------------|
| Output | Binary PASS/FAIL | Detailed report |
| Severity | FAIL only | FAIL + WARN + INFO |
@@ -126,8 +127,8 @@ Understand the current state of data architecture.
| Verbosity | Minimal | Comprehensive |
| Speed | Fast (skips INFO) | Thorough |
Use `/data-review` when you want to understand.
Use `/data-gate` when you want to automate.
Use `/data review` when you want to understand.
Use `/data gate` when you want to automate.
## Requirements
@@ -144,6 +145,6 @@ Use `/data-gate` when you want to automate.
## Related Commands
- `/data-gate` - Binary pass/fail for automation
- `/data-lineage` - Visualize dbt model dependencies
- `/data-schema` - Explore database schema
- `/data gate` - Binary pass/fail for automation
- `/data lineage` - Visualize dbt model dependencies
- `/data schema` - Explore database schema

View File

@@ -1,4 +1,8 @@
# /data-run - Execute dbt Models
---
name: data run
---
# /data run - Execute dbt Models
## Skills to Load
- skills/dbt-workflow.md
@@ -12,7 +16,7 @@ Display header: `DATA-PLATFORM - dbt Run`
## Usage
```
/data-run [model_selection] [--full-refresh]
/data run [model_selection] [--full-refresh]
```
## Workflow
@@ -30,11 +34,11 @@ See `skills/dbt-workflow.md` for full selection patterns.
## Examples
```
/data-run # Run all models
/data-run dim_customers # Run specific model
/data-run +fct_orders # Run model and upstream
/data-run tag:daily # Run models with tag
/data-run --full-refresh # Rebuild incremental models
/data run # Run all models
/data run dim_customers # Run specific model
/data run +fct_orders # Run model and upstream
/data run tag:daily # Run models with tag
/data run --full-refresh # Rebuild incremental models
```
## Required MCP Tools

View File

@@ -1,4 +1,8 @@
# /data-schema - Schema Exploration
---
name: data schema
---
# /data schema - Schema Exploration
## Skills to Load
- skills/mcp-tools-reference.md
@@ -11,7 +15,7 @@ Display header: `DATA-PLATFORM - Schema Explorer`
## Usage
```
/data-schema [table_name | data_ref]
/data schema [table_name | data_ref]
```
## Workflow
@@ -30,9 +34,9 @@ Display header: `DATA-PLATFORM - Schema Explorer`
## Examples
```
/data-schema # List all tables and DataFrames
/data-schema customers # Show table schema
/data-schema sales_data # Show DataFrame schema
/data schema # List all tables and DataFrames
/data schema customers # Show table schema
/data schema sales_data # Show DataFrame schema
```
## Required MCP Tools

View File

@@ -1,4 +1,8 @@
# /data-setup - Data Platform Setup Wizard
---
name: data setup
---
# /data setup - Data Platform Setup Wizard
## Skills to Load
- skills/setup-workflow.md
@@ -11,7 +15,7 @@ Display header: `DATA-PLATFORM - Setup Wizard`
## Usage
```
/data-setup
/data setup
```
## Workflow

View File

@@ -0,0 +1,24 @@
---
description: Data engineering tools with pandas, PostgreSQL, and dbt
---
# /data
Data engineering tools with pandas, PostgreSQL/PostGIS, and dbt integration.
## Sub-commands
| Sub-command | Description |
|-------------|-------------|
| `/data ingest` | Load data from CSV, Parquet, JSON into DataFrame |
| `/data profile` | Generate data profiling report with statistics |
| `/data schema` | Explore database schemas, tables, columns |
| `/data explain` | Explain query execution plan |
| `/data lineage` | Show dbt model lineage and dependencies |
| `/data lineage-viz` | dbt lineage visualization as Mermaid diagrams |
| `/data run` | Run dbt models with validation |
| `/data dbt-test` | Formatted dbt test runner with summary |
| `/data quality` | DataFrame quality checks |
| `/data review` | Comprehensive data integrity audits |
| `/data gate` | Binary pass/fail data integrity gates |
| `/data setup` | Setup wizard for data-platform MCP servers |

View File

@@ -1,26 +0,0 @@
{
"hooks": {
"SessionStart": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/startup-check.sh"
}
]
}
],
"PostToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/schema-diff-check.sh"
}
]
}
]
}
}

Some files were not shown because too many files have changed in this diff Show More