Agent Plugins Marketplace
← All plugins

craftsman

v4.11.0

Refuses any edit that breaks your architecture rules, before it reaches disk. A prompt asks; this enforces. SOLID, Clean Architecture, hexagonal, DDD and legacy rescue, with the same rules in your editor and your CI.

CodexClaude Code22 Skills

By Alexandre MalletLicense: Apache-2.035 GitHub starsUpdated 2 days ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
22 skill or MCP entries
Source updated
Sep 21, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install craftsman for Codex and Claude Code

Installs for the current user
codex plugin marketplace add BULDEE/ai-craftsman-superpowers
codex plugin marketplace upgrade ai-craftsman-superpowers
codex plugin add craftsman@ai-craftsman-superpowers

Paste and run these commands in a terminal with Codex. They add and refresh the ai-craftsman-superpowers catalog, then install this plugin.

Compatibility: the page URL and API slug “craftsman-2” remain stable.

  • Codex: craftsman-2@agent-plugin-marketplace → craftsman@ai-craftsman-superpowers

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/BULDEE/ai-craftsman-superpowers

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

craftsman/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/agent-design/SKILL.md
├── skills/challenge/SKILL.md
├── skills/ci/SKILL.md
├── skills/debug/SKILL.md
├── skills/design/SKILL.md
├── skills/git/SKILL.md
├── skills/healthcheck/SKILL.md
├── skills/legacy/SKILL.md
├── skills/loop/SKILL.md
├── skills/metrics/SKILL.md
├── skills/mlops/SKILL.md
├── skills/parallel/SKILL.md
├── skills/plan/SKILL.md
├── skills/rag/SKILL.md
├── skills/refactor/SKILL.md
├── skills/scaffold/SKILL.md
├── skills/setup/SKILL.md
├── skills/spec/SKILL.md
├── skills/team/SKILL.md
├── skills/test/SKILL.md
├── skills/verify/SKILL.md
└── skills/workflow/SKILL.md

Included Skills22

agent-designskills/agent-design/SKILL.md

Design AI agents using the 3P pattern (Perceive/Plan/Perform). Use when building autonomous AI agents or workflows.

challengeskills/challenge/SKILL.md

Senior architecture review and code challenge. Use when reviewing code or PRs for quality, auditing architecture decisions, or responding to code review comments.

ciskills/ci/SKILL.md

CI/CD pipeline integration. Use when setting up or checking CI quality gates, exporting rules to GitHub Actions/GitLab CI/Bitbucket/Jenkins, or verifying pipeline alignment with local rules.

debugskills/debug/SKILL.md

Systematic debugging using ReAct pattern. Use when encountering bugs, errors, unexpected behavior, test failures, or performance issues. Never guess - investigate methodically.

designskills/design/SKILL.md

Senior Domain-Driven Design methodology. Use for creating entities, value objects, aggregates, or designing domain models. Follows a 4-phase process (Understand, Challenge, Recommend, Implement).

gitskills/git/SKILL.md

Safe git workflow with destructive command protection. Use when committing changes, creating branches, managing git workflow, or handling merge conflicts.

healthcheckskills/healthcheck/SKILL.md

Run a comprehensive diagnostic of your Craftsman plugin installation and runtime. Use when troubleshooting plugin issues, after setup, or when session-start reports warnings.

legacyskills/legacy/SKILL.md

Legacy code rescue - audit hotspots, cover with characterization tests, break dependencies, and plan strangler-fig migrations. Use when inheriting, taming, testing, or refactoring an untested/undocumented codebase.

loopskills/loop/SKILL.md

Bounded goal-driven loop over the craftsman verify gate. Use for ratchet campaigns, red-to-green test runs, violation burn-down: any task shaped as act, verify, repeat until a Done-when condition holds. Every iteration re-verifies; the loop stops on green, on no-progress, or when the budget is spent.

metricsskills/metrics/SKILL.md

Quality metrics and local dashboard. Use when reviewing violation trends, session history, correction patterns, or rendering the aggregated multi-repository dashboard (--dashboard).

mlopsskills/mlops/SKILL.md

Audit ML projects for production readiness. Use when reviewing ML pipelines, deployments, or infrastructure against MLOps best practices.

parallelskills/parallel/SKILL.md

Parallel agent orchestration for independent tasks. Use when facing 2+ independent tasks that operate on different files/domains and can be parallelized for efficiency.

planskills/plan/SKILL.md

Structured planning for multi-step tasks. Use when starting features requiring 3+ steps, migrating or refactoring large codebases, or when task complexity clearly exceeds a single change.

ragskills/rag/SKILL.md

Design RAG (Retrieval-Augmented Generation) pipelines. Use when building knowledge bases, document Q&A, or semantic search systems.

refactorskills/refactor/SKILL.md

Systematic refactoring with behavior preservation. Use when improving existing code structure, reducing technical debt, or when code smells are detected.

scaffoldskills/scaffold/SKILL.md

Unified scaffolder for all pack types. Use when creating new entities, use cases, components, hooks, API resources, or custom packs. Types loaded from active packs.

setupskills/setup/SKILL.md

Interactive setup and onboarding. Use on first run, when changing stack/packs, or when healthcheck reports config issues.

specskills/spec/SKILL.md

Specification-first development (BDD/TDD). Use when implementing new features, creating new components, or when requirements need clarification through tests.

teamskills/team/SKILL.md

Multi-agent orchestration with native Claude Code teams. Use when facing 2+ independent tasks needing parallel work, full-stack features requiring backend+frontend agents, code reviews needing multiple specialist perspectives, or security audits.

testskills/test/SKILL.md

Pragmatic testing following Fowler/Martin principles. Use when writing or reviewing tests, deciding what to test, or improving test coverage strategically.

verifyskills/verify/SKILL.md

Evidence-based verification before claiming completion. Use before committing, creating PRs, or claiming a task is done. Never claim success without proof.

workflowskills/workflow/SKILL.md

Flexible development pipeline. Use when starting a new feature, fixing a complex bug, or when you want guided step-by-step methodology: design -> spec -> plan -> implement -> test -> verify -> commit.

Plugin manifests2

.codex-plugin/plugin.json
{
  "name": "craftsman",
  "description": "Refuses any edit that breaks your architecture rules, before it reaches disk. A prompt asks; this enforces. SOLID, Clean Architecture, hexagonal, DDD and legacy rescue, with the same rules in your editor and your CI.",
  "version": "4.11.0",
  "author": {
    "name": "Alexandre Mallet",
    "email": "[email protected]",
    "url": "https://github.com/BULDEE"
  },
  "homepage": "https://github.com/BULDEE/ai-craftsman-superpowers",
  "repository": "https://github.com/BULDEE/ai-craftsman-superpowers",
  "license": "Apache-2.0",
  "keywords": [
    "ddd",
    "domain-driven-design",
    "clean-architecture",
    "tdd",
    "craftsman",
    "software-engineering",
    "code-quality",
    "symfony",
    "react",
    "typescript",
    "php",
    "testing",
    "refactoring",
    "methodology",
    "quality-metrics",
    "static-analysis",
    "sentry",
    "channels"
  ],
  "skills": "./skills",
  "hooks": "./hooks/hooks.json"
}
.claude-plugin/plugin.json
{
  "name": "craftsman",
  "description": "Refuses any edit that breaks your architecture rules, before it reaches disk. A prompt asks; this enforces. SOLID, Clean Architecture, hexagonal, DDD and legacy rescue, with the same rules in your editor and your CI.",
  "version": "4.11.0",
  "author": {
    "name": "Alexandre Mallet",
    "email": "[email protected]",
    "url": "https://github.com/BULDEE"
  },
  "homepage": "https://github.com/BULDEE/ai-craftsman-superpowers",
  "repository": "https://github.com/BULDEE/ai-craftsman-superpowers",
  "license": "Apache-2.0",
  "keywords": [
    "ddd",
    "domain-driven-design",
    "clean-architecture",
    "tdd",
    "craftsman",
    "software-engineering",
    "code-quality",
    "symfony",
    "react",
    "typescript",
    "php",
    "testing",
    "refactoring",
    "methodology",
    "quality-metrics",
    "static-analysis",
    "sentry",
    "channels"
  ],
  "userConfig": {
    "strictness": {
      "type": "string",
      "title": "Strictness Level",
      "description": "Enforcement level: strict (block violations), moderate (block critical only), relaxed (warn only)",
      "default": "strict"
    },
    "stack": {
      "type": "string",
      "title": "Tech Stack",
      "description": "Your tech stack: symfony, react, fullstack or other. Selects the doctrine and the setup hints; every language pack validates its own files whatever the stack says.",
      "default": "fullstack"
    },
    "agent_hooks": {
      "type": "boolean",
      "title": "Agent Hooks",
      "description": "Enable background Haiku verification (DDD verifier on Write/Edit, final architecture review on Stop). Runs headless claude -p subprocesses on the Haiku tier: no main-context cost, wakes the session only when a violation is found. Disable to skip all model-based verification.",
      "default": true
    },
    "packs": {
      "type": "string",
      "title": "Active Packs",
      "description": "Comma-separated pack names to load (e.g., 'symfony,react,ai-ml'). Auto-detected from stack if not set.",
      "default": ""
    },
    "sentry_org": {
      "type": "string",
      "title": "Sentry Organization",
      "description": "Sentry organization slug for error context injection"
    },
    "sentry_project": {
      "type": "string",
      "title": "Sentry Project",
      "description": "Sentry project slug to query errors from"
    },
    "sentry_token": {
      "type": "string",
      "title": "Sentry Token",
      "description": "Sentry auth token (stored securely in keychain)",
      "sensitive": true
    }
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[craftsman on Agent Plugins Marketplace](https://pluginsmp.com/plugins/craftsman-2)