By buldee
Enforce senior craftsman methodology in AI-assisted development: initialize structured sessions for Symfony/React/PHP/TS stacks, orchestrate pipelines from DDD design and Clean Architecture to TDD implementation, testing, architecture reviews, safe git workflows, and commits; spawn expert agent teams for security audits, UI/UX design, docs; track quality metrics and run CI gates.
npx claudepluginhub buldee/ai-craftsman-superpowers --plugin craftsmanExecutes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimSenior architecture review and code challenge. Use when reviewing code or PRs for quality, auditing architecture decisions, or responding to code review comments.
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.
Systematic debugging using ReAct pattern. Use when encountering bugs, errors, unexpected behavior, test failures, or performance issues. Never guess - investigate methodically.
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).
Safe git workflow with destructive command protection. Use when committing changes, creating branches, managing git workflow, or handling merge conflicts.
Run a comprehensive diagnostic of your Craftsman plugin installation and runtime. Use when troubleshooting plugin issues, after setup, or when session-start reports warnings.
../packs/ai-ml/commands/knowledge.md
Quality metrics dashboard. Use when reviewing violation trends, session history, or correction patterns from the local SQLite database.
Parallel agent orchestration for independent tasks. Use when facing 2+ independent tasks that operate on different files/domains and can be parallelized for efficiency.
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.
Systematic refactoring with behavior preservation. Use when improving existing code structure, reducing technical debt, or when code smells are detected.
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.
Interactive setup and onboarding. Use on first run, when changing stack/packs, or when healthcheck reports config issues.
Specification-first development (BDD/TDD). Use when implementing new features, creating new components, or when requirements need clarification through tests.
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.
Pragmatic testing following Fowler/Martin principles. Use when writing or reviewing tests, deciding what to test, or improving test coverage strategically.
Evidence-based verification before claiming completion. Use before committing, creating PRs, or claiming a task is done. Never claim success without proof.
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.
Senior software architect — deep expertise in DDD (strategic + tactical), CQRS, Clean Architecture, Event-Driven Architecture, and system design. Validates dependency direction, bounded contexts, aggregate boundaries, and design decisions. Use for architecture reviews, design validation, or system design sessions.
Senior technical writer — generates and reviews API docs (OpenAPI), ADRs, READMEs, runbooks, and user guides. Verifies documentation accuracy against code. Use for documentation audits, API doc generation, or technical writing tasks.
Security specialist for finding vulnerabilities in code. Use when auditing security, reviewing authentication, or checking for OWASP issues.
CTO & Tech Lead clone — orchestrates specialized teams across all projects. Use as team lead for any multi-agent task: reviews, implementations, audits. Proactively delegates, challenges decisions, and consolidates deliverables.
UI/UX director and design system guardian — deep expertise in SaaS dashboard UX, data visualization, accessibility WCAG 2.1 AA, and design token systems. Use for design reviews, a11y audits, or UX improvements.
PHP Architecture Toolkit — DDD, CQRS, Event Sourcing, Clean/Hexagonal Architecture, GoF Patterns, PSR, Docker, CI/CD
Use Claude Code As Is - native plugin leveraging built-in architecture
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
Self-orchestrating multi-agent development system — 8 specialized AI agents, parallel quality gates, and automated workflows. You say WHAT, the AI decides HOW.
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
End-to-end development workflow: design → draft-plan → orchestrate → review → pr-create → pr-review → pr-merge
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Share bugs, ideas, or general feedback.
Transform Claude into a disciplined Senior Software Craftsman
Senior craftsman methodology for Claude Code. DDD, Clean Architecture, TDD.
Transform Claude Code into a disciplined software engineer with battle-tested methodologies.
claude --version to check# Step 1: Add the marketplace
/plugin marketplace add BULDEE/ai-craftsman-superpowers
# Step 2: Install the plugin
/plugin install craftsman@BULDEE-ai-craftsman-superpowers
# Step 3: Restart Claude Code
exit
claude
# If you cloned the repo locally
git clone https://github.com/BULDEE/ai-craftsman-superpowers.git /path/to/ai-craftsman-superpowers
/plugin marketplace add /path/to/ai-craftsman-superpowers
/plugin install craftsman@ai-craftsman-superpowers
# Open plugin manager
/plugin
# Go to "Installed" tab to see craftsman plugin
# Go to "Errors" tab if skills don't appear
The plugin uses AI agent hooks for deep semantic analysis beyond regex. These are optional and can be disabled.
| Agent Hook | Trigger | Model | Purpose |
|---|---|---|---|
| DDD Verifier | Each Write/Edit | Haiku | Layer violations, aggregate boundaries, naming |
| Sentry Context | Each Write/Edit | Haiku | Error context from Sentry (if configured) |
| Architecture Analyzer | Session start | Haiku | Build project context map |
| Final Reviewer | Session end | Haiku | Validate architecture (strict mode only) |
Estimated cost: ~$0.15-0.30 per session (50 Write/Edit operations)
Opt-out: Set agent_hooks: false in plugin config to disable all agent hooks. Regex-based validation (Level 1) and static analysis (Level 2) continue to work without agent hooks.
After installation, try:
# Design a new entity (follows DDD phases)
/craftsman:design
I need to create a User entity for an e-commerce platform.
# Debug an issue systematically (ReAct pattern)
/craftsman:debug
I have a memory leak in my Node.js app.
# Plan a feature implementation
/craftsman:plan
I need to migrate our API to microservices.
# Review code for architecture issues
/craftsman:challenge
[paste your code]
# Run the full development workflow (design → spec → plan → implement → test → verify → commit)
/craftsman:workflow
I need to add a forgot password feature.
# Quick setup (zero questions, smart defaults)
/craftsman:setup --quick
See /examples for detailed usage examples with expected outputs.
What makes this plugin genuinely unique in the Claude Code ecosystem:
Records every violation fix users make and injects correction trends at next session start. SQLite-backed feedback loop that progressively teaches Claude the exact patterns your codebase rejects. Cross-file pattern detection suggests project-wide fixes when 3+ files share the same violation. Unique in the ecosystem — no other Claude Code plugin creates this behavioral feedback loop.
Enterprise-ready rule customization: Global → Project → Directory overrides. Short form (PHP001: warn) and long form (custom rules with regex, message, severity, languages, paths). Legacy code coexists with strict new code via directory-level relaxation. Python-backed YAML parser with bash 3.2 shell compatibility.
Real-time detection of acceleration bias, scope creep, and over-optimization in user prompts. Context-aware bilingual FR/EN pattern matching on UserPromptSubmit hook — requires imperative verb context to reduce false positives. Non-blocking warnings that encourage reflection before action.
3-level progressive validation on every Write/Edit:
Graceful degradation: works with zero tools installed (Level 1 only).