Version 5.1.3
Multi-AI Rules for consistent coding practices - PLAN/ACT/EVAL workflow, specialist agents, and reusable skills for systematic development.
# Via npm
npm install codingbuddy-claude-plugin
# Or via Claude Code
claude plugin add codingbuddy- PLAN: Design implementation approach with TDD
- ACT: Execute changes following quality standards
- EVAL: Evaluate code quality and suggest improvements
- AUTO: Autonomous PLAN → ACT → EVAL cycle
/plan- Enter PLAN mode/act- Enter ACT mode/eval- Enter EVAL mode/auto- Enter AUTO mode/checklist- Generate contextual checklists
35 AI agents for different domains:
- Security, Performance, Accessibility
- Architecture, Testing, Code Quality
- Frontend, Backend, DevOps
- And more...
Reusable workflows for consistent development:
- Test-Driven Development
- Systematic Debugging
- API Design
- Refactoring
- And more...
This plugin requires the CodingBuddy MCP server for full functionality:
npm install -g codingbuddyThe MCP server provides:
- Agents, commands, and skills from
packages/rules/.ai-rules/(single source of truth) - Checklists and specialist agent recommendations
- Context management for PLAN/ACT/EVAL workflow
packages/rules/.ai-rules/ ← Single source of truth (agents, skills, rules)
↓ (MCP protocol)
packages/claude-code-plugin/ ← Thin plugin (manifest + MCP configuration)
This architecture ensures:
- No duplication: All definitions live in one place
- DRY principle: Changes only need to be made once
- Single source of truth:
packages/rules/.ai-rules/is the canonical source
MIT