What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center
This repository also configures its own agents. See what maggy tells them →
Agent Claude Code
Enhanced codebase explorer that uses iCPG and code property graphs for discovery. Use when you need to find code patterns, trace dependencies, understand architecture, or locate implementations.
Agent Claude Code
Performs code reviews on completed features - checks security, performance, architecture, code quality. Blocks on Critical/High.
Agent Claude Code
Implements one feature end-to-end following the strict TDD pipeline - spec, tests, implementation, validation.
Agent Claude Code
Creates feature branches and PRs for completed features via gh CLI. Never merges - only creates PRs.
Agent Claude Code
Enforces TDD discipline - verifies specs are complete, tests fail before implementation, tests pass after implementation, coverage >= 80%.
Agent Claude Code
Performs security analysis on completed features - OWASP scanning, secrets detection, dependency audit. Blocks on Critical/High.
Agent Claude Code
Orchestrates the agent team - creates tasks, spawns feature agents, monitors progress. Never writes code.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: