What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center
Agent
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
Performs code reviews on completed features - checks security, performance, architecture, code quality. Blocks on Critical/High.
Agent
Implements one feature end-to-end following the strict TDD pipeline - spec, tests, implementation, validation.
Agent
Creates feature branches and PRs for completed features via gh CLI. Never merges - only creates PRs.
Agent
Enforces TDD discipline - verifies specs are complete, tests fail before implementation, tests pass after implementation, coverage >= 80%.
Agent
Performs security analysis on completed features - OWASP scanning, secrets detection, dependency audit. Blocks on Critical/High.
Agent
Orchestrates the agent team - creates tasks, spawns feature agents, monitors progress. Never writes code.