What problem does it solve? Manual codebase audits are slow and inconsistent, and a single reviewer often misses entire categories of issues. This Skill coordinates multiple parallel audit agents so bugs, security vulnerabilities, test gaps, and dead code are all examined at once with consolidated findings. ## Core Features & Use Cases - Parallel Multi-Agent Audit: Spawns four background agents (bugs, security, tests, dead code) in full mode, or two agents in quick mode, coordinated through Agent Mail and a shared team. - Structured Findings Report: Synthesizes agent reports into a summary of critical bugs, security severities, missing tests, and removable dead code with file:line references. - Actionable Follow-Up: Offers to convert findings into tracked tasks and beads via TaskCreate and br create. - Use Case: Before a major release, run a full audit to have four agents simultaneously scan for race conditions, injection vulnerabilities, untested critical paths, and unused exports, then receive one consolidated report. ## Quick Start Ask the assistant to run a full codebase audit for bugs, security issues, test gaps, and dead code.
