What problem does it solve? Code changes often get committed without independent verification, letting security vulnerabilities, logic errors, and test regressions slip through because the same agent that wrote the code also reviews it. ## Core Features & Use Cases - Static Security Scanning: Greps added diff lines for hardcoded secrets, shell injection, eval/exec, unsafe pickle deserialization, and SQL injection patterns. - Baseline-Aware Quality Gates: Runs pytest, npm test, cargo test, or go test plus linters like ruff, mypy, eslint, and clippy, comparing failures against a pre-change baseline so only new regressions block the commit. - Independent Reviewer and Auto-Fix Loop: Dispatches a fresh-context reviewer subagent that returns a fail-closed JSON verdict, then spawns a separate fix agent for up to two fix-and-reverify cycles before committing with a [verified] prefix. - Use Case: After implementing a bug fix touching three files, run this pipeline before git push to catch a leftover debug statement and a new lint error, auto-fix them, and commit only after the independent reviewer passes. ## Quick Start Ask the agent to verify and review your staged changes before committing, for example by saying "review my changes before merge".
