What problem does it solve? Code written by an AI agent is often committed without independent verification, letting security flaws, logic errors, and regressions slip through. This Skill enforces a pre-commit verification pipeline so no agent verifies its own work. ## Core Features & Use Cases - Static Security Scanning: Greps the git diff for hardcoded secrets, shell injection, eval/exec, unsafe deserialization, and SQL injection patterns. - Baseline-Aware Quality Gates: Runs tests and linters (pytest, npm, cargo, go, ruff, mypy, eslint, clippy) and only blocks on NEW failures relative to a pre-change baseline. - Independent Reviewer Subagent: Dispatches a fresh-context reviewer via delegate_task that returns a fail-closed JSON verdict on security concerns and logic errors. - Auto-Fix Loop: Spawns a separate fix agent for up to 2 fix-and-reverify cycles before escalating to the user. - Use Case: After implementing a feature across multiple files, trigger this Skill before running git commit so an independent reviewer approves the diff and the commit is tagged with a [verified] prefix. ## Quick Start Verify my staged changes with the pre-commit review pipeline before I commit them.