What problem does it solve? Code often gets committed without verification, letting secrets, injection vulnerabilities, regressions, and logic errors slip into the repository. This Skill enforces a structured pre-commit review pipeline so every change is scanned, tested, and independently reviewed before it lands. ## Core Features & Use Cases - Static Security Scanning: Greps added diff lines for hardcoded secrets, shell injection, eval/exec, unsafe pickle deserialization, and SQL string formatting. - Baseline-Aware Quality Gates: Runs pytest, npm test, cargo test, or go test plus ruff, mypy, eslint, tsc, clippy, or go vet, comparing failures against a pre-change baseline so only new regressions block the commit. - Independent Reviewer Subagent: Dispatches a fresh-context reviewer via delegate_task with fail-closed JSON verdicts, then an auto-fix agent with a maximum of two fix-and-reverify cycles. - Use Case: After finishing a feature touching three files, ask for a review before committing; the Skill inspects the staged diff, flags a hardcoded API key, runs the test suite, gets a PASS verdict from the independent reviewer, and commits with a [verified] prefix. ## Quick Start Ask the agent to review your staged changes and run all relevant checks before committing.
