Enables AI agents to perform security audits on pull request diffs by detecting secrets, dangerous code patterns, and new dependencies, outputting structured JSON for generating PR review comments.
Enables coding agents to scout, rank, and preflight software work before implementation, returning evidence-backed ACT, VERIFY, or SKIP decisions for issues and pull requests.
Analyzes GitHub Pull Request diffs for security vulnerabilities and data leaks, using a deterministic filter to skip trivial changes and an AI-powered analysis for logic changes.
Enables code-review gating by converting a git diff into a typed verdict with safety probabilities, severity, and recommended actions for auto-merge or human review.