Stop trusting 'done'. Make AI coding agents prove their work — frozen specs, tamper-detected tests, an independent blind verifier, hard-blocking gates. Fails loudly instead of pretending. For Claude Code, Codex, OpenCode & any Agent Skills runtime. No unverified work passes.
5Stars
1Forks
1Open issues
Shell MIT v0.13.0 Updated 2 weeks ago
Comments (0)
Sign in to join the discussion.
No comments yet
Be the first to share your take.