Verification hooks for agentic coding: report what a session transcript can and cannot show about what the agent said it did, and check a scoped test claim against a pytest receipt.
It told you the tests passed. What is that based on? Reports what the transcript can and cannot show about each claim in the agent's final message, and checks a scoped test claim against an opt-in pytest receipt. Report-only.
hooks
1
README badge
Shows how many plugins this repo ships, and links here.