Jott2121/crucible

Adversarial test-hardening for AI-written code: a Tester writes tests, mutation testing finds what they miss, a Critic kills the named survivors. Mechanical verdicts, mutation-kill receipts, $0 on a Claude subscription.

2 best points · 0 comments · 1 Hacker News post · 1 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Crucible – your AI wrote the tests, so who tested the tests? (2 points, 0 comments, by jott2121, 2026-07-13)