Receipts reruns an agent's new tests with the fix reverted.

The tool, created September 25 as a Claude Code plugin, GitHub Action and CLI, runs each changed pytest, vitest or jest test twice: once with the change, once with only source files reverted. Each test gets labelled PROVEN, THEATER (passes both ways) or WEAK. Across 181 real changes, 82% of agent PRs were proven against 90% of maintainer fixes, and in 10% of agent PRs every test failed on old code only because it imported a new name. Its prove-fix skill makes Claude rewrite the test, not the fix, until it's proven. This is the cleanest answer I've seen to "the agent wrote tests, but do they test anything."