An agent patch that passes its own tests is a baseline, not a verdict. The same model wrote the code and the tests, so both share the same blind spots. Mutation testing scores the tests themselves: inject a fault, run the suite, and see whether it notices.
Source: [Dev.to](https://dev.to/datacpp_8185/mutation-testing-as-a-merge-gate-for-agent-written-tests-5gie)