fixing-tests

Use when tests themselves are broken, test quality is poor, or a user wants to fix or improve tests. Typical triggers: "test is broken", "test is wrong", "test is flaky", "make tests pass", "tests need updating", "green mirage", "tests pass but shouldn't", "audit report findings", "run and fix tests". Three modes: fix specific tests, process green-mirage audit findings, and run-then-fix. NOT for: bugs in production code that are correctly caught by tests (use debugging instead).