Fix Tests

This is a test maintenance orchestrator that spins up parallel agents to fix failing tests after you've changed business logic or refactored. It discovers your test infrastructure, identifies all failures, then launches one developer agent per broken test file with instructions to iterate until passing. The workflow is smart about complexity: simple single-file changes you handle yourself, but anything more complex gets delegated to agents who work in parallel. It includes a verification step at the end where you run the full suite again and launch new agents for any remaining failures. The constraint to fix tests rather than business logic is the right default, though it allows agents to fix obvious bugs. If you regularly break dozens of tests during refactors, this could save hours of tedious fix-and-verify cycles.