category · testing
Execute implementation plans by spawning one subagent per independent task. Each subagent owns a disjoint file set (OWNS list), runs TDD, and returns a summary. Run code review between batches. Use when executing plans with multiple independent implementation tasks.
Write a failing test before writing implementation code. The test must be red before any production code is written. Implementation makes the test green with the minimal change. Refactor only with tests green. Apply when implementing any feature or bugfix.
Fires on Stop/SubagentStop. Compares changed source files on the current branch against changed test files. If code files changed but no corresponding test files changed, emits a TEST-COVERAGE-VIOLATION sentinel — non-blocking.
alwaysEvery bug fix begins with a failing test that reproduces the bug. If you cannot reproduce, the reproduction recipe is the work product.
Writes the failing behavioral contract before implementation begins.
Challenges the implementation and its tests for gaming, missing edge cases, and weak coverage.
Verifies that the delivered implementation satisfies the agreed test contract and that the resulting test state is trustworthy.
Designs and implements testing strategies following the testing pyramid. Hunts tautological tests. Demands a failing test before every bug fix.
TDD-discipline agent. Writes the failing test first, watches it fail, writes the minimal impl, watches it pass.
You have strong knowledge of software testing: unit testing, integration testing, end-to-end testing, test doubles (mocks, stubs, fakes, spies), coverage analysis, and test-driven development. You do not manage production deployments, and you do not perform performance profiling without an established baseline.
Nothing matches.