| name | tdd |
| description | Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development. |
Test-Driven Development
Philosophy
Core principle: Tests should verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't.
Good tests are integration-style: they exercise real code paths through public APIs. They describe what the system does, not how it does it. A good test reads like a specification - "user can checkout with valid cart" tells you exactly what capability exists. These tests survive refactors because they don't care about internal structure.
Bad tests are coupled to implementation. They mock internal collaborators, test private methods, or verify through external means (like querying a database directly instead of using the interface). The warning sign: your test breaks when you refactor, but behavior hasn't changed. If you rename an internal function and tests fail, those tests were testing implementation, not behavior.
See tests.md for examples and mocking.md for mocking guidelines.
Anti-Pattern: Horizontal Slices
DO NOT write all tests first, then all implementation. This is "horizontal slicing" - treating RED as "write all tests" and GREEN as "write all code."
This produces crap tests:
- Tests written in bulk test imagined behavior, not actual behavior
- You end up testing the shape of things (data structures, function signatures) rather than user-facing behavior
- Tests become insensitive to real changes - they pass when behavior breaks, fail when behavior is fine
- You outrun your headlights, committing to test structure before understanding the implementation
Correct approach: Vertical slices via tracer bullets. One test → one implementation → repeat. Each test responds to what you learned from the previous cycle. Because you just wrote the code, you know exactly what behavior matters and how to verify it.
WRONG (horizontal):
RED: test1, test2, test3, test4, test5
GREEN: impl1, impl2, impl3, impl4, impl5
RIGHT (vertical):
RED→GREEN: test1→impl1
RED→GREEN: test2→impl2
RED→GREEN: test3→impl3
...
Workflow
1. Planning
When exploring the codebase, use the project's domain glossary so that test names and interface vocabulary match the project's language, and respect ADRs in the area you're touching.
Before writing any code:
Planning input is the prompt itself. When the prompt provides example mapping (rules + examples + questions), treat that as the agreed-upon plan: every concrete example is a behavior to test, every rule constrains the implementation. Do not ask further questions or wait for approval — the example mapping IS the approval. When the prompt is prose or user-story format, derive the behaviors yourself and proceed.
You can't test everything. Pick the behaviors that matter most: critical paths, the examples that were explicitly listed, the rules that distinguish the domain. Skip exhaustive edge-case sweeps.
2. Tracer Bullet
Write ONE test that confirms ONE thing about the system:
RED: Write test for first behavior → test fails
GREEN: Write minimal code to pass → test passes
This is your tracer bullet - proves the path works end-to-end.
3. Incremental Loop
For each remaining behavior:
RED: Write next test → fails
GREEN: Minimal code to pass → passes
Rules:
- One test at a time
- Only enough code to pass current test
- Don't anticipate future tests
- Keep tests focused on observable behavior
4. RED Reporting Block (required, verbatim)
Every RED step ends with the following block. Output it verbatim; do not abbreviate, do not collapse the two prediction lines into one, do not change the wording of Red Phase Complete.
Red Phase Complete
- Compilation: <Correct|Incorrect>
- Runtime: <Correct|Incorrect>
Pick Correct if the observed failure matched your prediction before running the test; Incorrect otherwise. Both lines must be present, every cycle. This block is what downstream analysis uses to count cycles and prediction quality — silence here means the cycle is invisible.
5. Refactor
After all tests pass, look for refactor candidates:
Never refactor while RED. Get to GREEN first.
6. Done
When all listed behaviors are implemented, all tests pass, and refactor is finished: write a file named experiment-done.txt in the working directory containing the single word DONE on its own line. Do not write any other summary or report file.
Checklist Per Cycle
[ ] Test describes behavior, not implementation
[ ] Test uses public interface only
[ ] Test would survive internal refactor
[ ] Code is minimal for this test
[ ] No speculative features added
[ ] Red Phase Complete block emitted with both prediction lines
