Test-Driven Development (TDD)

Purpose

TDD acts as the ultimate truth verifier. It prevents Agents from blindly inserting implementation code based on assumptions. By strictly enforcing the RED-GREEN-REFACTOR cycle, we guarantee that all code changes are demonstrably functional and logically sound before moving on to the next task.

---

Workflow (Strict Process)

ABSOLUTE DIRECTIVE: Under NO circumstances are you allowed to write the final implementation logic before a test has explicitly failed in the terminal environment.

1. RED Phase (Write the Failing Test)

• Read the specification for the current atomic task.
• Create or modify the appropriate test file (e.g.,

  *.test.ts

  ,

  *_test.go

  ,

  test_*.py

  ) to assert the expected behavior.
• EXECUTE: Use the terminal to run the test suite.
• GATE: Capture the terminal output. You MUST see the test FAIL. If the test passes immediately, your test is flawed or asserting the wrong state.

2. GREEN Phase (Make it Pass)

• Write the absolute minimum amount of source code necessary to fulfill the test requirement. Do not over-engineer or add "nice-to-have" features yet.
• EXECUTE: Use the terminal to run the test suite again.
• GATE: Capture the terminal output. You MUST see the test PASS.

3. REFACTOR Phase (Clean it Up)

• Optimize your implementation code (clean up naming, extract duplicate logic, improve types/interfaces) without altering behavior.
• EXECUTE: Run the test suite a final time to ensure your refactoring did not break the green state.

---

Output Format

Your final response to the user MUST contain the evidence of your execution in the following format:

# 🧪 TDD Execution: [Feature/Task Name]

## 🔴 RED Phase Evidence
- **Test added**: `[test_function_name]`
- **Terminal Output**:
```bash
[Insert the failing test output trace here - do not fake this]

🟢 GREEN Phase Evidence

• Implementation: Modified

  [file_name]

• Terminal Output:

[Insert the passing test output trace here]

Status: ✅ Code verified. Awaiting next command.

---

## Anti-Rationalizations

Be aware of lazy logic that an Agent typically uses to skip testing. If a thought on the left occurs, YOU MUST apply the rebuttal on the right:

| Excuse (Agent's Lazy Rationalization) | Rebuttal & Correct Action |
| :--- | :--- |
| "I'll just write the implementation first because it's super easy, and add the tests after." | **CRITICAL REJECTION.** Writing code before a test guarantees brittle code and untested edge cases. You MUST write the failing test first. No exceptions. |
| "The project doesn't seem to have a test framework set up, so I will just skip TDD and do a console.log." | **REJECTED.** `console.log` is not an automated test. If a test runner (Jest, PyTest, Go test, Vitest) is missing, STOP working and ask the User for permission to install and configure one immediately. |
| "I don't need to run the final terminal command to check if it's green. I can read the logic and I know it works." | **REJECTED.** Code does not exist until the compiler/test-runner proves it exists. You cannot hallucinate terminal outputs. Run the actual command. |

---

## Verification Gates

Do not conclude the turn unless you have:
- [ ] Executed the test runner during the **RED** phase and captured a definitive FAILING state log.
- [ ] Executed the test runner during the **GREEN** phase and captured a PASSING log.
- [ ] Displayed both terminal outputs (Red & Green) as indisputable evidence to the User.

---

## Edge Cases

- **[UI / Canvas Rendering]**: If the task involves purely visual UI CSS updates that cannot be easily unit tested, fallback to structured visual DOM tests (e.g., Testing Library query checks) or explicit manual testing steps listed for the user. Do not skip testing entirely.

---

## Related Skills

- `planning-and-task-breakdown` — TDD is the engine used to execute the tasks planned by this skill.
- `spec-driven-development` — TDD uses the spec as its single source of truth for what tests need to be written.