TDD Cycle - Comprehensive Test-Driven Development

TDD Cycle - Comprehensive Test-Driven Development

--phase Flag (v1.1.0+)

sw:tdd-cycle supports a --phase flag to run a single phase of the RED → GREEN → REFACTOR cycle. Omitting the flag (or passing --phase all) runs the full cycle.

Flag	Behavior
--phase all (default)	Full RED → GREEN → REFACTOR cycle. Same as omitting the flag.
--phase red	Runs only the RED phase — write failing tests. See Phase 2 below.
--phase green	Runs only the GREEN phase — write minimal code to make tests pass. See Phase 3 below.
--phase refactor	Runs only the REFACTOR phase — improve code quality with tests as safety net. See Phase 4 below.

Alias routing from deprecated skills

The following deprecated single-phase skills are aliased in marketplace.json to route through sw:tdd-cycle --phase <x>:

• /sw:tdd-red → /sw:tdd-cycle --phase red
• /sw:tdd-green → /sw:tdd-cycle --phase green
• /sw:tdd-refactor → /sw:tdd-cycle --phase refactor

The aliases emit a one-time migration warning pointing users to the canonical --phase form. The three tdd-* skills are scheduled for removal in v1.3.0 — see .specweave/docs/internal/specs/skill-deprecation-policy.md.

Examples

# Full cycle (default)
sw:tdd-cycle "user authentication"

# Single phases
sw:tdd-cycle --phase red "user authentication"
sw:tdd-cycle --phase green "user authentication"
sw:tdd-cycle --phase refactor "user authentication"

# Same as default — explicit
sw:tdd-cycle --phase all "user authentication"

---

Project Overrides

Skill Memories: If .specweave/skill-memories/tdd-cycle.md exists, read and apply its learnings.

Execute a comprehensive Test-Driven Development (TDD) workflow with strict red-green-refactor discipline:

[Extended thinking: This workflow enforces test-first development through coordinated agent orchestration. Each phase of the TDD cycle is strictly enforced with fail-first verification, incremental implementation, and continuous refactoring. The workflow supports both single test and test suite approaches with configurable coverage thresholds.]

Configuration

Coverage Thresholds

• Minimum line coverage: 80%
• Minimum branch coverage: 75%
• Critical path coverage: 100%

Refactoring Triggers

• Cyclomatic complexity > 10
• Method length > 20 lines
• Class length > 200 lines
• Duplicate code blocks > 3 lines

Phase 1: Test Specification and Design

1. Requirements Analysis

• Use Task tool with subagent_type="Plan"
• Prompt: "Analyze requirements for: $ARGUMENTS. Define acceptance criteria, identify edge cases, and create test scenarios. Output a comprehensive test specification."
• Output: Test specification, acceptance criteria, edge case matrix
• Validation: Ensure all requirements have corresponding test scenarios

2. Test Architecture Design

• Use Task tool with subagent_type="general-purpose"
• Prompt: "Design test architecture for: $ARGUMENTS based on test specification. Define test structure, fixtures, mocks, and test data strategy. Ensure testability and maintainability."
• Output: Test architecture, fixture design, mock strategy
• Validation: Architecture supports isolated, fast, reliable tests

Phase 2: RED - Write Failing Tests

3. Write Unit Tests (Failing)

• Use Task tool with subagent_type="general-purpose"
• Prompt: "Write FAILING unit tests for: $ARGUMENTS. Tests must fail initially. Include edge cases, error scenarios, and happy paths. DO NOT implement production code."
• Output: Failing unit tests, test documentation
• CRITICAL: Verify all tests fail with expected error messages

4. Verify Test Failure

• Use Task tool with subagent_type="general-purpose"
• Prompt: "Verify that all tests for: $ARGUMENTS are failing correctly. Ensure failures are for the right reasons (missing implementation, not test errors). Confirm no false positives."
• Output: Test failure verification report
• GATE: Do not proceed until all tests fail appropriately

Phase 3: GREEN - Make Tests Pass

5. Minimal Implementation

• Use Task tool with subagent_type="general-purpose"
• Prompt: "Implement MINIMAL code to make tests pass for: $ARGUMENTS. Focus only on making tests green. Do not add extra features or optimizations. Keep it simple."
• Output: Minimal working implementation
• Constraint: No code beyond what's needed to pass tests

6. Verify Test Success

• Use Task tool with subagent_type="general-purpose"
• Prompt: "Run all tests for: $ARGUMENTS and verify they pass. Check test coverage metrics. Ensure no tests were accidentally broken."
• Output: Test execution report, coverage metrics
• GATE: All tests must pass before proceeding

Phase 4: REFACTOR - Improve Code Quality

7. Code Refactoring

• Use Task tool with subagent_type="general-purpose"
• Prompt: "Refactor implementation for: $ARGUMENTS while keeping tests green. Apply SOLID principles, remove duplication, improve naming, and optimize performance. Run tests after each refactoring."
• Output: Refactored code, refactoring report
• Constraint: Tests must remain green throughout

8. Test Refactoring

• Use Task tool with subagent_type="general-purpose"
• Prompt: "Refactor tests for: $ARGUMENTS. Remove test duplication, improve test names, extract common fixtures, and enhance test readability. Ensure tests still provide same coverage."
• Output: Refactored tests, improved test structure
• Validation: Coverage metrics unchanged or improved

Phase 5: Integration and System Tests

9. Write Integration Tests (Failing First)

• Use Task tool with subagent_type="general-purpose"
• Prompt: "Write FAILING integration tests for: $ARGUMENTS. Test component interactions, API contracts, and data flow. Tests must fail initially."
• Output: Failing integration tests
• Validation: Tests fail due to missing integration logic

10. Implement Integration

• Use Task tool with subagent_type="general-purpose"
• Prompt: "Implement integration code for: $ARGUMENTS to make integration tests pass. Focus on component interaction and data flow."
• Output: Integration implementation
• Validation: All integration tests pass

Phase 6: Continuous Improvement Cycle

11. Performance and Edge Case Tests

• Use Task tool with subagent_type="general-purpose"
• Prompt: "Add performance tests and additional edge case tests for: $ARGUMENTS. Include stress tests, boundary tests, and error recovery tests."
• Output: Extended test suite
• Metric: Increased test coverage and scenario coverage

12. Final Code Review

• Use Task tool with subagent_type="Plan"
• Prompt: "Perform comprehensive review of: $ARGUMENTS. Verify TDD process was followed, check code quality, test quality, and coverage. Suggest improvements."
• Output: Review report, improvement suggestions
• Action: Implement critical suggestions while maintaining green tests

Incremental Development Mode

For test-by-test development:

1. Write ONE failing test
2. Make ONLY that test pass
3. Refactor if needed
4. Repeat for next test

Use this approach by adding --incremental flag to focus on one test at a time.

Test Suite Mode

For comprehensive test suite development:

1. Write ALL tests for a feature/module (failing)
2. Implement code to pass ALL tests
3. Refactor entire module
4. Add integration tests

Use this approach by adding --suite flag for batch test development.

Validation Checkpoints

RED Phase Validation

• All tests written before implementation
• All tests fail with meaningful error messages
• Test failures are due to missing implementation
• No test passes accidentally

GREEN Phase Validation

• All tests pass
• No extra code beyond test requirements
• Coverage meets minimum thresholds
• No test was modified to make it pass

REFACTOR Phase Validation

• All tests still pass after refactoring
• Code complexity reduced
• Duplication eliminated
• Performance improved or maintained
• Test readability improved

Coverage Reports

Generate coverage reports after each phase:

• Line coverage
• Branch coverage
• Function coverage
• Statement coverage

Failure Recovery

If TDD discipline is broken:

1. STOP immediately
2. Identify which phase was violated
3. Rollback to last valid state
4. Resume from correct phase
5. Document lesson learned

TDD Metrics Tracking

Track and report:

• Time in each phase (Red/Green/Refactor)
• Number of test-implementation cycles
• Coverage progression
• Refactoring frequency
• Defect escape rate

Anti-Patterns to Avoid

• Writing implementation before tests
• Writing tests that already pass
• Skipping the refactor phase
• Writing multiple features without tests
• Modifying tests to make them pass
• Ignoring failing tests
• Writing tests after implementation

Anti-Rationalization Table

These excuses signal you're about to break TDD discipline. Recognize them and return to the correct phase.

Excuse	Rebuttal	Why It Matters
"I'll test after"	Tests written after implementation pass immediately, proving nothing. You can't verify a test catches bugs if you never saw it fail.	Tests-after are biased by implementation — you test what you built, not what's required
"This is too simple to test"	Simple code has the most unexamined assumptions. Simple code breaks at integration boundaries where you least expect it.	The simpler it seems, the more likely you'll miss an edge case
"TDD slows me down"	TDD prevents 2-3 hour debugging sessions. Writing a test takes minutes; debugging an untested bug takes hours.	The time you "save" skipping tests is borrowed against future debugging
"Just this once"	Every "just this once" becomes the new standard. Discipline has no exceptions — the exception IS the precedent.	One skip normalizes skipping. There is no "just this once"
"I already manually tested it"	Manual testing leaves no record, isn't repeatable, and doesn't catch regressions. It proves nothing to anyone but you, right now.	Manual tests evaporate. Automated tests compound
"Deleting my code is wasteful"	Sunk cost fallacy — keeping bad code costs more than writing it correctly. Code written without tests is unverified code.	Bad code costs more to maintain than to rewrite correctly
"The spirit matters, not the ritual"	The ritual IS the spirit — the specific order (test → fail → implement → pass → refactor) is what produces the quality guarantee.	Skipping steps while claiming to follow TDD is not following TDD
"I'll keep deleted code as reference"	Reference code biases you toward the wrong implementation. Start fresh — the test tells you what to write.	Prior code anchors you to assumptions that may be wrong

Success Criteria

• 100% of code written test-first
• All tests pass continuously
• Coverage exceeds thresholds
• Code complexity within limits
• Zero defects in covered code
• Clear test documentation
• Fast test execution (< 5 seconds for unit tests)

Notes

• Enforce strict RED-GREEN-REFACTOR discipline
• Each phase must be completed before moving to next
• Tests are the specification
• If a test is hard to write, the design needs improvement
• Refactoring is NOT optional
• Keep test execution fast
• Tests should be independent and isolated

TDD implementation for: $ARGUMENTS

Resources

• Official Documentation