Test-Driven Development workflow with session integration. Use when implementing features/bugfixes to enforce RED-GREEN-REFACTOR discipline. Integrates with session-management for enhanced TDD session tracking, checkpoints, and metrics.
Automates RED-GREEN-REFACTOR test-driven development cycles. Triggers when implementing features, bug fixes, or refactoring to enforce test-first discipline. Integrates with session-management for automatic checkpoint tracking and metrics.
/plugin marketplace add AnthemFlynn/ccmp/plugin install tdd-workflow@ccmpThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Write the test first. Watch it fail. Write minimal code to pass.
Core principle: If you didn't watch the test fail, you don't know if it tests the right thing.
Violating the letter of the rules is violating the spirit of the rules.
Always:
Exceptions (ask your human partner):
Thinking "skip TDD just this once"? Stop. That's rationalization.
Enhanced when session-management is active:
If session has "TDD" in objective or uses --tdd flag:
Works standalone without session-management - all core TDD functionality available.
NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
Write code before the test? Delete it. Start over.
No exceptions:
Implement fresh from tests. Period.
RED → Verify RED → GREEN → Verify GREEN → REFACTOR → Repeat
Write one minimal test showing what should happen.
Good:
test('retries failed operations 3 times', async () => {
let attempts = 0;
const operation = () => {
attempts++;
if (attempts < 3) throw new Error('fail');
return 'success';
};
const result = await retryOperation(operation);
expect(result).toBe('success');
expect(attempts).toBe(3);
});
Clear name, tests real behavior, one thing.
Bad:
test('retry works', async () => {
const mock = jest.fn()
.mockRejectedValueOnce(new Error())
.mockRejectedValueOnce(new Error())
.mockResolvedValueOnce('success');
await retryOperation(mock);
expect(mock).toHaveBeenCalledTimes(3);
});
Vague name, tests mock not code.
Requirements:
Session Integration: If session-management active, I'll prompt for checkpoint label.
MANDATORY. Never skip.
npm test path/to/test.test.ts
Confirm:
Test passes? You're testing existing behavior. Fix test.
Test errors? Fix error, re-run until it fails correctly.
Session Integration: RED checkpoint automatically created with test file path.
Write simplest code to pass the test.
Good:
async function retryOperation<T>(fn: () => Promise<T>): Promise<T> {
for (let i = 0; i < 3; i++) {
try {
return await fn();
} catch (e) {
if (i === 2) throw e;
}
}
throw new Error('unreachable');
}
Just enough to pass.
Bad:
async function retryOperation<T>(
fn: () => Promise<T>,
options?: {
maxRetries?: number;
backoff?: 'linear' | 'exponential';
onRetry?: (attempt: number) => void;
}
): Promise<T> {
// YAGNI - You Aren't Gonna Need It
}
Over-engineered.
Don't add features, refactor other code, or "improve" beyond the test.
MANDATORY.
npm test path/to/test.test.ts
Confirm:
Test fails? Fix code, not test.
Other tests fail? Fix now.
Session Integration: GREEN checkpoint created, cycle count incremented.
After green only:
Keep tests green. Don't add behavior.
Session Integration: Optional REFACTOR checkpoint if significant changes.
Next failing test for next feature.
When session-management is installed and active:
# Explicit TDD session
python scripts/session.py start feature/auth --objective "Add auth (TDD)"
# Or with TDD flag
python scripts/session.py start feature/auth --tdd
Activates enhanced TDD mode with:
# RED checkpoint (test written, verified failing)
python scripts/session.py checkpoint --label "red-user-validation" --tdd-phase RED
# GREEN checkpoint (minimal code, test passing)
python scripts/session.py checkpoint --label "green-user-validation" --tdd-phase GREEN
# REFACTOR checkpoint (optional, when refactoring)
python scripts/session.py checkpoint --label "refactor-extract-validator" --tdd-phase REFACTOR
# Session summary with TDD stats
python scripts/session.py status
# Shows:
# - RED-GREEN-REFACTOR cycles completed
# - Tests written vs passing
# - Average cycle time
# - Coverage trend
python scripts/session.py end --handoff
Generates handoff including:
| Quality | Good | Bad |
|---|---|---|
| Minimal | One thing. "and" in name? Split it. | test('validates email and domain and whitespace') |
| Clear | Name describes behavior | test('test1') |
| Shows intent | Demonstrates desired API | Obscures what code should do |
"I'll write tests after to verify it works"
Tests written after code pass immediately. Passing immediately proves nothing:
Test-first forces you to see the test fail, proving it actually tests something.
"I already manually tested all the edge cases"
Manual testing is ad-hoc. You think you tested everything but:
Automated tests are systematic. They run the same way every time.
"Deleting X hours of work is wasteful"
Sunk cost fallacy. The time is already gone. Your choice now:
The "waste" is keeping code you can't trust. Working code without real tests is technical debt.
"TDD is dogmatic, being pragmatic means adapting"
TDD IS pragmatic:
"Pragmatic" shortcuts = debugging in production = slower.
"Tests after achieve the same goals - it's spirit not ritual"
No. Tests-after answer "What does this do?" Tests-first answer "What should this do?"
Tests-after are biased by your implementation. You test what you built, not what's required. You verify remembered edge cases, not discovered ones.
Tests-first force edge case discovery before implementing. Tests-after verify you remembered everything (you didn't).
30 minutes of tests after ≠ TDD. You get coverage, lose proof tests work.
| Excuse | Reality |
|---|---|
| "Too simple to test" | Simple code breaks. Test takes 30 seconds. |
| "I'll test after" | Tests passing immediately prove nothing. |
| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" |
| "Already manually tested" | Ad-hoc ≠ systematic. No record, can't re-run. |
| "Deleting X hours is wasteful" | Sunk cost fallacy. Keeping unverified code is technical debt. |
| "Keep as reference, write tests first" | You'll adapt it. That's testing after. Delete means delete. |
| "Need to explore first" | Fine. Throw away exploration, start with TDD. |
| "Test hard = design unclear" | Listen to test. Hard to test = hard to use. |
| "TDD will slow me down" | TDD faster than debugging. Pragmatic = test-first. |
| "Manual test faster" | Manual doesn't prove edge cases. You'll re-test every change. |
| "Existing code has no tests" | You're improving it. Add tests for existing code. |
All of these mean: Delete code. Start over with TDD.
Bug: Empty email accepted
RED
test('rejects empty email', async () => {
const result = await submitForm({ email: '' });
expect(result.error).toBe('Email required');
});
Verify RED
$ npm test
FAIL: expected 'Email required', got undefined
GREEN
function submitForm(data: FormData) {
if (!data.email?.trim()) {
return { error: 'Email required' };
}
// ...
}
Verify GREEN
$ npm test
PASS
REFACTOR Extract validation for multiple fields if needed.
Before marking work complete:
Can't check all boxes? You skipped TDD. Start over.
| Problem | Solution |
|---|---|
| Don't know how to test | Write wished-for API. Write assertion first. Ask your human partner. |
| Test too complicated | Design too complicated. Simplify interface. |
| Must mock everything | Code too coupled. Use dependency injection. |
| Test setup huge | Extract helpers. Still complex? Simplify design. |
Bug found? Write failing test reproducing it. Follow TDD cycle. Test proves fix and prevents regression.
Never fix bugs without a test.
Production code → test exists and failed first
Otherwise → not TDD
No exceptions without your human partner's permission.
TDD workflow automatically integrates with other CCMP plugins via .ccmp/state.json:
from lib.ccmp_integration import is_session_active, is_tdd_mode
if is_session_active():
# Enhanced TDD mode with session integration
pass
Legacy detection (still supported):
.git/sessions/<branch>/ directory exists--tdd flagsession.py commands availableAutomatic activation:
python scripts/session.py start feature/auth --tdd
# → TDD workflow detects via integration API
# → Enhanced mode activates automatically
TDD metrics in sessions:
Test context updates: When TDD GREEN checkpoints succeed:
tests/*/claude.md updatesIntegration example:
from lib.ccmp_integration import CCMPIntegration
integration = CCMPIntegration()
integration.update_state("tdd-workflow", {
"active": True,
"cycles_today": 5,
"current_phase": "GREEN",
"discipline_score": 100
})
If detected: Enhanced TDD mode with automatic checkpoints and metrics.
If not detected: Standard TDD guidance works perfectly standalone.
With session-management:
Without session-management:
Best of both worlds: Works great alone, better together.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.