Test Driven Development

Test-Driven Development (TDD)

Overview

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.

Evidence Artifacts

In this skill, a "test" means the cheapest evidence artifact that can fail for the right reason before implementation. For ordinary deterministic code, that is usually a unit or integration test. For AI, agent, RAG, prompt, skill, or research work, it may be an eval case, trajectory check, benchmark smoke run, scorer, or pressure scenario.

Choose the cheapest pattern that proves the intended behavior:

| Pattern | Use for | Cost | |---------|---------|------| | behavior-unit-test | deterministic functions, parsers, CLI behavior | fast | | contract-integration-test | APIs, file formats, tool protocols | fast/focused | | prompt-eval-case | prompts, extraction, classification, rewriting | fast/focused | | rag-eval-case | retrieval, citations, grounding | focused | | agent-trajectory-test | tool use, multi-turn agents, handoffs | focused | | research-benchmark | train/eval/ablation/reproduction | expensive/scheduled | | skill-pressure-test | skill or agent-process behavior | focused | | macro-eval | cross-trace or multi-agent behavior patterns | expensive/scheduled |

For full pattern definitions and examples, read references/evidence-pattern-gallery.md.

When to Use

Always:

• New features
• Bug fixes
• Refactoring
• Behavior changes

Exceptions (ask your human partner):

• Throwaway prototypes
• Generated code
• Configuration files

Thinking "skip TDD just this once"? Stop. That's rationalization.

The Iron Law

NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST

Write code before the test? Delete it. Start over.

No exceptions:

• Don't keep it as "reference"
• Don't "adapt" it while writing tests
• Don't look at it
• Delete means delete

Implement fresh from tests. Period.

Red-Green-Refactor

digraph tdd_cycle {
    rankdir=LR;
    red [label="RED\nWrite failing test", shape=box, style=filled, fillcolor="#ffcccc"];
    verify_red [label="Verify fails\ncorrectly", shape=diamond];
    green [label="GREEN\nMinimal code", shape=box, style=filled, fillcolor="#ccffcc"];
    verify_green [label="Verify passes\nAll green", shape=diamond];
    refactor [label="REFACTOR\nClean up", shape=box, style=filled, fillcolor="#ccccff"];
    next [label="Next", shape=ellipse];

    red -> verify_red;
    verify_red -> green [label="yes"];
    verify_red -> red [label="wrong\nfailure"];
    green -> verify_green;
    verify_green -> refactor [label="yes"];
    verify_green -> green [label="no"];
    refactor -> verify_green [label="stay\ngreen"];
    verify_green -> next;
    next -> red;
}

RED - Write Failing Evidence

Write one minimal evidence artifact showing what should happen. Keep it cheap enough for the inner loop, and make sure it will fail for the intended reason before implementation.

test('retries failed operations 3 times', async () => {
  let attempts = 0;
  const operation = () => {
    attempts++;
    if (attempts 

```typescript
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:

• One behavior, scenario, or eval case
• Clear name
• Real code, real prompt, real trace, or real scorer (mocks only if unavoidable)
• Small enough to run at the selected cost tier

Verify RED - Watch It Fail

MANDATORY. Never skip.

npm test path/to/test.test.ts

Confirm:

• Evidence fails (not errors)
• Failure message is expected
• Fails because behavior is missing (not typos, broken setup, or noisy eval)

Test passes? You're testing existing behavior. Fix test.

Test errors? Fix error, re-run until it fails correctly.

GREEN - Minimal Code

Write simplest code to pass the test.

async function retryOperation(fn: () => Promise): Promise {
  for (let i = 0; i 

```typescript
async function retryOperation(
  fn: () => Promise,
  options?: {
    maxRetries?: number;
    backoff?: 'linear' | 'exponential';
    onRetry?: (attempt: number) => void;
  }
): Promise {
  // YAGNI
}

Over-engineered

Don't add features, refactor other code, or "improve" beyond the test.

Verify GREEN - Watch It Pass

MANDATORY.

npm test path/to/test.test.ts

Confirm:

• Test passes
• Other tests still pass
• Output pristine (no errors, warnings)

Test fails? Fix code, not test.

Other tests fail? Fix now.

REFACTOR - Clean Up

After green only:

• Remove duplication
• Improve names
• Extract helpers

Keep tests green. Don't add behavior.

Repeat

Next failing test for next feature.

Good Tests

| 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 | | Right-sized | Fast RED, stronger confidence gate later | Full benchmark in every edit loop |

Why Order Matters

"I'll write tests after to verify it works"

Tests written after code pass immediately. Passing immediately proves nothing:

• Might test wrong thing
• Might test implementation, not behavior
• Might miss edge cases you forgot
• You never saw it catch the bug

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:

• No record of what you tested
• Can't re-run when code changes
• Easy to forget cases under pressure
• "It worked when I tried it" ≠ comprehensive

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:

• Delete and rewrite with TDD (X more hours, high confidence)
• Keep it and add tests after (30 min, low confidence, likely bugs)

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:

• Finds bugs before commit (faster than debugging after)
• Prevents regressions (tests catch breaks immediately)
• Documents behavior (tests show how to use code)
• Enables refactoring (change freely, tests catch breaks)

"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.

Common Rationalizations

| 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. |

Red Flags - STOP and Start Over

• Code before test
• Test after implementation
• Test passes immediately
• Can't explain why test failed
• Tests added "later"
• Rationalizing "just this once"
• "I already manually tested it"
• "Tests after achieve the same purpose"
• "It's about spirit not ritual"
• "Keep as reference" or "adapt existing code"
• "Already spent X hours, deleting is wasteful"
• "TDD is dogmatic, I'm being pragmatic"
• "This is different because..."

All of these mean: Delete code. Start over with TDD.

Example: Bug Fix

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.

Verification Checklist

Before marking work complete:

• [ ] Every new behavior has a test or evidence artifact
• [ ] Watched each evidence artifact fail before implementing
• [ ] Each failure happened for the expected reason (behavior missing, not typo/setup/noise)
• [ ] Wrote minimal code to pass the selected gate
• [ ] Required tests/evals/checks pass
• [ ] Output pristine (no errors, warnings)
• [ ] Evidence uses real code, prompts, traces, scorers, or commands (mocks only if unavoidable)
• [ ] Edge cases and errors covered

Can't check all boxes? You skipped TDD. Start over.

When Stuck

| 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. |

Debugging Integration

Bug found? Write failing test reproducing it. Follow TDD cycle. Test proves fix and prevents regression.

Never fix bugs without a test.

Testing Anti-Patterns

When adding mocks or test utilities, read @testing-anti-patterns.md to avoid common pitfalls:

• Testing mock behavior instead of real behavior
• Adding test-only methods to production classes
• Mocking without understanding dependencies

When testing AI, agent, prompt, RAG, research, or skill behavior, read references/evidence-pattern-gallery.md to choose the right evidence pattern and cost tier.

Final Rule

Production behavior → evidence artifact exists and failed first
Otherwise → not TDD

No exceptions without your human partner's permission.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: Tx1207
• Source: Tx1207/hello-scholar-2
• License: MIT

Install and usage instructions live in the source repository linked above.