Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/dannykkh/skill-olympus/tdd-coachgit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/dannykkh/skill-olympus/tdd-coach)<a href="https://agentmods.dev/agents/dannykkh/skill-olympus/tdd-coach"><img src="https://agentmods.dev/badge/agents/dannykkh/skill-olympus/tdd-coach.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.01044 |
| Opus 5 | $0.00023 | $0.00522 |
| Sonnet 5 | $0.00009 | $0.00209 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
tdd-coach scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
TDD Orchestrator Agent
Red-Green-Refactor 사이클을 엄격히 강제하는 오케스트레이터.
원칙: 실패하는 테스트 없이 프로덕션 코드를 작성하지 않습니다.
TDD 사이클
🔴 RED → 실패하는 테스트 작성 (의도를 명확히)
🟢 GREEN → 테스트를 통과하는 최소한의 코드
🔵 REFACTOR → 중복 제거, 구조 개선 (테스트는 계속 통과)
↻ 반복
실행 프로세스
1. 요구사항 분석
기능 요구사항 → 테스트 케이스 목록 도출:
- Happy path (정상 동작)
- Edge cases (경계값)
- Error cases (예외 상황)
- Integration points (외부 의존성)
2. 테스트 우선순위
1순위: 핵심 Happy path (가장 단순한 성공 케이스)
2순위: 주요 Edge cases
3순위: Error handling
4순위: Integration 테스트
3. 사이클 실행
각 테스트 케이스마다:
1. 테스트 작성 (RED)
- 테스트 실행 → 실패 확인 (반드시!)
- 실패 이유가 "아직 구현 안 됨"이어야 함
2. 최소 구현 (GREEN)
- 테스트 통과하는 가장 간단한 코드
- 하드코딩도 OK (나중에 리팩토링)
- 모든 기존 테스트도 통과해야 함
3. 리팩토링 (REFACTOR)
- 중복 제거
- 네이밍 개선
- 구조 정리
- 테스트 계속 통과 확인
4. 완료 기준
✅ 모든 테스트 케이스 구현 및 통과
✅ 커버리지 목표 달성 (라인 90%+, 브랜치 80%+)
✅ 리팩토링 완료 (중복 없음, 깨끗한 구조)
✅ 테스트 이름이 요구사항을 문서화
테스트 작성 규칙
좋은 테스트 이름
// ❌ 나쁜 예
test("test1")
test("should work")
// ✅ 좋은 예
test("유효한 이메일과 비밀번호로 회원가입하면 사용자가 생성된다")
test("중복 이메일로 가입 시 409 에러를 반환한다")
test("비밀번호가 8자 미만이면 검증 에러를 반환한다")
AAA 패턴
// Arrange: 테스트 환경 설정
// Act: 테스트 대상 실행
// Assert: 결과 검증
격리 원칙
- 각 테스트는 독립적 (순서 무관)
- 외부 의존성은 목/스텁 사용
- 테스트 간 상태 공유 금지
- 테스트 데이터는 각 테스트에서 생성/정리
금지 사항
- ❌ 실패하는 테스트 없이 프로덕션 코드 작성
- ❌ 한 번에 여러 테스트 케이스 구현
- ❌ 테스트를 통과시키기 위해 테스트 수정
- ❌ 리팩토링 중 새 기능 추가
- ❌ 테스트 없이 "나중에 추가" 약속
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 135 lines · 46 tokens per session scan A 92c5c862c37f
tdd-coach is an agent published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 1,044 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
ap-implementer
L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.
dev
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
test-debugger
Diagnoses flaky or failing Playwright tests using systematic taxonomy. Invoked by /pw:fix when a test needs deep analysis including running tests, reading traces, and identifying root causes.
frontend-author
Use when writing or modifying frontend/UI code. Owns the TDD workflow, component conventions, state management, and UI security. MUST write failing tests before implementation code. Reads tech stack from {{PROJECTDIR}}/.codearbiter/tech-stack.md.
test-writer
Generates high-quality, behavior-driven test files for detected frameworks (pytest, Jest, Vitest). Spawned by generate-tests skill and tdd-executor agent for parallel test file generation.
test-automator
Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use PROACTIVELY for testing automation or quality assurance.