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 skills add msbaek/msbaek-claude-plugins --skill tddgit clone --depth 1 https://github.com/msbaek/msbaek-claude-pluginsWrote 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/skills/msbaek/msbaek-claude-plugins/tdd)<a href="https://agentmods.dev/skills/msbaek/msbaek-claude-plugins/tdd"><img src="https://agentmods.dev/badge/skills/msbaek/msbaek-claude-plugins/tdd/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/msbaek/msbaek-claude-plugins/tdd"><img src="https://agentmods.dev/badge/skills/msbaek/msbaek-claude-plugins/tdd.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00130 | $0.02363 |
| Opus 5.5 | $0.00052 | $0.00945 |
| Sonnet 5.5 | $0.00026 | $0.00473 |
| Haiku 4.5 | $0.00013 | $0.00236 |
Grade A, and why
tdd 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD 오케스트레이터
TDD 프로젝트 생성 및 진행 상황을 관리하는 진입점입니다.
GOAL
- 성공 = TDD 유형에 맞는 템플릿 문서가 생성되거나, 기존 프로젝트의 진행 상황이 분석되어 다음 단계가 안내됨
- 프로젝트 생성: 템플릿 문서 + 빈 테스트 클래스 생성 후 "/tdd-plan 실행하세요" 안내
- 진행 상황 분석: 체크박스 기반 현재 단계 파악 후 적절한 다음 명령어 안내
CONSTRAINTS
Hard Rules
Ground Rule
- 모르는 정보면 모른다고 확실히 대답
- 요청에 답변하기 위해 필요한 정보가 있으면 먼저 질문
- 코드는 최신 Java, Spring Boot 기준으로 작성
- 요청하지 않는 한 리팩터링하지 않고, 절차적/명령형 스타일로 하나의 메소드로 직관적이게 작성
- 메소드 추출(extract method)이나 변수 추출(extract variable/field) 최소화
- 금액, 거리, 무게 등은 대한민국 기준
- getter/setter는 lombok 활용, 최대한 record 활용
- 마크다운 문서는 한글로 작성
- Class 파일에서 중요한 public method가 먼저, private 메소드가 나중에
피드백 규칙
- 한 단계에서 관련된 코드를 생성한 후에는 반드시 사용자에게 피드백을 요청
- 사용자가 명시적으로 다음 단계로 진행하는 것을 결정해야만 다음 단계로 진행
- 피드백이 필요할 때마다 다음 형식으로 질문:
[피드백 요청]
- 대상: [테스트/구현/설계/리팩토링]
- 초점: [특정 관심 영역]
- 맥락: [현재까지의 작업 요약]
- 구체적 질문: [구체적인 피드백 요청 사항]
OUTPUT FORMAT
호출 형식
/tdd $1 $2
$1=general|web-app(TDD 유형)$2= FQCN (예:com.example.bowling.BowlingGame)
FQCN에서 패키지명과 클래스명을 자동 파싱합니다. 패키지명 없이 입력 시 예시를 보여주며 재입력 요청합니다.
예: /tdd general com.example.bowling.BowlingGame
예: /tdd web-app com.example.basket.CreateShoppingBasket
프로젝트 탐색 로직
1. 빌드 시스템 탐색
- 현재 디렉토리에서 Gradle(
build.gradle,build.gradle.kts) 또는 Maven(pom.xml) 프로젝트 루트 탐색 - 프로젝트 루트를 기준으로 경로 결정
2. FQCN 기반 경로 결정
FQCN을 기반으로 다음 경로를 결정합니다:
- 템플릿 문서:
src/test/java/{package_path}/{ClassName}.md - 테스트 클래스:
src/test/java/{package_path}/{ClassName}Test.java
예: com.example.bowling.BowlingGame →
- 문서:
src/test/java/com/example/bowling/BowlingGame.md - 테스트:
src/test/java/com/example/bowling/BowlingGameTest.java
상태 판단
Case A: 템플릿 없음 → 프로젝트 생성
- TDD 유형에 따라 템플릿 문서 생성
- 빈 테스트 클래스 생성 — 주석 언어와 빌드 파일 UTF-8 인코딩 명시는
../../references/code-comment-style.md를 따른다 - 산출물 커밋 1회 — 템플릿 문서 + 빈 테스트 클래스(+ 새로 만든 빌드 골격이 있으면 함께).
메시지 형식·한글 안전 방식은
../../references/commit-style.md를 따른다 - "/tdd-plan 실행하세요" 안내
Case B: 템플릿 있음 → 진행 상황 분석
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.
- 1mo ago Changed · +98 tokens per session bd306d2f56ae
- 1mo ago Changed fb033df68a0f
- 1mo ago Changed · -1 lines 4337e24fd3c3
- 1mo ago First seen · 201 lines · 32 tokens per session scan A 5a91175be058
tdd is a skill published in the GitHub repository msbaek/msbaek-claude-plugins (8 stars, last pushed 5d ago), licensed MIT. It adds 130 tokens to every session and 2,363 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…