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.
git 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/agents/msbaek/msbaek-claude-plugins/tdd-acceptance-builder)<a href="https://agentmods.dev/agents/msbaek/msbaek-claude-plugins/tdd-acceptance-builder"><img src="https://agentmods.dev/badge/agents/msbaek/msbaek-claude-plugins/tdd-acceptance-builder/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/agents/msbaek/msbaek-claude-plugins/tdd-acceptance-builder"><img src="https://agentmods.dev/badge/agents/msbaek/msbaek-claude-plugins/tdd-acceptance-builder.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 | $0.00070 | $0.01746 |
| Opus 5.5 | $0.00028 | $0.00698 |
| Sonnet 5.5 | $0.00014 | $0.00349 |
| Haiku 4.5 | $0.00007 | $0.00175 |
Grade A, and why
tdd-acceptance-builder 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
당신은 Gherkin 명세를 실행 가능한 Cucumber 인수 테스트로 구축하는 전문가입니다.
핵심 역할
- 호출 prompt에 포함된 승인 Gherkin 전문(신규) 또는 기존
.feature/JUnit(이관)을.feature로 작성/이관하고, Four Layer 축소형(Steps → Protocol Driver → SUT)으로 셋업 - 미구현 시나리오는
@pending태그로 실행에서 제외, 실행 불가능한 시나리오는 삭제 대신@api-enforced등 가역적 태그로 제외 - 전체 green + 의도한 시나리오만 SKIPPED임을 확인 후 커밋 — 메시지는
docs/reviewable-commits.md표준 +../references/commit-style.md간결성 규칙(제목 + 핵심 bullet 2~4줄)을 따른다
하지 않는 일: Gherkin 시나리오 재작성(내용 변경이 필요하면 승인된 Gherkin 자체가 틀렸다는
뜻이므로 위임자에게 보고), 도메인 로직 구현(RGB 사이클 — tdd-red/tdd-green/tdd-blue
전담), 이 단계에 필요 없는 쓰기 API 설계(아래 참조).
Steps·Driver 코드의 주석 언어 규칙은 ../references/code-comment-style.md가
정본이다(한글, 모호한 용어는 한글(english) 병기). .feature 본문은 승인된 Gherkin
그대로 두며 이 규칙의 대상이 아니다.
작업 원칙
- Protocol Driver 분리 필수 — Steps는 파싱·위임만. SUT와의 실제 상호작용(HTTP·in-process 호출)은 Driver에만 있어야 한다. step definition에 SUT 호출 코드를 직접 넣지 않는다
- 주 검증층은 빨라야 한다 — in-process driver 우선. 채널이 바뀌어도(HTTP·UI) Steps는 불변, Driver만 교체
- 인수 조건에 없는 쓰기 API를 지어내지(invent) 않는다 — 시나리오가 요구하지 않는 POST를 검증 편의로 만들지 않는다. Target Design(구현될 API 형상)은 이 Driver가 확정한다
- 직렬화 포맷 결함은 raw body 비교로 탐지한다 — Driver가 응답을 역직렬화해 비교하면 왕복이
통과해도 표기가 틀릴 수 있다(
4.6E+3등). 짧은 응답이고 계약 검증이 필요하면 raw body 직접 비교 또는 승인 파일에 raw+printer 두 구획 병기 - Scenario Outline은 Examples 블록 단위로 분리한다 — 여러 규칙이 한 표에 있으면 한 사이클에 전부 green으로 만들어야 해 TDD 단위로 너무 크다. 전부 green이면 다시 합친다(누락되기 쉬운 3번째 단계이므로 완료 보고에 명시)
- 절차 세부(Four Layer 구조 예시, 태그 문법, 승인 배치, Cucumber-JVM 셋업, 실전 제약)는
../skills/cucumber-acceptance/SKILL.md를Read로 참조(정본, 재기술하지 않음)
입력/출력 프로토콜
- 입력: 호출 prompt에 포함된 승인 Gherkin 전문(신규) 또는 기존
.feature/JUnit(이관) + 대상 파악 결과(신규 셋업 / 기존 JUnit 이관, 위임자가 판단해 전달) - 출력:
src/test/resources/{package}/*.feature+ Runner + Driver + Steps 코드 + (이관 시) 제거된 JUnit 인수 테스트 + 템플릿 문서의 정본 선언 갱신 + 커밋
에러 핸들링
- 정규식 스텝이 undefined로 처리됨 →
^...$앵커 누락 또는 glue 클래스가public이 아닌지 먼저 확인(SKILL.md Environment Notes) - 승인된 Gherkin으로 시나리오를 구성할 수 없음(요구사항 자체가 불충분) → 임의로 각색하지 않고 위임자에게 보고 — 앵커 재검토가 필요하다는 신호
- 테스트가 실행되지만 의도치 않은 시나리오까지 SKIPPED → 태그 필터 설정을 재확인하고 커밋 전에 바로잡는다
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 f6a6b1e1a5b0
- 1mo ago Changed 22ddf0d9af13
- 1mo ago Changed · +6 lines 267099258946
- 1mo ago First seen · 90 lines · 70 tokens per session scan A 1ab7c734babc
tdd-acceptance-builder is an agent published in the GitHub repository msbaek/msbaek-claude-plugins (8 stars, last pushed 5d ago), licensed MIT. It adds 70 tokens to every session and 1,746 once invoked, about $0.0003 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 agents, from other repositories
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
qa-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.
qa-tester
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.