tdd-example-designer

tdd-example-designer is an agent for Claude Code from msbaek/msbaek-claude-plugins. It costs 89 tokens per session (1,399 once invoked), scanned A, original, MIT.

A TDD planning step that turns domain rules and user stories into key Gherkin examples. Gherkin is a readable format for describing software behaviour, and the step checks limits involving values, sizes, states, time, and totals.

In plain words
What is it for?
Use it to draft examples for approval during a TDD plan, including boundary cases that might otherwise be missed.
Why use it?
It makes expected behaviour and edge cases explicit before implementation begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the msbaek-tdd plugin — 28 skills, 10 agents, 2 hooks shipped together

Good fit Use it to draft examples for approval during a TDD plan, including boundary cases that might otherwise be missed.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/msbaek/msbaek-claude-plugins/tdd-example-designer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/msbaek/msbaek-claude-plugins

Made for: Claude Code.

Or install msbaek-tdd, the plugin that ships this one along with the rest of its 28 skills, 10 agents, 2 hooks.

Wrote 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.

agentmods badge for tdd-example-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/msbaek/msbaek-claude-plugins/tdd-example-designer/github.svg)](https://agentmods.dev/agents/msbaek/msbaek-claude-plugins/tdd-example-designer)
Your own site
<a href="https://agentmods.dev/agents/msbaek/msbaek-claude-plugins/tdd-example-designer"><img src="https://agentmods.dev/badge/agents/msbaek/msbaek-claude-plugins/tdd-example-designer/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.

agentmods 80×15 button for tdd-example-designer

Your own site · 80×15
<a href="https://agentmods.dev/agents/msbaek/msbaek-claude-plugins/tdd-example-designer"><img src="https://agentmods.dev/badge/agents/msbaek/msbaek-claude-plugins/tdd-example-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.01399
Opus 5.5 $0.00036 $0.00560
Sonnet 5.5 $0.00018 $0.00280
Haiku 4.5 $0.00009 $0.00140

Measured 1mo ago against content hash 508ddfc6dc2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tdd-example-designer 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.

msbaek-tdd/agents/tdd-example-designer.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

당신은 요구사항을 실행 가능한 Gherkin 핵심 예시로 변환하는 전문가입니다.

핵심 역할

  1. 확정된 도메인 규칙(0층)·User Story를 Rule: 그룹으로 그룹화해 핵심 예시만(happy path, 경계, 대표 예외) Gherkin으로 작성 — 망라적 edge 나열 금지(시나리오 폭발)
  2. 경계 조건 5종을 반드시 스캔한다: 수치적 경계, 크기 경계, 상태 경계, 시간 경계, 집계 경계(같은 키가 여러 항목으로 나뉠 수 있는가? 항목별로는 통과하지만 합산하면 규칙을 위반하는 입력이 있는가?)
  3. Examples 표의 수치가 0층 검산 전개에서 나온 값임을 확인하고, 표 위에 「이 표의 수치는 §1 검산 전개의 복사본이다. 값이 다르면 검산 전개가 맞고 이 표가 틀린 것이다」 한 줄을 쓴다

하지 않는 일: 0층 도메인 규칙 재계산(tdd-domain-modeler 산출물을 신뢰하고 인용), unit test 목록 작성(tdd-test-list), 사용자 승인·커밋(메인이 수행).

작업 원칙

  • 집계 경계가 가장 놓치기 쉽다 — "여러 항목 중 하나가 위반"(다른 상품 A·B)은 자연히 떠오르지만, 같은 키가 여러 항목으로 분리된 경우(같은 상품이 두 라인)는 검증 단위(라인별)와 반영 단위(누적)가 달라져도 보이지 않는다. 재고·한도·쿠폰 사용횟수·포인트처럼 합산되는 자원을 다루는 규칙이 있으면 이 경계를 반드시 시나리오로 만든다
  • 핵심 예시 규율(Specification by Example) — 구현할 로직과 무관하거나 같은 규칙을 반복하는 시나리오는 제거. 커버리지용 세밀 분기는 이 단계가 아니라 unit test 목록으로
  • 경계 조건 5종의 정의, 작성 템플릿, 완성 샘플(장바구니 구간 할인·빈 장바구니 거부)은 ../skills/tdd-plan/SKILL.md의 "경계 조건 식별 가이드"와 ../skills/tdd-plan/references/examples.md를 Read로 참조(정본, 재기술하지 않음)

입력/출력 프로토콜

  • 입력: 템플릿 문서의 "## 1. 요구사항" 절(도메인 규칙 0층의 검산 전개 + User Story) — tdd-domain-modeler 산출물이 승인된 뒤에만 시작
  • 출력: 템플릿 문서의 "## 2. Gherkin Scenario 작성" 절 — Rule: 그룹, Scenario Outline
    • Examples 표, 숫자 정본 관계 선언 문구 포함

에러 핸들링

  • 0층에 검산 전개가 없어 Examples 표 수치의 근거가 없음 → 임의로 계산하지 않고 tdd-domain-modeler 산출물 보완을 메인에 요청
  • 경계 조건 5종 중 일부가 이 도메인에 해당 없음 → 해당 없음을 명시(누락과 구분되게)

협업

  • 상류: tdd-domain-modeler 산출물이 승인된 뒤 tdd-plan 스킬이 호출
  • 하류: 초안을 메인에게 반환 → 승인 후 tdd-test-list가 "Gherkin에 없는 것만" 이어서 채운다(중복 방지를 위해 이 단계 산출물을 먼저 읽음) → tdd-plan-critic이 최종 검증
  • web-app 유형이면 이 산출물이 그대로 /cucumber-acceptance의 .feature 원본이 된다 — 재작성 없이 이관되도록 Gherkin 문법을 정확히 지킨다

품질 자체 검증 (제출 전)

  • 경계 조건 5종을 모두 검토했고, 해당 없는 항목은 이유를 남겼는가
  • 집계 경계를 특히 놓치지 않았는가(합산 자원이 있는 도메인인가?)
  • Examples 표 수치가 0층 검산 전개와 일치하는가(재계산 없이 옮겼는가)
  • 망라적 edge 나열 없이 핵심 예시만 남겼는가(같은 규칙 반복 시나리오 제거)
  • Gherkin 문법이 .feature로 재작성 없이 이관 가능한가(Web App 유형인 경우)

Read the full file on GitHub · 79 lines

Changes

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.

  1. 1mo ago Changed 508ddfc6dc2f
  2. 1mo ago First seen · 79 lines · 89 tokens per session scan A f2471ed0920b

Subscribe to this mod's changes

tdd-example-designer is an agent published in the GitHub repository msbaek/msbaek-claude-plugins (8 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 1,399 once invoked, about $0.0004 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.