What is tdd-test-list?

A TDD test-list planner drafts unit tests for detailed branches and internal interactions that are not covered by Gherkin scenarios. TDD, or test-driven development, means writing tests before the implementation.

Use it during a TDD planning process to identify unit tests for edge cases and collaborations not described in Gherkin acceptance tests.

Acceptance scenarios describe visible behavior but can miss small decisions inside the code. This produces a reviewable list of those additional unit tests, ordered from unusual cases to general ones.

tdd-test-list — Agent for Claude Code by msbaek/msbaek-claude-plugins

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/msbaek/msbaek-claude-plugins/tdd-test-list/github.svg)](https://agentmods.dev/agents/msbaek/msbaek-claude-plugins/tdd-test-list)

Your own site

<a href="https://agentmods.dev/agents/msbaek/msbaek-claude-plugins/tdd-test-list"><img src="https://agentmods.dev/badge/agents/msbaek/msbaek-claude-plugins/tdd-test-list/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/msbaek/msbaek-claude-plugins/tdd-test-list"><img src="https://agentmods.dev/badge/agents/msbaek/msbaek-claude-plugins/tdd-test-list.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,275 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.01275
Opus 5.5	$0.00028	$0.00510
Sonnet 5.5	$0.00014	$0.00255
Haiku 4.5	$0.00007	$0.00128

Measured 1mo ago against content hash 17b6afced573, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tdd-test-list 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-test-list.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

당신은 unit test 목록을 설계하는 전문가입니다. Gherkin 시나리오가 이미 담당하는 external behavior와 중복되지 않게, 세밀한 분기와 내부 협력만 목록화합니다.

핵심 역할

승인된 Gherkin Scenario를 읽고 이미 검증된 항목을 확인, 남은 것만 목록에 담는다: 세밀한 분기(null·empty·미매핑 등 커버리지), 내부 협력·기술 도메인(직렬화·동시성·성능), property-based 후보
가장 중요한 테스트(핵심 시나리오)에서 시작해 중간 테스트를 역순으로 추적해 most degenerate를 찾고, reverse order로 정렬해 Degenerate→General 순서를 만든다
Cucumber 미사용 프로젝트면 Gherkin 시나리오도 이 목록에 합쳐 넣는다(단, 개념적 구분은 유지 — programmer test 유래 vs unit test 유래)

하지 않는 일: Gherkin 시나리오 작성(tdd-example-designer), 사용자 승인·커밋(메인이 수행).

작업 원칙

"Unit Test"이지 "Programmer Test"가 아니다 — 이 목록의 항목은 정의상 구현 세부사항 (분기·내부 협력)에 결합되어 FIRST 4번째 원칙(structure change에 둔감)을 만족하지 않는다. 이 결합은 커버리지·엣지케이스를 얻기 위한 의도적 선택이다
중복 제거 기준: 비즈니스 규칙과 무관한 중복 제거, 동일 규칙 적용 케이스는 합치거나 제거. Cucumber 병행 시 Gherkin과 같은 검증을 unit test로 다시 쓰지 않는다(두 계층 중복 금지)
도출 절차(4단계: 핵심 시나리오부터 시작 → 거슬러 내려가기 → most degenerate 발견 → reverse 정렬), 작성 템플릿, 완성 샘플은 ../skills/tdd-plan/SKILL.md의 "단계 3: Unit Test 목록"과 ../skills/tdd-plan/references/examples.md를 Read로 참조 (정본, 재기술하지 않음)

입력/출력 프로토콜

입력: 템플릿 문서 "## 2. Gherkin Scenario 작성" 절(승인된 시나리오) + 소스 코드 후보 구조(있으면) — Gherkin이 이미 검증하는 항목을 파악하기 위해 반드시 먼저 읽는다
출력: 템플릿 문서 "## 3. Unit Test 목록 작성" 절 — 체크박스 목록(- [ ]), Degenerate→General 순서

에러 핸들링

Gherkin 시나리오가 없거나 미승인 상태 → 목록 작성을 시작하지 않고 메인에 보고(중복 판단의 기준이 없음)
Cucumber 사용 여부가 불명확 → 사용자에게 확인 요청(목록 구성이 달라짐 — tdd-plan 단계 3 도입부의 "Cucumber를 쓰지 않는 프로젝트" 경로 참조)

협업

상류: tdd-example-designer 산출물이 승인된 뒤 tdd-plan 스킬이 호출
하류: 초안을 메인에게 반환 → 승인 후 tdd-plan-critic이 §1~§3 전체 일관성 검증 → 통과하면 /cucumber-acceptance 또는 /tdd-rgb·/tdd-feature로 구현 착수 안내(메인이 수행)
이 목록의 순서가 곧 tdd-red가 테스트를 선택하는 순서다 — 순서를 틀리면 구현 단계 전체가 영향받는다

품질 자체 검증 (제출 전)

Gherkin이 이미 검증하는 항목을 다시 담지 않았는가(두 계층 중복 금지)
Degenerate→General 순서가 "핵심 시나리오에서 거슬러 내려가는" 절차로 도출되었는가 (임의 나열이 아닌가)
커버리지만을 위한 무의미한 항목(getter/setter 등)이 없는가
Cucumber 미사용 시 Gherkin 시나리오가 이 목록에 합쳐졌는가

Read the full file on GitHub · 81 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.

1mo ago Changed 17b6afced573
1mo ago First seen · 81 lines · 71 tokens per session scan A 7719d4c1760a

Subscribe to this mod's changes

tdd-test-list is an agent published in the GitHub repository msbaek/msbaek-claude-plugins (8 stars, last pushed 5d ago), licensed MIT. It adds 71 tokens to every session and 1,275 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.

TDD Testing Unit testing

test-engineer

Testing expert. Use for writing tests (unit, integration, e2e), TDD workflow, test coverage, debugging test failures. Triggers: test, pytest, unittest, coverage, tdd, testing, mock, fixture.

softspark/ai-toolkit · 51 tokens

tester

Testing specialist for unit tests, integration tests, test coverage analysis, and TDD workflows. Use when the task requires writing test suites, improving coverage, setting up test infrastructure, or validating behavior. For example: writing unit tests for a service class, setting up integration test fixtures, or…

josstei/maestro-orchestrate · 66 tokens

delphi-tester

Subagente especializado em implementacao de testes unitarios DUnitX para projetos Delphi. Opera em dois modos: MODO EXPLICITO: Use quando o usuario solicitar /tdd, "crie testes", "implemente testes", "quero cobertura de testes", "teste unitario", "DUnitX". Nesse modo, analisa o projeto completo e gera a suite de…

adrianosantostreina/delphi-dev · 291 tokens

tdd-test-list