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 skills/programmeranthony/expert-coding-harness/tdd-masternpx skills add ProgrammerAnthony/Expert-Coding-Harness --skill tdd-mastergit clone --depth 1 https://github.com/ProgrammerAnthony/Expert-Coding-HarnessWhat 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 | $0.00083 | $0.02019 |
| Opus 5 | $0.00042 | $0.01009 |
| Sonnet 5 | $0.00017 | $0.00404 |
| Haiku 4.5 | $0.00008 | $0.00202 |
Grade A, and why
tdd-master 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 2d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD 开发大师
铁律：没有失败的测试，不写一行生产代码。 先写代码再补测试的，必须删掉先写的代码重来。
核心哲学
竖向切片，而非横向切片
反模式（横向切片）：先把所有测试写完，再一口气写所有实现
- 问题：测试套件成为规格书，不是活文档；实现阶段难以获得快速反馈
正确做法（竖向 tracer bullet 切片）：每次选一个最小可验证行为，完成 RED→GREEN→REFACTOR 完整循环
- 每个切片都是端到端的最小功能（一个完整行为）
- 通过测试可以立即运行并得到结果
测试测行为，而非测实现
# 错误：测试内部实现（脆弱，重构即失效）
def test_calls_validate_method():
service = UserService()
with patch.object(service, '_validate') as mock:
service.create_user(data)
mock.assert_called_once()
# 正确：测试可观察行为（稳健，重构不影响）
def test_create_user_returns_user_id():
service = UserService()
user_id = service.create_user({"name": "Alice", "email": "[email protected]"})
assert isinstance(user_id, int)
assert user_id > 0
工作流
阶段一：规划（获得用户批准前禁止写代码）
1.1 接口设计
先设计公共接口，不暴露内部实现细节：
询问用户：这个功能/模块需要提供什么公共接口？
输出：函数/方法签名 + 输入/输出类型 + 前置/后置条件
加载 references/testing-principles.md 检查接口设计原则。
1.2 行为清单
将功能拆解为可测试的行为列表：
待实现的行为：
- [ ] 正常路径：[描述]
- [ ] 边界条件：[描述]
- [ ] 错误路径：[描述]
- [ ] 并发场景：[如适用]
每个行为必须是：独立可测试 + 有明确期望结果 + 最小粒度
1.3 可测试性检查
评估设计是否可测试（加载 references/testing-principles.md）：
- 依赖是否可以被替换（Mock/Stub）？
- 是否有隐藏的全局状态？
- 是否混合了业务逻辑和 I/O？
将设计展示给用户确认，批准后才开始实现。
阶段二：RED-GREEN-REFACTOR 循环
每次选一个行为（从行为清单第一项开始）：
RED 阶段
-
写最小的失败测试：
- 测试名称描述行为（
test_用户注册成功返回用户ID） - 只测一个行为
- 使用尽可能真实的代码（避免过度 mock）
- 测试名称描述行为（
-
强制验证 RED（不可跳过）：
pytest tests/test_user.py::test_用户注册成功返回用户ID -v
确认：测试因正确原因失败（功能未实现），而非因测试代码错误失败
- RED 失败则停止：如果无法让测试变红，说明测试本身有问题，先修复测试
GREEN 阶段
-
写最小的实现：只写让当前测试通过所需的最少代码
- 可以暂时硬编码（如
return 42），只要测试通过 - 禁止超前实现"以后会用到的"功能
- 可以暂时硬编码（如
-
强制验证 GREEN（不可跳过）：
pytest tests/test_user.py -v确认：全部测试通过，包括之前的测试
-
GREEN 失败则停止：回到实现代码修复，不重构，不写新测试
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 205 lines · 83 tokens per session scan A a8c31ca3fc0b
tdd-master is a skill published in the GitHub repository ProgrammerAnthony/Expert-Coding-Harness (235 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 2,019 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.