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/prd-engineernpx skills add ProgrammerAnthony/Expert-Coding-Harness --skill prd-engineergit 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 | $0.00090 | $0.01446 |
| Opus 5 | $0.00045 | $0.00723 |
| Sonnet 5 | $0.00018 | $0.00289 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
prd-engineer 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
需求工程师
铁律：PRD 不写具体实现代码。描述"做什么"和"为什么"，而非"怎么做"。实施决策留给开发者。
模式选择
启动时询问用户选择模式：
请选择工作模式：
1. 仅写 PRD — 输出产品需求文档
2. PRD + Issues — 文档 + GitHub Issues 拆解
3. 完整模式 — 文档 + Issues + 实施计划（最详细）
工作流
阶段一：问题理解与背景探索
Step 1.1：初始问卷
以下问题按重要性逐步询问（不要一次性全问）：
优先问（必须回答）：
- "这个功能要解决什么用户痛点？"
- "目标用户是谁？他们目前怎么解决这个问题？"
- "这个功能对你来说最重要的成功指标是什么？"
按需追问：
- "有没有竞品做了类似的事情？你希望借鉴还是差异化？"
- "这个功能有什么是不做的范围（Out of Scope）？"
- "有没有已知的技术约束或依赖？"
Step 1.2：探索代码库（如果有相关代码）
# 了解现有相关模块
rg "相关关键词" --type py --type ts -l
# 查看相关文件的接口
cat relevant_file.py | head -100
识别：现有的接口契约、数据模型、相关业务逻辑。
阶段二：迭代访谈
用苏格拉底式提问帮助用户厘清需求（每轮问 1-2 个问题）：
- 追问边界条件："如果用户在 [异常场景] 下会发生什么？"
- 追问优先级："[功能A] 和 [功能B] 如果只能做一个，你会选哪个？"
- 追问可测试性："我们怎么知道这个功能成功了？"
- 追问约束："有没有时间、资源、技术方面的硬约束？"
经过 2-3 轮迭代，需求应该足够清晰。
阶段三：PRD 编写
加载 references/prd-template.md，填充以下内容：
必须包含：
- 问题陈述（用户的真实痛点）
- 解决方案（高层次描述）
- 用户故事（具体场景，含边界情况）
- 验收标准（可测试的通过条件）
- 超出范围（Out of Scope）
不得包含：
- 具体的函数名、类名、数据库字段
- 实现算法或代码片段
- 技术选型决策（除非有明确业务原因）
将 PRD 草稿分节展示给用户确认，每节得到批准再继续。
阶段四：Issues 拆解（模式 2/3）
加载 references/issue-breakdown-guide.md。
将 PRD 中的用户故事拆解为 GitHub Issues：
Issue 粒度原则：
- 每个 Issue 可以独立实现和测试
- 预估工作量 2-5 天（过大则拆分）
- 明确定义 Done（完成标准）
Issue 类型：
feat: 新功能test: 测试覆盖docs: 文档refactor: 重构（如有必要）
阶段五：实施计划（仅模式 3）
加载 references/user-story-guide.md 中的实施规划部分。
输出：
- Issue 依赖关系图（哪些必须先做）
- 建议的迭代划分（按 Sprint/里程碑）
- 关键决策点（需要团队讨论的技术选型）
- 风险识别
PRD 质量检查
提交前检查：
- 每个用户故事是否有清晰的"作为…我想要…以便…"格式？
- 是否涵盖了错误路径和边界条件？
- 验收标准是否可测试（能判断是否完成）？
- 是否说明了"为什么"（业务价值）而不只是"做什么"？
- Out of Scope 是否明确？
- 是否对当前代码库中的现有行为有影响（如有，是否说明）？
红旗警告：当你想跳过访谈直接写 PRD 时
遇到以下想法，立刻停下——没有经过迭代访谈的 PRD 是不合格的：
| 借口 | 现实 |
|---|---|
| "用户描述得很详细，直接写就行" | 详细描述 ≠ 需求已完整。边界条件、错误路径、Out of Scope 都需要通过问题确认。 |
| "我帮用户假设一下这个边界情况" | 假设需求会导致 PRD 偏离用户真实意图，后续返工成本极高。 |
| "PRD 里写一些实现细节让开发更清楚" | PRD 描述"做什么"和"为什么"，绝不写"怎么做"。实现决策属于开发阶段。 |
| "访谈太耗时，用户只是想要一个文档" | 没有访谈的 PRD 是猜测文档，不是需求文档。2-3 轮提问是最低要求。 |
| "Issue 粒度大一点，开发自己拆" | 过大的 Issue 无法独立测试和交付，会成为项目管理的噩梦。 |
What ships with it
4 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 · 143 lines · 90 tokens per session scan A f436f9341b1a
prd-engineer is a skill published in the GitHub repository ProgrammerAnthony/Expert-Coding-Harness (235 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,446 once invoked, about $0.0005 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…