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/davidyichengwei/agentic-engineering-framework/workflow-requirements-clarificationnpx skills add davidYichengWei/agentic-engineering-framework --skill workflow-requirements-clarificationgit clone --depth 1 https://github.com/davidYichengWei/agentic-engineering-frameworkWrote 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/skills/davidyichengwei/agentic-engineering-framework/workflow-requirements-clarification)<a href="https://agentmods.dev/skills/davidyichengwei/agentic-engineering-framework/workflow-requirements-clarification"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agentic-engineering-framework/workflow-requirements-clarification.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.02835 |
| Opus 5 | $0.00026 | $0.01418 |
| Sonnet 5 | $0.00010 | $0.00567 |
| Haiku 4.5 | $0.00005 | $0.00283 |
Grade A, and why
workflow-requirements-clarification 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 5d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
需求澄清
核心定位
AI 负责调研代码背景，用户负责提供需求信息。
AI 职责划分
AI 自己调研（读代码）：
- 现有实现是怎样的
- 代码路径、数据流
- 已有的接口和数据结构
- 技术约束（如使用的框架）
- 相关模块的职责
向用户询问：
- 为什么需要这个功能
- 要解决什么问题
- 具体要做哪些功能
- 目标和成功标准
- 非目标（不做什么）
- 性能/兼容性等非功能需求
规则：如果信息可以从 codebase 获取，AI 必须自己调研，不问用户。
苏格拉底式提问
向用户询问需求信息时，采用苏格拉底式提问——刨根问底，理解问题本质：
| 技巧 | 说明 | 示例 |
|---|---|---|
| 追问 Why | 不接受表面答案，追问到问题本质 | 用户："加个缓存" → AI："为什么需要缓存？慢到什么程度？目标是多少？" |
| 指出矛盾 | 发现用户表述中的矛盾时，引导用户澄清 | 用户："要高并发，但不能改接口" → AI："异步化会改变接口语义，这两个目标是否冲突？" |
| 揭示遗漏 | 引导用户思考未考虑的场景 | AI："你考虑过 X 失败的情况吗？" |
AI 生成内容的前置条件
- AI 已完成代码调研（理解现状，并向用户确认）
- AI 已充分追问（理解问题本质）
- 加载相关规范（如
bp-distributed-systems等）
触发条件
- 用户描述功能需求但缺乏具体细节
- 用户请求开发新功能
spec.md不存在或需求章节为空
对话模式
AI 角色边界
| AI 应该做 | AI 不应该做 |
|---|---|
| 提问，追问 Why | 未经请求就给答案 |
| 指出矛盾或遗漏 | 未追问清楚就生成内容 |
| 质疑不清晰的表述 | 跳过追问直接给建议 |
| 用户请求时生成内容 | 生成后不询问用户意见 |
每轮对话结构
1. 说明当前阶段和目标
2. 提出一个开放式问题（让用户思考）
3. 等待用户回答
4. 评估用户回答：
- 清晰完整 → 复述确认，进入下一问题
- 模糊 → 追问具体含义
- 有矛盾 → 指出矛盾
- 有遗漏 → 引导思考
5. 用户澄清后，再次确认
工作流程
Step 0: 评估复杂度并创建 spec
| 复杂度 | 信号 | 处理方式 |
|---|---|---|
| 简单 | bug fix、配置调整、单点修改 | 不创建 spec，1-2 轮对话后直接进入 code-generation |
| 中等 | 涉及多文件、单模块功能 | 创建 spec |
| 复杂 | 跨模块、新特性、架构变更 | 创建 spec |
中等及以上：立即创建目录并复制模板：
mkdir -p docs/design-docs/<module>/<feature>/
cp skills/workflow-requirements-clarification/reference/spec_template.md \
docs/design-docs/<module>/<feature>/spec.md
路径规则：根据功能所属模块确定。文件名必须是 spec.md。
Step 1: 代码调研（AI 自主完成）
目标：理解现有实现，不询问用户
AI 操作：
- 调用
codebase-researchersubagent 深度调研相关代码（模块结构、接口、依赖关系、数据流） - 识别相关模块、接口、数据结构
- 生成现状分析摘要
向用户汇报（必须）：
我先调研了一下相关代码：
**相关模块**：
- [文件路径1]: [职责说明]
- [文件路径2]: [职责说明]
**现有实现**：
[概述当前的实现方式、数据流、关键接口]
**技术约束**：
- [约束1，如使用的框架、协议]
- [约束2，如已有的接口规范]
请确认我的理解是否正确？有遗漏或错误的地方吗？
结束条件：用户确认理解正确。必须等用户确认后才能进入 Step 2。
实时更新 spec：用户确认后，更新 spec.md 的 1.2 现状分析 和 1.3 主要使用场景。
What ships with it
1 file 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.
- 5d ago First seen · 270 lines · 52 tokens per session scan A 08616ec41f95
workflow-requirements-clarification is a skill published in the GitHub repository davidYichengWei/agentic-engineering-framework (158 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 2,835 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…