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 skills add Today-Hbw/claude-code-dev-workflow --skill read-prdgit clone --depth 1 https://github.com/Today-Hbw/claude-code-dev-workflowWrote 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/today-hbw/claude-code-dev-workflow/read-prd)<a href="https://agentmods.dev/skills/today-hbw/claude-code-dev-workflow/read-prd"><img src="https://agentmods.dev/badge/skills/today-hbw/claude-code-dev-workflow/read-prd/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.
<a href="https://agentmods.dev/skills/today-hbw/claude-code-dev-workflow/read-prd"><img src="https://agentmods.dev/badge/skills/today-hbw/claude-code-dev-workflow/read-prd.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00023 | $0.00883 |
| Opus 5.5 | $0.00009 | $0.00353 |
| Sonnet 5.5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
read-prd 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.
What it actually says
读 PRD · 方法论
你的任务
读取 PRD 文件（PDF、MD、HTML），提取需求要点，识别可独立交付的任务单元。在对话中输出摘要供用户确认，不写 MD 文件。
执行步骤
1. 文件扫描
用 Glob 扫描 PRD 目录：
**/*.pdf— PDF 需求文档**/*.md— Markdown 需求文档**/*.html、**/*.htm— HTML 需求文档- 忽略隐藏文件和
.idea/等 IDE 目录
2. 逐文件阅读
MD 文件：直接 Read 全部内容
HTML 文件：直接 Read 全部内容
- 读取时忽略标签、样式、脚本噪音，聚焦正文需求内容
PDF 文件：使用 Read 工具的 pages 参数分页读取
- 先读第 1 页，判断是否相关
- 相关则继续读后续页
- 每次最多读 10 页
内嵌截图/原型是视觉规格的权威来源：PRD 里带标注的 UI 截图、原型图与散文正文同等重要。读到图不要略过，逐张逐元素提取以下视觉规格五要素：
- 字段所在列：折进已有列（合并）还是独立新列
- 按钮/入口的精确文案：照抄图中原文，不自拟、不改写、不增减字
- 元素所在页签/区域：挂到已有页签，还是新建
- 筛选项位置：与哪些现有项并列
- 字段/筛选的排列顺序
凡图里已给出的位置/文案，即为已定死的规格，不得当作开放项。
3. 信息提取
对每个文件提取：
| 提取项 | 说明 |
|---|---|
| 任务名称 | 简短描述（10 字以内） |
| 任务 ID | 如 ID1019077（从文件名或内容中提取） |
| 核心需求 | 这个任务要做什么（1-3 句话） |
| 涉及页面/模块 | 前端页面、后端模型、数据库表 |
| 关键约束 | 边界条件、依赖关系、特殊规则 |
| 视觉规格 | 有截图/原型时必填：按视觉规格五要素逐元素照图记录；无图则记「正文与图均未给出」 |
4. 需求摘要输出
按以下格式在对话中输出摘要，向用户确认：
## 需求摘要
共发现 N 个文件，识别 M 个可交付任务：
### 任务 1：<任务名>（IDxxxxxxx）
- **核心需求**：...
- **涉及模块**：...
- **关键约束**：...
- **视觉规格（据截图/原型）**：按五要素记录；无图则写「正文与图均未给出」
### 任务 2：<任务名>（IDxxxxxxx）
- ...
请确认以上理解是否正确，或补充遗漏的需求。
注意事项
- PDF/HTML 中的标注截图、原型不是配图噪音，须逐元素提取视觉规格
- 如果 PDF 无法读取，提示用户转换为 MD 或手动粘贴内容
- HTML 聚焦正文，忽略无关标记
- Word（.doc/.docx）等二进制格式不支持：提示用户先另存为 PDF/MD
- 不要遗漏任何文件
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 First seen · 86 lines · 23 tokens per session scan A e931ba0328d4
read-prd is a skill published in the GitHub repository Today-Hbw/claude-code-dev-workflow (23 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 883 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
summarize-transcript
Analyze and summarize a transcript, meeting notes, or discussion thread into a clear actionable document.
notebooklm-grounded-research
Use when: NotebookLM, notebooklm MCP, large documentation sets, courses, books, papers, or citation-backed research are mentioned. Retrieves a small grounded answer from a stable corpus, preserves citations, and verifies claims against primary documentation, repository code, and tests. Do not use when: the answer is…
add-template
Scaffold a new document template inside an existing addon or framework.
alterlab-markitdown
Converts files and Office documents to clean, LLM-friendly Markdown with Microsoft MarkItDown (markitdown CLI, Python API, and markitdown-mcp server), supporting PDF, DOCX, PPTX, XLSX/XLS, images (EXIF metadata, LLM descriptions), audio (transcription), HTML, CSV, JSON, XML, ZIP archives, EPUB e-books, Outlook MSG…
alterlab-open-notebook
Runs and scripts Open Notebook, a self-hosted open-source alternative to Google NotebookLM with a full REST API, for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating…
alterlab-iso13485
Prepares ISO 13485 certification documentation for medical device Quality Management Systems (QMS) — gap analysis of existing documentation, Quality Manuals, required procedures and work instructions, and Medical Device Files. Use for ISO 13485 QMS documentation, conducting a documentation gap analysis, drafting a…