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 instructions/derricktang/pm-workflow-plugin/claude-mdgit clone --depth 1 https://github.com/derricktang/pm-workflow-pluginWrote 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/instructions/derricktang/pm-workflow-plugin/claude-md)<a href="https://agentmods.dev/instructions/derricktang/pm-workflow-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/derricktang/pm-workflow-plugin/claude-md.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 | $0.13700 | $0.13700 |
| Opus 5 | $0.06850 | $0.06850 |
| Sonnet 5 | $0.02740 | $0.02740 |
| Haiku 4.5 | $0.01370 | $0.01370 |
Grade A, and why
pm-workflow-plugin CLAUDE.md 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 3d 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 — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目性质
这是一个 AI 产品工作流项目，不含可执行代码。所有工作均以 Markdown 文件驱动，由 Claude Code 扮演编排器，协调两个 AI Agent（产品经理、产品主管）完成产品文档的全流程生产与审核。
斜杠命令
| 命令 | 说明 |
|---|---|
/newRequirement <需求文件或文字> |
启动新需求工作流，从需求分析开始执行全四阶段 |
/nextStage |
产品总监正式通过当前阶段，推进至下一阶段 |
/projectStatus |
查看当前工作流进度简报 |
/changeRequest |
启动需求变更工作流 |
/retro |
问题复盘：分析最新未分析的调整意见文件，找共性根因 + 提机制改进（避免同类问题再次发生），等产品总监确认后再标记为已分析 |
/investigate |
调查分析指令：对非平凡的调查 / 排查 / 评估 / 审计 / 逻辑缺陷检查走标准化三步（选执行者 → 取证 doc_query+命令实证 → 呈现前对抗 pass 5 段 checklist），杜绝单遍自评漏判。编排器给非平凡结论前亦自走 |
命令定义在 .claude/commands/ 目录下，每个命令是一个 Markdown 文件。
[Must] /changeRequest vs 调整意见 判定对照表（议题 29 防误读，议题 26 §1.D 同型延续）
下游 PM 易把"PM 实现整改"误当"业务需求变更"启动 /changeRequest（实证：下游误用 /changeRequest 处理 UI 表达层重组）。本对照表 [Must] 在判定时 grep 命中即用，禁推断。
| 维度 | /changeRequest 适用 | 调整意见 / PM 实现整改 适用 |
|---|---|---|
| 触发性质 | 客户/产品总监对业务功能层的新增/变更/废弃诉求 | PM 在某阶段对实现表达方式的选择不优 |
| 业务需求 | ✅ 变更 | ❌ 不变 |
| 流程载体 | process_record/changes/CR-XXX_*.md + 串行约束（CR 必须闭环才能启动下一个） |
process_record/issues/YYYY-MM-DD_HHMM.md（按本文件 §「调整意见自动记录规则」4 步流程） |
| 版本号 | 主版本 +1 / 次版本归零（v0.1→v1.0 / v1.x→v2.0） | 不动版本号 + 不入变更记录表（产品阶段内部循环不暴露下游，G-02 派生） |
| 典型场景 | 新需求加章节 / 删除功能 / 客户决策变更架构 / 业务规则改变 | PM 优化 UI 表达 / 重组页面承载（如 P06 独立路由 → P01 卡片子态） / 整改 PRD 字面 / 修复 spec 缺漏 |
| 反 pattern（议题 26 §1.D 对立字面自检） | ❌ 误把 PM 实现整改当业务变更 → 误启动 /changeRequest 触发 CR 串行 + 升版本号 + 下游误感知伪 release | ❌ 误把业务需求变更当调整意见 → 不入 CR 链路 + 下游无感知真业务变化 |
判定 SOP（PM 自检 3 步，禁推断）：
- 业务需求是否变？（管理员/客户/系统行为意图是否改变）— 是 → /changeRequest；否 → 调整意见
- 变更承载在哪？（业务功能/规则/状态/数据流 vs UI 表达/页面组织/字面表达）— 业务层 → /changeRequest；表达层 → 调整意见
- 下游消费方是否需感知？（外部 release 需感知版本变化 vs 内部循环不暴露）— 需感知 → /changeRequest；不需感知 → 调整意见
详细参考（议题 26 §1.D 对立字面互引）：
- /changeRequest 流程定义 →
.claude/commands/changeRequest.md - 调整意见流程定义 → 本文件 §「调整意见自动记录规则」
- 版本号纪律 → 本文件 §「文件命名规范」L412（PM 自审整改不动版本号 + 阶段 4 G-02 SemVer 触发点）
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.
- 3d ago First seen · 453 lines · 13,700 tokens per session scan A d33842ddd8bf
pm-workflow-plugin CLAUDE.md is an instructions file published in the GitHub repository derricktang/pm-workflow-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 13,700 tokens to every session, about $0.0685 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 2026-08-31.
Other instructions, from other repositories
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
harness-starter-kit AGENTS.md
Instructions for harnessworks/harness-starter-kit, covering agents.md, purpose, core rules, command routing and project analysis rule.
hyper-waterfall CLAUDE.md
Instructions for postmelee/hyper-waterfall: 본 저장소의 에이전트 운영 규칙은 AGENTS.md를 단일 진실 원천으로 한다. Claude Code도 이 규칙을 그대로 적용한다.
mumei CLAUDE.md
Instructions for iroha924/mumei, covering mumei development guide, what mumei is, language policy, bash + jq conventions (essentials) and schemas/ conventions (essentials).
gru-ai CLAUDE.md
Instructions for andrew-yangy/gru-ai, covering gruai — claude code rules, what this is, context tree structure, how to read the context tree and key conventions.
harness-evolver CLAUDE.md
Instructions for raphaelchristi/harness-evolver, covering claude.md, what this is, dependencies, running tools locally and use --no-canary to skip preflight check.