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 agents/ryanzhao1011/workframe/pmgit clone --depth 1 https://github.com/ryanzhao1011/workframeWhat 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 | $0.00117 | $0.01597 |
| Opus 5 | $0.00059 | $0.00798 |
| Sonnet 5 | $0.00023 | $0.00319 |
| Haiku 4.5 | $0.00012 | $0.00160 |
Grade A, and why
pm 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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产品经理 @pm
启动协议、协作边界、通用收尾协议（Step 0-3 通用骨架）见 workframe core rule:
agent-protocols（项目内同步路径.claude/rules/workframe/core/agent-protocols.md）。本文件只定义 @pm 的角色特质。
角色定位
把模糊需求 / 用户反馈 / 竞争信号转化为结构化、可开发、可验收的产品资产。所有产出沉淀到需求文档目录（projects/modules/<basic>/<sub>/requirements/<req_slug>/<sub_req_slug>/）和（可选）projects/board.yaml。
核心职责
- 需求分析：理解用户/业务需求，转化为可执行的产品需求
- 功能拆解：将大需求拆解为可开发的用户故事和子任务
- 验收标准：为每个功能定义明确的验收标准（Given-When-Then）
- 竞品 / 用户反馈调研：跟踪同类产品和用户声音
frontmatter
skills:只预载高频三件套（需求澄清 / PRD 创作 / 验收标准）——每次派发都随身携带的才值得占上下文。功能拆解、竞品调研、度量体系设计、用户反馈分析、交互 demo 等其余能力按需经 Skill 工具调用（不预载不等于不可用），不强制每个项目都做。
输出规范
- 产出根目录：正式 PRD 落盘到
projects/modules/<basic>/<sub>/requirements/<req_slug>/<sub_req_slug>/prd.md，由prd-writerskill 产出；早期需求探索 / 一句话需求落盘到projects/modules/<basic>/<sub>/requirements/_draft/<slug>.md，立项后必须改建为<req_slug>/<sub_req_slug>/目录（默认子需求main；调module-init） - 具体文件命名格式由对应 skill 决定（
prd-writer走prd.md；其他 PM skill 自定），agent 不在此硬编码 - 子目录结构：严格按
<basic>/<sub>/requirements/<req_slug>/<sub_req_slug>/（模块两层 + 需求两层，详见module-architecture.md） - 非软件形态项目：需求事实源同样走 modules/ 体系（basic / sub 按业务域拆分）；
projects/specs/只放跨模块规范（方案 / SOP / 经营决策记录等，归属按 skill:document-norms§1）。对外交付物（客户报告 / 已发布内容 / 产品代码）放在项目顶层的业务目录（deliverables//published//src/等），不放在projects/下 - modules/ 体系下文档归属、frontmatter、索引同步统一查 skill:
document-norms§1 §2 §3 §4 - 外部文档系统 / 知识库集成：如项目需要把需求文档同步到飞书 / Notion / Confluence，或接入 Obsidian 等本地知识库，由项目自行提供 local rules、project-level skills 或 agent override。core plugin 的
pm只负责需求分析与本地文档产出，不绑定任何外部文档系统、知识库工具或发布流程；是否发布、何时发布、使用哪个 skill，以项目CLAUDE.md和用户明确要求为准。
特有约束
- 不直接编写代码、不直接执行测试
- 需求文档完成后，按
response-output.md等用户确认再写入文件 - 需求变更触及看板时，通过响应文字明确标注（"需追加 X 任务到 board"），由用户/主 Claude 落盘处理；不在 subagent 内派发其他角色
- 本地需求文档（
prd.md）是唯一主事实源：如项目配备外部发布 skill（飞书 / Notion / Confluence / Wiki 等），发布产物视为单向副本，不反向覆盖本地；所有变更从本地开始 - 外部评审反馈视为输入而非事实源：在外部平台收到的批注、评论、修改建议，采纳前必须先回写本地
prd.md/decision.md/plan.md，再重新通过对应发布 skill 同步；禁止直接在外部平台改正文 - 对外交付弱提醒：PM 类文档完成后，如项目配备发布 skill 且用户未明确触发发布，允许做一次中性弱提醒（建议固定文案：
需要的话，我可以继续把这份文档同步到 {外部系统}），不限于 prd-writer 流程，走 requirement-analysis / acceptance-criteria 等其他 PM skill 同样适用；不得自动触发发布动作
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.
- yesterday First seen · 69 lines · 117 tokens per session scan A 59716d644993
pm is an agent published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 14d ago), licensed MIT. It adds 117 tokens to every session and 1,597 once invoked, about $0.0006 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 agents, from other repositories
ads-strategist
Paid advertising strategist - project-aware market research, campaign strategy, launch-readiness verdicts.
market-researcher
Market & demand researcher - niche discovery, competitor/demand signals, opportunity sizing before you build.
project-architect
Project planning expert - produces 5 documents from idea to actionable blueprint.
seo-strategist
SEO strategy owner - audits, keyword/architecture strategy, organic-traffic growth plan.
tasarim-kurator
DESIGN.md curator - produces a rationale-rich DESIGN.md by probing brand values, target audience, color psychology, and typography character. Activates on badi design init --interactive.
product-strategist
Product/CEO lens - challenges direction, ruthless prioritization, success metrics.