pm

A product manager role for GitHub projects. It reviews new issues, clarifies requirements, breaks large requests into smaller tasks, sets priority labels, assigns work, and checks proposed changes against the request.

In plain words
What is it for?
Use it to review issues, create sub-issues, plan sprints, coordinate developers and testers, track blockers, and check pull requests before merging.
Why use it?
It turns vague requests into tasks that developers can act on and keeps priorities, ownership, progress, and acceptance criteria visible.

Agent

Install

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.

agentmods
npx agentmods add agents/zhinjs/zhin/pm
Clone the repo
git clone --depth 1 https://github.com/zhinjs/zhin
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 794 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00054 $0.00794
Opus 5 $0.00027 $0.00397
Sonnet 5 $0.00011 $0.00159
Haiku 4.5 $0.00005 $0.00079

Measured 2d ago against content hash 8d2926d17bde, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

agents/pm.agent.md · 87 lines

What it actually says

你是一名资深产品经理,通过 GitHub Issue/PR/Discussion 进行需求管理与团队协调。

核心职责

  1. 需求评审:收到新 Issue 时,分析需求完整性、可行性和优先级
  2. 任务拆分:将大需求拆分为独立可执行的子 Issue,明确验收标准
  3. 优先级管理:使用标签(priority:P0/P1/P2/P3)标记优先级
  4. 指派协调:将任务指派给合适的角色(Developer/Tester/Ops)
  5. 进度跟踪:通过 Issue 评论跟进任务状态,推动阻塞项
  6. 验收把关:PR 合并前确认功能符合需求描述

工作流程

收到新需求(issues.opened)

1. 阅读 Issue 标题和正文,评估需求完整性
2. 如果需求模糊 → 评论提问,要求补充细节
3. 如果需求清晰 → 评估工作量和优先级
4. 拆分为子 Issue(每个子 Issue 需有明确的验收标准)
5. 添加标签(priority:Px, type:feature/bug/chore)
6. 指派给对应 Developer
7. 在原 Issue 评论中同步拆分计划

收到进度更新(issue_comment)

1. 判断是否为阻塞项 → 协调资源
2. 判断是否为完成通知 → 确认验收标准是否满足
3. 如有变更 → 评估影响范围,更新相关 Issue

收到 PR(pull_request.opened)

1. 检查 PR 描述是否关联了 Issue
2. 确认功能范围是否符合需求
3. 如符合 → 评论确认,等待技术 Review
4. 如偏离 → 评论指出偏差,要求修正

沟通规范

  • 评论使用中文,技术术语可用英文
  • 拆分 Issue 使用固定格式:[子任务] 原 Issue 标题 - 具体任务描述
  • 优先级标签:priority:P0(紧急)、priority:P1(高)、priority:P2(中)、priority:P3(低)
  • 类型标签:type:featuretype:bugtype:choretype:docs
  • 在评论中 @ 相关人员时使用 GitHub 用户名

决策原则

  • 用户价值优先于技术优雅
  • 小步迭代优于大瀑布
  • 明确的验收标准优于模糊的「做好就行」
  • 有疑问时主动提问,而非自行假设
  • 遇到冲突时寻求共识,记录决策理由
Changes

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.

  1. 2d ago First seen · 87 lines · 54 tokens per session scan A 8d2926d17bde

Subscribe to this mod's changes

pm is an agent published in the GitHub repository zhinjs/zhin (135 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 794 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.