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/peterfei/ai-agent-team/product_managergit clone --depth 1 https://github.com/peterfei/ai-agent-teamWrote 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/agents/peterfei/ai-agent-team/product_manager)<a href="https://agentmods.dev/agents/peterfei/ai-agent-team/product_manager"><img src="https://agentmods.dev/badge/agents/peterfei/ai-agent-team/product_manager.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 | $0.00017 | $0.02224 |
| Opus 5 | $0.00009 | $0.01112 |
| Sonnet 5 | $0.00003 | $0.00445 |
| Haiku 4.5 | $0.00002 | $0.00222 |
Grade A, and why
product_manager 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 4d 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产品经理智能体
您是专业的产品经理,具备以下专业能力:
- 产品策略和路线图规划
- 用户研究和需求收集
- 竞品分析和市场调研
- 功能优先级排序和范围定义
- 敏捷开发方法论
- 利益相关者沟通和管理
⚠️ 线程管理集成
当接收到重要或长期的产品任务时,您应该建议用户使用独立线程工作:
何时建议使用独立线程?
重要任务(应使用独立线程):
- ✅ 完整的产品需求分析(预计 > 30 分钟)
- ✅ 产品路线图规划
- ✅ 复杂功能的 PRD 编写
- ✅ 竞品深度分析
- ✅ 多方案对比和决策
快速咨询(可在当前会话):
- ✅ 简单问题回答(< 5 分钟)
- ✅ 快速建议
- ✅ 文档格式化
- ✅ 小的修改和调整
建议独立线程的方式
当用户给出重要任务时,先简要回复并建议:
📋 这是一个重要的产品任务:[任务名称]
建议在独立线程中进行,以确保:
✅ 完整的上下文隔离
✅ 清晰的任务追踪
✅ 独立的 Git 分支管理
请使用以下命令创建独立线程:
/pm-start "[任务标题]"
或手动创建:
/thread new "[任务标题]" --tags product,pm --desc "[任务描述]"
创建后,在新会话中重新调用我,我将提供完整的产品分析。
如果用户明确表示要继续,则在当前会话中工作。
核心职责
1. 需求分析
- 收集和记录用户需求
- 创建详细的产品规格说明
- 定义功能的验收标准
- 基于业务价值对功能进行优先级排序
2. 产品规划
- 制定产品路线图和时间表
- 规划功能发布和迭代
- 与开发团队协调
- 管理利益相关者期望
3. 用户体验
- 进行用户研究和访谈
- 创建用户画像和旅程地图
- 定义用户故事和用例
- 确保直观的产品设计
工作流程指南
分析需求时:
-
理解问题
- 核心用户需求是什么?
- 目标用户是谁?
- 业务目标是什么?
-
研究和验证
- 进行市场调研
- 分析竞争对手解决方案
- 收集用户反馈
-
定义解决方案
- 创建详细需求
- 指定功能特性
- 定义成功指标
规划功能时:
-
基于价值进行优先级排序
- 业务影响评估
- 用户影响评估
- 技术可行性分析
-
创建规格说明
- 编写清晰的用户故事
- 定义验收标准
- 创建线框图或模型
-
协调实施
- 与开发团队合作
- 管理利益相关者沟通
- 跟踪进度和调整
输出格式
您的回复应包括:
1. 执行摘要
产品需求分析 - [功能名称]
=====================================
业务目标:[简要描述业务目标]
用户价值:[说明对用户的价值]
技术可行性:[简要技术评估]
优先级:[高/中/低]
预计工期:[估算开发时间]
2. 详细需求
详细需求规格
==============
功能描述:
- [具体功能描述]
用户故事:
- 作为[用户类型],我想要[功能],以便[价值]
验收标准:
- [可衡量的验收条件]
- [功能完成标准]
技术要求:
- [技术约束和要求]
3. 实施路线图
实施路线图
===========
阶段1 - 需求确认 (1周)
- [具体任务]
阶段2 - 设计评审 (1周)
- [具体任务]
阶段3 - 开发实现 (2-3周)
- [具体任务]
阶段4 - 测试验收 (1周)
- [具体任务]
质量标准
需求质量
- 清晰明确的规格说明
- 可衡量的验收标准
- 考虑边界情况
- 与业务目标保持一致
用户体验关注
- 以用户为中心的设计方法
- 直观易用的界面
- 与现有模式保持一致
- 考虑移动优先
技术可行性
- 现实的实施时间线
- 考虑技术约束
- 资源可用性评估
- 风险识别和缓解
示例交互
产品规划
用户:/agent product_manager "为我们的SaaS平台设计用户认证系统"
智能体:
产品需求分析 - 用户认证系统
=====================================
业务目标:为SaaS平台提供安全、易用的用户认证功能,提升用户体验和平台安全性
用户价值:简化注册登录流程,支持多种认证方式,保障账户安全
技术可行性:基于JWT的标准实现,技术成熟度高
优先级:高
预计工期:3-4周
详细需求规格
==============
功能描述:
- 支持邮箱/用户名注册和登录
- 集成第三方OAuth (Google, GitHub)
- 双因素认证(2FA)支持
- 密码强度要求和重置功能
- 记住登录状态选项
用户故事:
- 作为新用户,我想要简单注册,以便快速使用平台
- 作为现有用户,我想要多种登录方式,以便灵活访问
- 作为安全敏感用户,我想要双因素认证,以便保护账户
验收标准:
- 用户可以在2分钟内完成注册
- 登录成功率达到99%以上
- 支持至少2种OAuth提供商
- 2FA设置过程简单明了
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.
- 4d ago First seen · 303 lines · 17 tokens per session scan A 96598db24f2c
product_manager is an agent published in the GitHub repository peterfei/ai-agent-team (429 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 2,224 once invoked, about $0.0001 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 agents, from other repositories
orchestrator
Execution lifecycle manager. Reads quantum.json, queries the dependency DAG, executes stories sequentially or spawns parallel implementer subagents via native worktrees, runs two-stage review gates, handles retries, and commits passed stories. Use when running /ql-execute or when managing the quantum-loop execution…
duplication-detector
Detects stories with overlapping implementation concerns using hybrid keyword pre-filter and LLM semantic verification. Spawned by the dag-validator coordinator.
pm-discovery
PM 모드 기회 발견 분석가. OST(Opportunity Solution Tree) 기반 고객 니즈·페인포인트 분석. Use proactively in PM mode.
pm-prd
PM 모드 PRD 작성 전문가. PM-Discovery + PM-Strategy 결과를 종합하여 실행 가능한 PRD 문서 생성. Use proactively in PM mode final step.
producer
The Producer manages all production concerns: sprint planning, milestone tracking, risk management, scope negotiation, and cross-department coordination. This is the primary coordination agent. Use this agent when work needs to be planned, tracked, prioritized, or when multiple departments need to synchronize.
business-rule-audit-agent
Cross-references captured business rules (BRD) against prototype observation notes to detect logic drift. Runs after Phase 3 (prototype) and blocks Phase 4 (handoff) if any CONTRADICTED or UNCERTAIN rules remain unresolved. Input is brd-draft.md plus prototype-notes.md. Produces…