product_manager

product_manager is an agent for Claude Code from peterfei/ai-agent-team. It costs 17 tokens per session (2,224 once invoked), scanned A, original, MIT.

A product-management agent for planning software products. It helps analyze needs, research users and competitors, define requirements, prioritize work, and plan product releases.

In plain words
What is it for?
Use it for product discovery, roadmaps, requirements documents, user stories, acceptance criteria, prioritization, and stakeholder planning.
Why use it?
It turns broad product ideas into clearer requirements and decisions, while keeping large planning efforts organized and separate when needed.

Agent for Claude Code

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/peterfei/ai-agent-team/product_manager
Clone the repo
git clone --depth 1 https://github.com/peterfei/ai-agent-team

Made for: Claude Code.

Wrote 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.

agentmods badge for product_manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/peterfei/ai-agent-team/product_manager.svg)](https://agentmods.dev/agents/peterfei/ai-agent-team/product_manager)
Your own site
<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>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,224 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 $0.00017 $0.02224
Opus 5 $0.00009 $0.01112
Sonnet 5 $0.00003 $0.00445
Haiku 4.5 $0.00002 $0.00222

Measured 4d ago against content hash 96598db24f2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/agents/product_manager.md · 303 lines

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:

  1. 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?
  2. 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
  3. 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:

  1. 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
  2. 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
  3. 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

Read the full file on GitHub · 303 lines

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. 4d ago First seen · 303 lines · 17 tokens per session scan A 96598db24f2c

Subscribe to this mod's changes

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.

Related

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…

andyzengmath/quantum-loop · 64 tokens

duplication-detector

Detects stories with overlapping implementation concerns using hybrid keyword pre-filter and LLM semantic verification. Spawned by the dag-validator coordinator.

andyzengmath/quantum-loop · 31 tokens

pm-discovery

PM 모드 기회 발견 분석가. OST(Opportunity Solution Tree) 기반 고객 니즈·페인포인트 분석. Use proactively in PM mode.

smorky850612/Aurakit · 36 tokens

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.

smorky850612/Aurakit · 40 tokens

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.

IdoCohen560/claude-unity-game-studio · 56 tokens

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…

richfrem/agent-plugins-skills · 89 tokens