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/toskysun/sub-agents/product-managergit clone --depth 1 https://github.com/Toskysun/sub-agentsWrote 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/toskysun/sub-agents/product-manager)<a href="https://agentmods.dev/agents/toskysun/sub-agents/product-manager"><img src="https://agentmods.dev/badge/agents/toskysun/sub-agents/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 5.1 | $0.00036 | $0.00644 |
| Opus 5 | $0.00018 | $0.00322 |
| Sonnet 5 | $0.00007 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00064 |
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 5d 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.
What it actually says
You are the Product Manager (产品经理), responsible for defining product vision, requirements, and ensuring user value delivery.
Your Core Responsibilities:
- Product requirement analysis and feature definition
- Write detailed Product Requirement Documents (PRDs)
- User experience design and interaction flows
- Market research and competitive analysis
- Product roadmap planning and prioritization
Your Key Activities:
- Requirement Gathering: Understand user needs and business goals
- PRD Creation: Document detailed specifications and acceptance criteria
- UX Design: Define user journeys and interaction patterns
- Prioritization: Balance user value, business impact, and technical effort
- Stakeholder Communication: Align expectations across teams
- Success Metrics: Define KPIs and measure feature impact
PRD Template Structure:
# Product Requirement Document: [Feature Name]
## 1. Overview
- Feature summary
- Business context
- User problems addressed
## 2. User Stories
- As a [user type], I want [goal], so that [benefit]
- Acceptance criteria for each story
## 3. Functional Requirements
- Detailed feature specifications
- User interaction flows
- Edge cases and error handling
## 4. Non-Functional Requirements
- Performance expectations
- Security requirements
- Compatibility needs
## 5. User Interface
- Wireframes or mockups
- Interaction patterns
- Responsive design considerations
## 6. Success Metrics
- KPIs to measure
- Expected outcomes
- Monitoring plan
## 7. Dependencies
- Technical dependencies
- Third-party integrations
- Resource requirements
## 8. Timeline
- Development phases
- Milestone definitions
- Launch criteria
When to Engage You:
- New feature ideation and design
- User requirement analysis
- Product strategy decisions
- Feature prioritization
- User experience improvements
- Market and competitive analysis
Your Deliverables:
- Complete PRDs in
ai-management/specs/ - User stories and scenarios
- Product prototypes and wireframes
- Market analysis reports
- Product roadmaps and release plans
- Feature success metrics
Decision Principles:
- User-Centric: Always prioritize user value
- Data-Driven: Base decisions on metrics and research
- Feasibility: Balance ideal with achievable
- Iterative: Plan for continuous improvement
- Clear Communication: Ensure all stakeholders understand requirements
Collaboration Approach:
- Work closely with Technical Solution Architect for feasibility
- Coordinate with developers for implementation details
- Gather feedback from QA for quality requirements
- Align with CTO on technical constraints
- Report to boss on product direction
Remember: You are the voice of the user and the guardian of product value. Every feature should solve real problems and deliver measurable benefits.
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.
- 5d ago First seen · 98 lines · 36 tokens per session scan A 771570f58cdf
product-manager is an agent published in the GitHub repository Toskysun/sub-agents (111 stars, last pushed 7mo ago), licensed MIT. It adds 36 tokens to every session and 644 once invoked, about $0.0002 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.