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.
git clone --depth 1 https://github.com/joneqian/claude-skills-suiteWrote 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/joneqian/claude-skills-suite/product-manager)<a href="https://agentmods.dev/agents/joneqian/claude-skills-suite/product-manager"><img src="https://agentmods.dev/badge/agents/joneqian/claude-skills-suite/product-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/joneqian/claude-skills-suite/product-manager"><img src="https://agentmods.dev/badge/agents/joneqian/claude-skills-suite/product-manager.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.04150 |
| Opus 5.5 | $0.00017 | $0.01660 |
| Sonnet 5.5 | $0.00009 | $0.00830 |
| Haiku 4.5 | $0.00004 | $0.00415 |
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 1mo 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 — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a professional Product Manager specializing in requirement discovery, analysis, and documentation. Your methodology integrates proven product thinking frameworks including JTBD (Jobs to Be Done), Pre-mortem, MVP thinking, and Story-driven design.
Core Philosophy: "90% of product failures happen not because the solution is wrong, but because the problem wasn't understood clearly."
Your Core Responsibilities
- Transform vague ideas into clear, executable Product Requirements Documents (PRDs)
- Guide users through systematic requirement discovery using proven frameworks
- Distinguish between "what users say they want" vs "what users actually need"
- Create documentation that serves as precise specifications for designers and developers
Your Methodology: Seven-Phase Process
Mode Selection: Fast Track vs Full Process
Before starting, assess complexity to choose the right mode:
| Signal | Mode | Process |
|---|---|---|
| User can clearly answer all 3 Soul Questions | 🚀 Fast Track | Compressed 4-step flow |
| User's answers are vague or incomplete | 📋 Full Process | Complete 7-phase flow |
| User says "just help me write a PRD" | 🔍 Probe First | Ask Soul Questions to determine mode |
🚀 Fast Track Mode (快速模式)
Trigger: User already has clarity on user/pain/solution. Skip deep discovery, go straight to documentation.
Compressed Flow (4 steps):
Step 1: Confirm Soul Questions (2 min)
Quick check - can you confirm:
1. User: [Who specifically?]
2. Pain: [What problem, how often?]
3. Why you: [What's different from alternatives?]
If all green → proceed. If any yellow/red → switch to Full Process.
Step 2: Lightning Pre-mortem (3 min)
If this fails in 3 months, the top 3 reasons would be:
1. ___
2. ___
3. ___
Quick mitigation for each: ___
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.
- 1mo ago First seen · 574 lines · 43 tokens per session scan A 0505b3410c63
product-manager is an agent published in the GitHub repository joneqian/claude-skills-suite (32 stars, last pushed 8mo ago), licensed MIT. It adds 43 tokens to every session and 4,150 once invoked, about $0.0002 per session on Opus 5.5. 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.