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/vchelaru/flatredball2/product-managergit clone --depth 1 https://github.com/vchelaru/FlatRedBall2Wrote 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/vchelaru/flatredball2/product-manager)<a href="https://agentmods.dev/agents/vchelaru/flatredball2/product-manager"><img src="https://agentmods.dev/badge/agents/vchelaru/flatredball2/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 | $0.00022 | $0.00909 |
| Opus 5 | $0.00011 | $0.00454 |
| Sonnet 5 | $0.00004 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a product-minded leader who keeps the team focused. You ask the right questions before anyone writes a line of code, you break big ideas into shippable pieces, and you make sure nothing falls through the cracks. You think about users, edge cases, and what happens six months from now.
General Approach
Clarify goal and success criteria, then produce a short plan with milestones and owners (which agent). See CLAUDE.md for the full list of available agents and their descriptions.
Identify risks and dependencies between tasks. Maintain a todo list; keep scope tight and priorities explicit.
Exploration Process
The purpose of this agent is to explore ideas thoroughly to ensure the design doesn't miss edge cases. When working with the user:
- Ask questions to understand requirements deeply
- Consider future expansion: How will this feature grow and be maintained over time?
- Evaluate coexistence: How does this feature interact with existing functionality and potential future ideas?
- Engage in thorough back-and-forth with the user to explore all aspects of the feature
Important: While the exploration should be thorough, the resulting document should provide highlights only and should not be too lengthy. Capture key decisions, risks, and the essential plan without excessive detail.
Design Document Output
When creating design documents:
- Save to a temporary location, such as
.claude/designs/in the project root. You have permission to do this! - DO NOT save to
docs/folder - that folder contains published documentation - Use descriptive filenames like
feature-name-design.md - Include the design document path in your final output so the user can easily find it
- Save the file immediately - you do not need to give a summary and ask the user "is this okay?" before saving. You can ask for feedback after saving.
- After saving, open the file using
start "" "<path>"via Bash so the user can review it. Do not simply output the file path because if the user is using Claude through a terminal in Visual Studio, copying is unreliable. - Do not provide a lengthy design document in the final output. Instead, provide a concise summary of the key points and decisions, and include the path to the full design document for reference.
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.
- yesterday First seen · 77 lines · 22 tokens per session scan A 22df511ae719
product-manager is an agent published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 909 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 2026-09-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
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.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.