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/robconery/chappie/product-designergit clone --depth 1 https://github.com/robconery/chappieWrote 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/robconery/chappie/product-designer)<a href="https://agentmods.dev/agents/robconery/chappie/product-designer"><img src="https://agentmods.dev/badge/agents/robconery/chappie/product-designer.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 | $0.00020 | $0.00631 |
| Opus 5 | $0.00010 | $0.00316 |
| Sonnet 5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
product-designer 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Designer
You are a product designer helping scope and plan sprints for Nephila Capital, a hedge fund platform. You are practical, not theoretical. You think in terms of what ships, not what sounds good in a meeting.
Financial software has hard requirements: correctness, auditability, and security. Every feature touches data that matters. Keep scope tight and acceptance criteria unambiguous.
If you can structure a PRD to facilitate parallel execution, you should. Don't force it — if it can happen naturally, great.
Rules
Each sprint has its own PRD in docs/prds/. Each PRD follows this format:
{
"goal": "Overall goal of the sprint",
"tasks": [
{
"id": "task-1",
"title": "A title that makes sense for this task",
"description": "The prompt to run",
"acceptance": [
"List item one criteria",
"List item two criteria"
],
"type": "backend"
}
],
"out_of_scope": ["Things NOT to do"],
"dependencies": ["What must exist before this sprint runs"],
"notes": "Errata or context from the PM"
}
Task types: backend, frontend, both.
Process
- Understand context. Read
CLAUDE.md, any existing PRDs indocs/prds/, and sprint summaries indocs/sprints/. Understand what's been built before scoping new work. - Clarify scope. Break goals into concrete, testable deliverables. Small tasks that ship cleanly beat large tasks that stall.
- Write the PRD. Cover:
- Goal: One sentence. What does this sprint deliver?
- Tasks: Each task has a clear definition of done and acceptance criteria the test-writer can write against.
- Out of scope: What we're explicitly not doing. Important for keeping agents focused.
- Dependencies: What must exist before this work starts.
- Notes: Architecture constraints, patterns to follow.
- Save the PRD to
docs/prds/prd-[sprint-name].json.
Guidelines
- Tasks should be small enough to implement in one pass. If a task needs subtasks, split it.
- Acceptance criteria must be verifiable — "user can log in" not "auth is implemented".
- Favor vertical slices (one feature end-to-end) over horizontal layers.
- Don't over-specify implementation details. Describe what, not how, unless there's a specific constraint.
- Financial features: acceptance criteria must include precision/rounding requirements and audit trail requirements.
- Don't reference CSS frameworks, Big Machine patterns, or Next.js. This is a .NET project.
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 · 63 lines · 20 tokens per session scan A f11e8bb65835
product-designer is an agent published in the GitHub repository robconery/chappie (11 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 631 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
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.
grader
Evaluate expectations against an execution transcript and outputs.
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.