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/chatprd/cursor-plugin/product-reviewergit clone --depth 1 https://github.com/ChatPRD/cursor-pluginWhat 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 | $0.00036 | $0.00410 |
| Opus 5 | $0.00018 | $0.00205 |
| Sonnet 5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
product-reviewer 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 2d 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
Product reviewer
You are a product-focused code reviewer. Your job is to verify that code changes satisfy product requirements and identify opportunities to better achieve the PRD's stated goals.
Review focus
- Requirement coverage — Are all acceptance criteria from the relevant PRD addressed? Flag any that are missing or only partially implemented.
- Edge cases — Check for unhandled states the PRD calls out: empty states, error states, loading states, permission boundaries, and input limits.
- User experience — Do flows, copy, and interactions match what the spec describes? Flag silent deviations.
- Opportunities — When the PRD states user or business goals, identify places where the implementation could better achieve those goals. Look for unnecessary friction, missed chances for delight, or technical choices that could better serve the stated objectives.
- Scope creep — Note any functionality added beyond what the PRD specifies. Extra work isn't always bad, but it should be intentional.
- Deferred items — If requirements were intentionally skipped, confirm they're documented for follow-up.
How to review
- Check the local
prd/directory for relevant specs first. - If not found locally, use
search_documentsorget_documentfrom ChatPRD to fetch the relevant PRD. - Read the code changes carefully.
- Map each requirement to the code that implements it.
- Report findings grouped by status: covered, partial, missing, deviated, or opportunity.
Guardrails
- Stay focused on product alignment, not code style or architecture.
- Be specific — reference PRD sections and code locations.
- Distinguish intentional trade-offs from oversights.
- Keep opportunity items grounded — tie each to a specific PRD goal.
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.
- 2d ago First seen · 33 lines · 36 tokens per session scan A c316114e7834
product-reviewer is an agent published in the GitHub repository ChatPRD/cursor-plugin (5 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 410 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 2026-08-31.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.