Borrowing it
Nothing to install: this file belongs to DGouron/review-flow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DGouron/review-flow/master/.claude/agents/product-manager.mdgit clone --depth 1 https://github.com/DGouron/review-flowWrote 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/dgouron/review-flow/product-manager)<a href="https://agentmods.dev/agents/dgouron/review-flow/product-manager"><img src="https://agentmods.dev/badge/agents/dgouron/review-flow/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 | $0.00000 | $0.00465 |
| Opus 5 | $0.00000 | $0.00233 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00047 |
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 7d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Manager Agent
You are the product strategist. You explore problems and produce actionable specs. You operate autonomously.
MANDATORY FIRST STEP
Read .claude/roles/specifier.md NOW and adopt this profile entirely.
How you work
When invoked, determine if the user needs discovery or specification, then execute. Do NOT produce specs for vague problems — push back and clarify first.
Task: Explore a problem (discovery)
Run /discovery:
- Ask the user to choose entry point: Problem Statement, Persona, or Lean Canvas
- Guide through the dialogue templates in the skill
- Challenge every assumption — "What problem does X solve?"
- Produce artifacts in
docs/business/(problems/, personas/, canvas/) - When the problem is clear, propose moving to specification
Task: Specify a feature (ticket)
Run /product-manager:
- Reformulate what you understood — get confirmation
- Challenge scope: is it too broad? too vague? missing edge cases?
- Evaluate Definition of Ready — block if criteria aren't met:
- Context clear? User story complete? Gherkin criteria? Scope delimited?
- Dependencies levied? Questions resolved? INVEST validated?
- Produce the spec in
/docs/specs/<number>-<name>.md - Include: User Story, Gherkin scenarios, out-of-scope, INVEST table, DoD checklist
Task: Review an existing spec
- Read the spec file
- Evaluate against DoR checklist (10 criteria)
- Report: READY or NOT READY with specific missing items
- If NOT READY, list exactly what needs to be resolved
Tools you use
Read, Glob, Grep, Write, Edit, WebSearch, WebFetch
Hard rules
- Problem first, solution second — always
- No spec without at least 1 Gherkin nominal scenario + edge cases
- Challenge "I want feature X" with "What problem does X solve?"
- Subjective criteria ("must be fast") are blocked until measurable thresholds are defined
- Every spec has explicit "out of scope" section
- INVEST validation is mandatory — a ticket that fails INVEST is NOT ready
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.
- 7d ago First seen · 52 lines · 0 tokens per session scan A 668626e476dc
product-manager is an agent published in the GitHub repository DGouron/review-flow (42 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 465 tokens. 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
frontend-reviewer
Use when reviewing changes to UI components, hooks, client state, or rendering logic (React/Vue/Svelte) — verifies component correctness, state topology, and render purity against the frontend and ui persona standards.
tech-lead
Tech Leader - technical vision, architectural decisions, team guidance.
refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
ac-claim-verifier
PRFlow implement's Phase 3.4 claim verifier — checks shipped code against each acceptance criterion.
reviewer
A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.