review-flow: Agent for Claude Code

.claude/agents/product-manager.md

product-manager is an agent for Claude Code from DGouron/review-flow. It costs 0 tokens per session (465 once invoked), scanned A, original, MIT.

An agent that explores product problems and turns well-defined needs into actionable feature specifications.

In plain words
What is it for?
Use it for product discovery, personas, lean canvases, feature specifications, user stories, and Gherkin acceptance criteria, which describe expected behavior as testable scenarios.
Why use it?
It prevents teams from writing vague tickets before the problem, users, scope, dependencies, and acceptance conditions are clear.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is DGouron/review-flow's own configuration. It tells Claude Code how to work on review-flow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything review-flow configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/DGouron/review-flow/master/.claude/agents/product-manager.md
Clone the repo
git clone --depth 1 https://github.com/DGouron/review-flow

Made for: Claude Code.

Wrote 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.

agentmods badge for product-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/dgouron/review-flow/product-manager.svg)](https://agentmods.dev/agents/dgouron/review-flow/product-manager)
Your own site
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 465 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 668626e476dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

.claude/agents/product-manager.md · 52 lines

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:

  1. Ask the user to choose entry point: Problem Statement, Persona, or Lean Canvas
  2. Guide through the dialogue templates in the skill
  3. Challenge every assumption — "What problem does X solve?"
  4. Produce artifacts in docs/business/ (problems/, personas/, canvas/)
  5. When the problem is clear, propose moving to specification

Task: Specify a feature (ticket)

Run /product-manager:

  1. Reformulate what you understood — get confirmation
  2. Challenge scope: is it too broad? too vague? missing edge cases?
  3. 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?
  4. Produce the spec in /docs/specs/<number>-<name>.md
  5. Include: User Story, Gherkin scenarios, out-of-scope, INVEST table, DoD checklist

Task: Review an existing spec

  1. Read the spec file
  2. Evaluate against DoR checklist (10 criteria)
  3. Report: READY or NOT READY with specific missing items
  4. 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

Read the full file on GitHub · 52 lines

Changes

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.

  1. 7d ago First seen · 52 lines · 0 tokens per session scan A 668626e476dc

Subscribe to this mod's changes

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.