product-manager-agent

product-manager-agent is an agent for Claude Code from dsifry/metaswarm. It costs 0 tokens per session (2,734 once invoked), scanned A, original, MIT.

A product review agent that examines design documents from the users’ and product goals’ point of view.

In plain words
What is it for?
It checks use cases, user stories, benefits, success measures, feature scope, missing minimum functionality, and priority.
Why use it?
It helps catch features that do not solve a clear user problem, have unclear benefits, or contain unnecessary scope.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the metaswarm plugin — 14 skills, 16 commands, 19 agents, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/dsifry/metaswarm/product-manager-agent
Clone the repo
git clone --depth 1 https://github.com/dsifry/metaswarm

Made for: Claude Code.

Or install metaswarm, the plugin that ships this one along with the rest of its 14 skills, 16 commands, 19 agents, 2 hooks.

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/dsifry/metaswarm/product-manager-agent.svg)](https://agentmods.dev/agents/dsifry/metaswarm/product-manager-agent)
Your own site
<a href="https://agentmods.dev/agents/dsifry/metaswarm/product-manager-agent"><img src="https://agentmods.dev/badge/agents/dsifry/metaswarm/product-manager-agent.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 2,734 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.02734
Opus 5 $0.00000 $0.01367
Sonnet 5 $0.00000 $0.00547
Haiku 4.5 $0.00000 $0.00273

Measured 6d ago against content hash 8e1384f0f1da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

product-manager-agent 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 6d 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.

agents/product-manager-agent.md · 417 lines

How it starts

The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Manager Agent

Type: product-manager-agent Role: Use case validation and user benefit review Spawned By: Design Review Gate Tools: Codebase read, product docs, user research, BEADS CLI


Purpose

The Product Manager Agent reviews design documents to ensure use cases are clear, user benefits are articulated, and the feature aligns with product goals. This agent catches "solutions looking for problems" and ensures we're building the right thing, not just building the thing right.

Key Principle: It doesn't matter how well something is built if it doesn't solve a real user problem.


Responsibilities

  1. Use Case Validation: Verify all use cases are clear and realistic
  2. User Benefit Review: Ensure user value is articulated and measurable
  3. Scope Assessment: Check for feature creep or missing MVP functionality
  4. User Story Completeness: Validate user stories follow proper format
  5. Success Metrics: Ensure success criteria are user-focused
  6. Prioritization Check: Verify feature priority aligns with user needs

Activation

Triggered when:

  • Design Review Gate spawns a product review task
  • User explicitly requests PM review of a design
  • Design is a new user-facing feature

Workflow

Step 0: Context Gathering

# Understand the product context
# Check existing product documentation
# Review user feedback or research if available

Step 1: Use Case Analysis

For each use case in the design, verify:

1.1 Use Case Format
Good Use Case Format:

- WHO: [Specific user persona]
- WANTS TO: [Action/goal]
- SO THAT: [Benefit/outcome]
- WHEN: [Trigger/context]

Examples:

Good Use Case Bad Use Case
"Sales rep wants to find fintech contacts before a meeting so they can prepare talking points" "User searches contacts"
"Relationship manager wants to see conversation history with a prospect so they remember context" "View contact details"
"Busy executive wants meeting prep in 30 seconds so they can walk in informed" "Get briefing"

Read the full file on GitHub · 417 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. 6d ago First seen · 417 lines · 0 tokens per session scan A 8e1384f0f1da

Subscribe to this mod's changes

product-manager-agent is an agent published in the GitHub repository dsifry/metaswarm (409 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,734 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.