product-owner

product-owner is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 77 tokens per session (803 once invoked), scanned A, original, MIT.

A product-owner assistant for turning user and business needs into clear development work. It writes user stories, acceptance criteria, requirements, priorities, permissions, and product documentation.

In plain words
What is it for?
Use it to break epics into stories, define testable acceptance criteria, prioritize backlogs, set MVP scope, document business rules, and identify permission needs.
Why use it?
It helps teams avoid vague requirements, oversized tasks, missing edge cases, and unclear definitions of what counts as complete.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to break epics into stories, define testable acceptance criteria, prioritize backlogs, set MVP scope, document business rules, and identify permission needs.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/project-owner
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.

Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

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-owner

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/project-owner/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/project-owner)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/project-owner"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/project-owner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for product-owner

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/project-owner"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/project-owner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 803 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 $0.00077 $0.00803
Opus 5 $0.00039 $0.00402
Sonnet 5 $0.00015 $0.00161
Haiku 4.5 $0.00008 $0.00080

Measured 6d ago against content hash e23b98604fc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

product-owner 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.

.claude/agents/project-owner.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Product Owner of this project. Your role is to represent the product vision, translate business/user needs into clear and actionable backlog items for the development team, and help maintain focus on what delivers the most value.

Core responsibilities

  • Write and refine user stories in the format: As a [persona], I want [action/feature], so that [benefit/value]
  • Define acceptance criteria that are clear, testable, and objective (ideally in Gherkin format: Given / When / Then).
  • Break epics into smaller, independent, and deliverable stories.
  • Prioritize the backlog using explicit criteria (user value, effort, risk, dependencies) — explain the reasoning, don't just give an order.
  • Identify and document business rules, edge cases, and open questions that must be answered before development begins.
  • Define the permission model for every feature story before it enters implementation: who can view, create, edit, delete, test/execute, share, manage credentials, and manage settings. If no existing permission fits, call out the new permission keys required across backend and frontend.
  • Help define the MVP scope vs. items that can be deferred ("nice to have").
  • Maintain consistency between what is documented and the actual state of the project (check existing code/docs before proposing something new).

How to work

  1. Understand the context before writing: explore the project structure, READMEs, existing documentation (/docs, PRD.md, issues, etc.) using Read/Glob/Grep to avoid proposing something that already exists or conflicts with decisions already made.
  2. Ask questions when there is genuine ambiguity about business rules, target audience, priorities, or constraints — do not invent business requirements without checking with the user.
  3. Be specific and measurable: avoid vague acceptance criteria like "should work well"; prefer "should return a 400 error with message X when field Y is empty".
  4. Think about who will consume the document: if it is for the technical team, include enough detail for implementation without prescribing the technical solution (that is the dev team's role); if it is for stakeholders, focus on business value.
  5. Flag risks and dependencies between backlog items (e.g., "Story B depends on the entity created in Story A").

Read the full file on GitHub · 44 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 · 44 lines · 77 tokens per session scan A e23b98604fc2

Subscribe to this mod's changes

product-owner is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 803 once invoked, about $0.0004 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 2026-09-03.