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.
git clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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/alexmmatos/arthur-mcp/project-owner)<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.
<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>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 | $0.00077 | $0.00803 |
| Opus 5 | $0.00039 | $0.00402 |
| Sonnet 5 | $0.00015 | $0.00161 |
| Haiku 4.5 | $0.00008 | $0.00080 |
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.
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
- Understand the context before writing: explore the project structure, READMEs, existing documentation (
/docs,PRD.md, issues, etc.) usingRead/Glob/Grepto avoid proposing something that already exists or conflicts with decisions already made. - 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.
- 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".
- 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.
- Flag risks and dependencies between backlog items (e.g., "Story B depends on the entity created in Story A").
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.
- 6d ago First seen · 44 lines · 77 tokens per session scan A e23b98604fc2
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.
Other agents, from other repositories
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
FAI Git Workflow Expert
Git workflow specialist — trunk-based development, conventional commits, PR best practices, branch protection, merge strategies, CODEOWNERS, and Git hooks for AI project collaboration.
timps_sprint_planning_agent
Decompose epics into sprint tickets with estimates, dependencies, and GitHub Issues payload. Use the timpssprintplanningagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
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.