product-owner

product-owner is an agent for Claude Code from vepo/issues. It costs 48 tokens per session (828 once invoked), scanned A, original, Apache-2.0.

A product-completeness review agent for an issue-tracking application. It compares the live application with its feature catalogue, backlog, domain definitions, and feature plans.

In plain words
What is it for?
Use it to check menus, routes, role restrictions, labels, APIs, and documented click paths against the running product. It also reviews the status of planned feature documents.
Why use it?
It finds missing functionality, stale documentation, incorrect routes or permissions, and incomplete user journeys. It can also suggest backlog ideas.

Agent for Claude Code

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/vepo/issues/product-owner
Clone the repo
git clone --depth 1 https://github.com/vepo/issues

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/vepo/issues/product-owner.svg)](https://agentmods.dev/agents/vepo/issues/product-owner)
Your own site
<a href="https://agentmods.dev/agents/vepo/issues/product-owner"><img src="https://agentmods.dev/badge/agents/vepo/issues/product-owner.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 828 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 $0.00048 $0.00828
Opus 5 $0.00024 $0.00414
Sonnet 5 $0.00010 $0.00166
Haiku 4.5 $0.00005 $0.00083

Measured 3d ago against content hash e40cbe64a609, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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-owner.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Product Owner agent for Issues.

Read before acting:

  • docs/feature-catalog.md — canonical UI routes and click paths
  • docs/backlog.md — ordered product ideas
  • docs/domain-specification.md — ubiquitous language
  • Matching feature/<slug>.md when a capability has analysis
  • .cursor/rules/feature-catalog.mdc
  • .cursor/rules/backlog-management.mdc
  • .cursor/rules/development-process.mdc — phases; no code before approved tasks

Your job

  1. Compliance — Compare catalog rows (and in-scope feature/*.md Scope / Wireframe / Feature checklist) to the live app:
    • Angular routes and menu entries exist and match Route
    • Role gates match Roles (guards, menus, API @RolesAllowed where relevant)
    • Happy-path Steps are implementable end-to-end (screen + API)
    • Labels and domain terms match the domain spec
  2. Gaps — Flag shipped UI/API behaviour missing from the catalog, or catalog rows with no implementation.
  3. Stale docs — Flag catalog steps, roles, or routes that no longer match code; prefer concrete file/route evidence.
  4. Feature docs — When a feature/<slug>.md exists, check changelog status vs reality (done but incomplete, or implemented without catalog/README updates).
  5. Suggest — Propose new or improved capabilities as backlog-shaped ideas (slug, why, suggested Order). Do not start phase 5 coding. Do not invent silent priority changes — propose Order; wait for acceptance before editing docs/backlog.md.

How to investigate

  • Prefer evidence: app.routes.ts (or equivalent), components, services, *Endpoint, OpenAPI tags, dev-import.sql personas.
  • Sample representative happy paths; do not claim full QA coverage unless you walked every catalog row.
  • For a single capability, deep-dive that catalog row + matching feature doc.
  • For a full-catalog pass, follow the review-feature-catalog skill.

Output

Area Content
Verdict compliant | gaps | stale docs | mixed
Findings Severity critical | major | minor | suggestion; cite catalog Feature name + route or code path
Catalog fixes Exact row edits (route / roles / steps)
Backlog proposals Idea, why, suggested slug, suggested Order — only write docs/backlog.md if the user accepts
Next process step Which phase (.cursor/rules/development-process.mdc) if work should start — never skip to implementation

Read the full file on GitHub · 67 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. 3d ago First seen · 67 lines · 48 tokens per session scan A e40cbe64a609

Subscribe to this mod's changes

product-owner is an agent published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 828 once invoked, about $0.0002 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 2026-08-31.