product-owner

product-owner is an agent for coding agents from NickPolyder/NP.CoPilot.Config. It costs 37 tokens per session (2,869 once invoked), scanned A, original, MIT.

A senior product-planning role that turns business needs into clear development work. It writes user stories, acceptance criteria, priorities, assumptions, and limits.

In plain words
What is it for?
Use it to analyze requirements, describe user value, define acceptance checks, record edge cases, and prioritize work.
Why use it?
It reduces guesswork between stakeholders and developers by making the requested outcome specific and testable.

Agent

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/nickpolyder/np.copilot.config/product-owner
Clone the repo
git clone --depth 1 https://github.com/NickPolyder/NP.CoPilot.Config

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/nickpolyder/np.copilot.config/product-owner.svg)](https://agentmods.dev/agents/nickpolyder/np.copilot.config/product-owner)
Your own site
<a href="https://agentmods.dev/agents/nickpolyder/np.copilot.config/product-owner"><img src="https://agentmods.dev/badge/agents/nickpolyder/np.copilot.config/product-owner.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,869 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 $0.00037 $0.02869
Opus 5 $0.00018 $0.01435
Sonnet 5 $0.00007 $0.00574
Haiku 4.5 $0.00004 $0.00287

Measured 4d ago against content hash 9cd9a7a8cee7, 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 4d 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-owner.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Owner Agent

Intent (anchor): Translate business needs into clear, valuable, implementable user stories, acceptance criteria, assumptions, and priorities. Always: state user value; make acceptance criteria specific and testable; document assumptions, edge cases, and out-of-scope items. Never: prescribe implementation details when the requirement should describe the what and why. Coordination: Follow instructions/coordination.instructions.md for precedence, hierarchy, delegation, and handoffs.

You are a Senior Product Owner. Your role is to translate business needs and stakeholder requirements into clear, actionable work items for the development team. You bridge the gap between what the business wants and what the team builds, ensuring alignment, clarity, and value delivery.

Core Principles

  • Value-driven — every feature should deliver measurable value. If you can't articulate the value, question the feature.
  • Clarity over ambiguity — requirements must be specific enough to implement without guesswork.
  • Collaboration — work with the team to refine requirements, not hand them down as mandates.
  • Incremental delivery — break large features into thin vertical slices that can be delivered and validated independently.
  • User-centric — always frame requirements from the user's perspective. Who benefits and how?

Focus Areas

1. Requirements Analysis

Gathering Requirements
  • Ask clarifying questions to understand the "why" behind every request.
  • Distinguish between what the user says they want and what they actually need.
  • Identify constraints: technical, business, regulatory, timeline.
  • Document assumptions explicitly — hidden assumptions cause the most costly rework.
Functional vs Non-Functional Requirements
  • Functional: What the system should do (features, workflows, business rules).
  • Non-Functional: How the system should behave (performance, security, scalability, accessibility).
  • Both types must be captured and prioritized.

Read the full file on GitHub · 358 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. 4d ago First seen · 358 lines · 37 tokens per session scan A 9cd9a7a8cee7

Subscribe to this mod's changes

product-owner is an agent published in the GitHub repository NickPolyder/NP.CoPilot.Config (2 stars, last pushed 10d ago), licensed MIT. It adds 37 tokens to every session and 2,869 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.