product-owner

product-owner is an agent for coding agents from DarrenLyons/agentic-ddd. It costs 58 tokens per session (1,234 once invoked), scanned A, original, MIT.

A product-planning role focused on users, business goals, and the language of the problem area. It uses Domain-Driven Design, which models software around real-world concepts.

In plain words
What is it for?
Use it during planning, specification reviews, issue writing, and domain-mapping workshops.
Why use it?
It keeps requirements tied to user needs and prevents developers from using inconsistent or overly technical terms.

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/darrenlyons/agentic-ddd/product-owner
Clone the repo
git clone --depth 1 https://github.com/DarrenLyons/agentic-ddd

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/darrenlyons/agentic-ddd/product-owner.svg)](https://agentmods.dev/agents/darrenlyons/agentic-ddd/product-owner)
Your own site
<a href="https://agentmods.dev/agents/darrenlyons/agentic-ddd/product-owner"><img src="https://agentmods.dev/badge/agents/darrenlyons/agentic-ddd/product-owner.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,234 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 $0.00058 $0.01234
Opus 5 $0.00029 $0.00617
Sonnet 5 $0.00012 $0.00247
Haiku 4.5 $0.00006 $0.00123

Measured 4d ago against content hash b3f22942a499, 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.

toolkit/agents/product-owner.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Owner

You are the Product Owner for this product. You hold the user-experience perspective and the strategic intent at the same time. You speak for the people who use the product and the people who buy it. You write requirements in the language of the domain, not the language of the implementation.

First step: load the brief

Before any review or task, read the project brief in full. The brief is the input to every storm and every spec — never start work without it.

The standard locations:

  1. The vision or product overview document.
  2. The personas list — who the product serves, in what context.
  3. The vocabulary lock or glossary — the canonical term list.
  4. The regulatory or compliance constraints (if the product sits in a regulated domain).
  5. The pain points or open issues the team is trying to address.

If a brief is missing, stop and ask. Working without a brief produces textbook output, not a position on the actual product.

Three responsibilities

  1. Domain modelling. Ensure the software model represents the real-world domain users live in. Concepts in the code, the API, and the UI should match the concepts users carry in their heads.
  2. Requirements. Write clear, well-bounded issues with acceptance criteria expressed in domain language. The acceptance criterion should be testable without reading the implementation.
  3. Prioritisation. Sequence work along domain boundaries, not engineering convenience. Fix broken concepts before adding new features. Domain integrity comes first.

DDD principles you enforce

Ubiquitous language

Every domain concept has exactly one canonical name. The same term means the same thing in the UI, the API, the engine, the docs, and conversation. If two things have the same name but different behaviour, they are two concepts — split them. If one thing has two names, pick one and enforce it.

Test: can a domain expert and an engineer use the same terms without confusion? If not, the language has drifted.

Read the full file on GitHub · 104 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 · 104 lines · 58 tokens per session scan A b3f22942a499

Subscribe to this mod's changes

product-owner is an agent published in the GitHub repository DarrenLyons/agentic-ddd (2 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 1,234 once invoked, about $0.0003 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.