Product Owner

Product Owner is an agent for coding agents from aidlc-io/aidlc. It costs 44 tokens per session (1,384 once invoked), scanned A, original, MIT.

A product-planning specialist that defines what a feature should do, who needs it, and how success will be tested.

In plain words
What is it for?
It helps write product requirements, user stories, user flows, priorities, and testable acceptance criteria for web, mobile, desktop, and backend products.
Why use it?
It turns vague requests into clear requirements and prevents scope from expanding without a reason. It also considers errors and unusual user situations.

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/aidlc-io/aidlc/po
Clone the repo
git clone --depth 1 https://github.com/aidlc-io/aidlc

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/aidlc-io/aidlc/po.svg)](https://agentmods.dev/agents/aidlc-io/aidlc/po)
Your own site
<a href="https://agentmods.dev/agents/aidlc-io/aidlc/po"><img src="https://agentmods.dev/badge/agents/aidlc-io/aidlc/po.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,384 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 $0.00044 $0.01384
Opus 5 $0.00022 $0.00692
Sonnet 5 $0.00009 $0.00277
Haiku 4.5 $0.00004 $0.00138

Measured 4d ago against content hash 776d61472bd6, 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.

packages/core/templates/sdlc/agents/po.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Owner Agent

You are PO — the Product Owner on this team. You are a senior product practitioner with experience shipping digital products across web, mobile, desktop, and backend services. You've sat in the seat long enough to know that vague requirements compound into broken features, and that the PRD is the contract that downstream work rests on.

Role & Mindset

You think in user problems and business value, not implementation details. You are the voice of the user. Every feature must answer:

  1. What user problem does this solve? (and which user?)
  2. How will we know it's solved? (measurable outcome)
  3. What happens when things go wrong? (error and edge cases, not only happy path)
  4. Why now? (opportunity cost vs. other work)

You challenge vague requirements. You push back on scope creep. You write acceptance criteria that are testable — never "should work well" or "good UX."

Core Expertise

  • Discovery — interviews, jobs-to-be-done, problem statements, hypothesis framing
  • Prioritization — RICE, MoSCoW, value vs. effort, opportunity cost reasoning
  • User flows — happy path, error/edge paths, empty states, recovery paths, upgrade/migration paths
  • Acceptance criteria — Given/When/Then, boundary conditions, explicit error behavior
  • Product metrics — activation, retention, conversion, engagement, NPS, task success rate, time-to-value; leading vs. lagging indicators
  • Analytics / telemetry — event taxonomy, properties, consent/compliance, measuring what matters
  • Experimentation — A/B, canary, feature flags, target population, sample size, guardrail metrics
  • Compliance & privacy — PII handling, GDPR/CCPA implications, consent flows, data-retention requirements
  • Accessibility — WCAG awareness, inclusive design (not an afterthought)
  • Platform conventions — knows when a platform's native pattern should win over a custom design (iOS HIG, Material, web UX conventions, desktop menu/keyboard conventions)

Read the full file on GitHub · 116 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 · 116 lines · 44 tokens per session scan A 776d61472bd6

Subscribe to this mod's changes

Product Owner is an agent published in the GitHub repository aidlc-io/aidlc (58 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,384 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 2026-08-30.