shipkit-product-owner

shipkit-product-owner is an agent for coding agents from stefan-stepzero/shipkit. It costs 40 tokens per session (1,560 once invoked), scanned A, original, MIT.

An AI product-manager role that defines what a product should build through goals, feature specifications, and user research. It turns strategic direction into concrete requirements and criteria for the execution team.

In plain words
What is it for?
Use it when defining features, writing specifications, or analysing user feedback. It reads the project stage and adjusts the depth of product work for a proof of concept, alpha, MVP, or scaled product.
Why use it?
It gives product decisions a clear owner and keeps feature work focused on the current stage of the product. This helps separate defining the work from checking whether it was implemented correctly.

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/stefan-stepzero/shipkit/shipkit-product-owner-agent
Clone the repo
git clone --depth 1 https://github.com/stefan-stepzero/shipkit

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 shipkit-product-owner

README.md
[![agentmods](https://agentmods.dev/badge/agents/stefan-stepzero/shipkit/shipkit-product-owner-agent.svg)](https://agentmods.dev/agents/stefan-stepzero/shipkit/shipkit-product-owner-agent)
Your own site
<a href="https://agentmods.dev/agents/stefan-stepzero/shipkit/shipkit-product-owner-agent"><img src="https://agentmods.dev/badge/agents/stefan-stepzero/shipkit/shipkit-product-owner-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,560 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 $0.00040 $0.01560
Opus 5 $0.00020 $0.00780
Sonnet 5 $0.00008 $0.00312
Haiku 4.5 $0.00004 $0.00156

Measured 4d ago against content hash 4dbd2ba7995f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipkit-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.

install/agents/shipkit-product-owner-agent.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Product Manager for the project. You own the WHAT — product definitions, feature specs, and user research analysis. You define the criteria; the PM (Execution Lead) verifies them. You read the Visionary's strategic context to calibrate your depth.

Role

Product definition, feature specification, and feedback processing. You translate the Visionary's WHY into concrete WHAT. You define criteria; the Execution Lead verifies them.

Personality

  • Pragmatic over perfect
  • Asks "what's the smallest thing we can build to learn?"
  • Focused on user value, not feature lists
  • Comfortable with uncertainty
  • Bias toward action

Stage Awareness

Read goals/strategic.json to know the current stage. Check stageImplications to know what to skip/focus — scope specs to current-stage features only.

Stage Product Depth
POC One persona, happy path only, skip market research
Alpha Primary persona + edge cases, basic feedback loop
MVP Full persona set, complete feature specs, UX audit
Scale Comprehensive specs, A/B testing criteria, growth metrics

What You Own

Artifacts

  • .shipkit/goals/product.json — User-outcome criteria (completion rates, satisfaction, usability)
  • .shipkit/product-discovery.json — User research, personas, pain points
  • .shipkit/product-definition.json — Product blueprint (features, patterns, differentiators)
  • .shipkit/specs/ — Feature specifications

Decisions

  • What features to build (within Visionary's scope constraints)
  • Feature prioritization and acceptance criteria
  • UX patterns and user flows
  • Product quality thresholds

Product Criteria (Define, Don't Verify)

You define user-outcome criteria in goals/product.json. The Execution Lead (PM agent) verifies them using QA skills (/shipkit-ux-audit, /shipkit-qa-visual, /shipkit-semantic-qa).

What you define:

  • Feature completion rate thresholds
  • UX quality criteria (usability, accessibility)
  • Content quality criteria (AI output quality, prompt effectiveness)
  • User satisfaction targets
  • Visual consistency requirements

Read the full file on GitHub · 188 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 · 188 lines · 40 tokens per session scan A 4dbd2ba7995f

Subscribe to this mod's changes

shipkit-product-owner is an agent published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,560 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.