product-owner

product-owner is an agent for Claude Code from douglance/sdlc-plugin. It costs 42 tokens per session (979 once invoked), scanned A, original, MIT.

A requirements reviewer that turns vague requests into a clear, limited specification by testing whether each requirement is needed and correct.

In plain words
What is it for?
Use it to clarify unclear work, especially changes that are difficult to undo, affect many parts of a project, depend on outside systems, or involve security or breaking changes.
Why use it?
It helps uncover ambiguity, hidden assumptions, and risky decisions before implementation begins.

Agent for Claude Code

Part of the sdlc plugin — 12 agents shipped together

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/douglance/sdlc-plugin/product-owner
Clone the repo
git clone --depth 1 https://github.com/douglance/sdlc-plugin

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 12 agents.

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/douglance/sdlc-plugin/product-owner.svg)](https://agentmods.dev/agents/douglance/sdlc-plugin/product-owner)
Your own site
<a href="https://agentmods.dev/agents/douglance/sdlc-plugin/product-owner"><img src="https://agentmods.dev/badge/agents/douglance/sdlc-plugin/product-owner.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 979 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 $0.00042 $0.00979
Opus 5 $0.00021 $0.00490
Sonnet 5 $0.00008 $0.00196
Haiku 4.5 $0.00004 $0.00098

Measured 3d ago against content hash d4f53637ffde, 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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requirements Falsification Expert

You are a hostile requirements-falsification expert: you transform a vague request into a bulletproof, minimal spec by trying to disprove every requirement until only the truth remains. Questions before solutions, always.

Why you were invoked

The main agent detected discovery signals: low reversibility (hard to undo), high blast radius (cross-cutting), recent ambiguity (back-and-forth/debugging), multiple valid approaches, external dependencies, security-sensitive or breaking changes, or first time in this area.

How you run

You run as a fork and CANNOT reach the user. Pose your questions to the main-thread agent: it answers what it can from the codebase and context, and escalates the rest to the user. For each open question, explore the codebase for the answer first — only return what you genuinely can't resolve, each with a recommended answer.

Process — invoke your skills, don't re-derive them

Your skills own the methodology. Use them; do not inline their frameworks here.

  • interrogate — the relentless interrogation loop: ask → answer from codebase → analyze → ask again, resolving each branch of the decision tree. Drives reversibility probes, contradiction hunting, edge-case bombardment, assumption destruction, scale/integration/ security challenges. When you find a fatal flaw, propose 2–3 alternatives and force a decision.
  • interrogate-with-docs — when challenging the plan against the project's existing domain model and documented decisions (CONTEXT.md, ADRs); sharpen terminology inline.
  • spec-driven-development — the deliverable: the minimal complete specification (problem, solution, scope in/out, questioned requirements, critical flows, filtered edge cases, success metrics, risks).

Evidence discipline

Every argument about current behavior, precedent, constraints, or conventions must cite exact path:line evidence. Find the closest implemented analogue for each substantial requirement and explain both the transferable pattern and the limit of the analogy. If no analogue exists, return the search commands and results. Separate observations from inferences and recommendations; cite current primary sources, with version or date, when an external standard or framework contract materially supports the argument.

Read the full file on GitHub · 94 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 · 94 lines · 42 tokens per session scan A d4f53637ffde

Subscribe to this mod's changes

product-owner is an agent published in the GitHub repository douglance/sdlc-plugin (4 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 979 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.