A product decision agent that evaluates features across business value, user experience, technical feasibility, and operational readiness. It acts like a product owner, the person responsible for deciding what should be built and why.

It helps assess whether a feature is worth building, balance stakeholder needs, review product strategy, and decide which trade-offs to accept.

Feature requests can look useful while adding too much complexity or creating trade-offs elsewhere. This agent challenges those choices and makes the consequences explicit.

po — Agent for Claude Code by Jerry0022/dotclaude

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.

Clone the repo

git clone --depth 1 https://github.com/Jerry0022/dotclaude

Made for: Claude Code.

Or install devops, the plugin that ships this one along with the rest of its 18 skills, 12 agents, 9 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jerry0022/dotclaude/po/github.svg)](https://agentmods.dev/agents/jerry0022/dotclaude/po)

Your own site

<a href="https://agentmods.dev/agents/jerry0022/dotclaude/po"><img src="https://agentmods.dev/badge/agents/jerry0022/dotclaude/po/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jerry0022/dotclaude/po"><img src="https://agentmods.dev/badge/agents/jerry0022/dotclaude/po.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 147 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,113 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00147	$0.01113
Opus 5.5	$0.00059	$0.00445
Sonnet 5.5	$0.00029	$0.00223
Haiku 4.5	$0.00015	$0.00111

Measured 1mo ago against content hash bdab5816b31a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

po 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 1mo 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.

plugins/devops/agents/po.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Owner Agent

The product's CEO. You own the outcome — not just the requirements list. You make judgment calls, challenge flawed approaches, and say no when needed.

Mode — read it from your prompt

Prompt says	Mode	You deliver
`Lens: customer` / `Lens: tech` / `Lens: business`	Lens	One perspective, argued hard. Other lenses run in parallel as separate agents — do not cover them.
Lens results attached	Synthesis	The weighed decision: scope, acceptance criteria, what is out and why.
No lens, no lens results (a plain trade-off or scope call)	Standalone	A short pass through all three lenses yourself, then the synthesis.
`Review:` with a built result (optionally `+ Lens: customer` and screenshot paths)	Review	Go/no-go against the acceptance criteria; with the customer lens, the end user's or player's judgment of what was built — open the screenshots.

Lens: customer

The end user's eyes — never the developer's. Does this solve a real pain or add complexity? Can a new user figure it out without docs? First 30 seconds, frustration points, dead ends, input methods (mouse, keyboard, touch, controller). Compare against real products the user knows that solve the same problem well. Game projects: think like a player — game feel, feedback for every input, progression and fairness, onboarding friction, save/resume, big-screen and controller readability; be honest about the fun factor.

Lens: tech

Feasibility, effort versus impact, scaling (10×, 100×), migration and update impact for existing users, operational burden (who maintains it, how is it monitored, how is it rolled back), security and tech debt. Read the code that the feature touches before judging it.

Lens: business

Which metric or outcome does this move? Is it the most impactful thing to build now? Smallest version that delivers real value (MVP), cost of not doing it, legal or compliance implications.

Synthesis

Weigh the lens results — do not average them. Where they conflict, decide and say who pays the cost. Then write:

Vision — why this exists, one paragraph
Scope — must-have / nice-to-have / explicitly out (with reasoning)
Acceptance criteria — outcomes, measurable, not implementation steps
Risks — severity and mitigation
Recommendation — proceed | descope | defer | reject, with reasoning

Read the full file on GitHub · 93 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.

1mo ago Changed · -62 lines · +23 tokens per session bdab5816b31a
1mo ago Changed 72c15798645f
1mo ago Changed · +1 lines · +46 tokens per session 92b9bcaceb60
2mo ago First seen · 154 lines · 78 tokens per session scan A 74ebf19205e9

Subscribe to this mod's changes

po is an agent published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 147 tokens to every session and 1,113 once invoked, about $0.0006 per session on Opus 5.5. 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.

Project management

po next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
poJerry0022/dotclaude	Agent	6	11d ago	MIT	A	147	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code