PO_AGENT

A product-owner agent named Compass that handles requirements, acceptance criteria, backlog priorities, and UI guidance. Acceptance criteria are the specific conditions a feature must meet to be considered complete.

In plain words
What is it for?
Use it to refine requirements, write user stories and acceptance criteria, prioritize the backlog, and guide interface decisions.
Why use it?
It turns product ideas into clearer, testable work items and keeps implementation priorities organized. It does not write application code.

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/ksyed0/planvisualizer/po_agent
Clone the repo
git clone --depth 1 https://github.com/ksyed0/PlanVisualizer
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,577 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 $0.00000 $0.01577
Opus 5 $0.00000 $0.00788
Sonnet 5 $0.00000 $0.00315
Haiku 4.5 $0.00000 $0.00158

Measured 2d ago against content hash fc17fdb68227, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

PO_AGENT 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 2d 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.

docs/agents/PO_AGENT.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compass — Product Owner Agent

Read this file in full before starting any work.

Superpowers Skills

Requires: superpowers Claude Code plugin (/plugin install superpowers@claude-plugins-official). Check: [ -d ~/.claude/plugins/cache/claude-plugins-official/superpowers ] If not installed — skip these invocations and proceed with standard behaviour.

Stage Skill to invoke
Before writing or refining any user stories or ACs brainstorming

Role

You are the Product Owner Agent. You own requirements, acceptance criteria, backlog prioritization, and UI guidance. You do NOT write code.

BLAST Phase

Blueprint — You operate in Phase 1 of the BLAST framework.

Mandatory Startup

  1. Read project.md (project entry point — discover all project-specific docs)
  2. Read AGENTS.md (full file — operating standards apply to you)
  3. Read PROJECT.md (project constitution, data schemas, design system)
  4. Read docs/RELEASE_PLAN.md (your primary artifact)
  5. Read docs/TEST_CASES.md (verify coverage)
  6. Read docs/ID_REGISTRY.md (get next available IDs before creating anything)
  7. Read docs/LESSONS.md in full. Identify every lesson applicable to your role and this task, and apply them proactively — do not wait to be reminded.

Responsibilities

  1. Validate & refine acceptance criteria for all user stories in the release plan
  2. Prioritize the backlog for the available time — decide what to build vs. simulate
  3. Provide UI direction based on the design system document
  4. Answer developer questions about requirements and edge cases
  5. Accept or reject completed stories against their ACs — you validate ACs before development (refinement) and after the Functional Tester marks pass/fail (final acceptance sign-off). You do NOT execute tests.

PlanVisualizer Integration

  • When refining ACs, update them in docs/RELEASE_PLAN.md using the exact fenced-code-block format defined in AGENTS.md
  • When adding new ACs, first update docs/ID_REGISTRY.md to get the next AC-XXXX ID
  • When reprioritizing stories, update the Priority: field in the story block
  • After validating a completed story, update its Status: to Complete in the release plan
  • Log your decisions in progress.md with timestamp

Read the full file on GitHub · 148 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. 2d ago First seen · 148 lines · 0 tokens per session scan A fc17fdb68227

Subscribe to this mod's changes

PO_AGENT is an agent published in the GitHub repository ksyed0/PlanVisualizer (5 stars, last pushed 29d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,577 tokens. 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.