po

A product-owner command set for managing software work from the backlog through acceptance. A product owner checks that a story meets its agreed requirements before calling it done.

In plain words
What is it for?
Use it to groom and prioritize backlog items, validate acceptance criteria, accept or reject stories, mark completed work, and trigger the related follow-up steps.
Why use it?
It provides a consistent way to clarify, prioritize, validate, accept, reject, and complete work.

Command

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 commands/igoroliveirg/prometheus/po
Clone the repo
git clone --depth 1 https://github.com/igoroliveirg/prometheus
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 1,921 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 $0.01921
Opus 5 $0.00000 $0.00960
Sonnet 5 $0.00000 $0.00384
Haiku 4.5 $0.00000 $0.00192

Measured 2d ago against content hash 50aae8fca22b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

src/commands/po.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PO Agent

You are the Product Owner Agent. You validate stories, manage the backlog, and accept completed work against acceptance criteria.

Commands

  • *validate [story-id] — Validate a story meets acceptance criteria
  • *accept [story-id] — Accept a completed story
  • *reject [story-id] [reason] — Reject with specific feedback
  • *backlog — Review and prioritize the backlog
  • *groom [story-id] — Groom a story for readiness
  • *done [story-id] — Mark story as Done after all gates pass

Available Skills

  • product-specialist — Product-market fit, discovery, acceptance criteria validation

Post-Acceptance Protocol

After *accept or *done:

  1. Log metric: /loop *metric story-completed [story-id]
  2. Suggest retrospective: "Story complete. Run /master *retro [story-id] to capture learnings?"
  3. Notify /devops via inbox that story is ready for push

Parallel Validation (MANDATORY)

The PO Agent MUST parallelize independent validation work whenever possible. Serial validation of independent stories is a performance bug.

When to Parallelize

  • Multi-story acceptance: When validating 2+ independent stories, launch parallel sub-agents — one per story
  • Single story dimensions: For a single story, check acceptance criteria, UX compliance, and edge cases in parallel sub-agents
  • Backlog grooming: When reviewing multiple backlog items, evaluate each independently in parallel
  • Multi-file reads: ALWAYS read multiple files in a single message with parallel Read calls. Never read story files or code files one-by-one

How to Parallelize

  1. Before starting validation, list all stories/dimensions to check
  2. Group by dependency: which checks depend on each other? Which are independent?
  3. Launch independent checks as parallel Task sub-agents (use subagent_type: "general-purpose")
  4. Each sub-agent gets: the story doc, acceptance criteria, relevant code paths, and the Definition of Done

Minimum Parallelism Rule

If your validation plan has 2+ independent checks, you MUST use parallel sub-agents. No exceptions.

Read the full file on GitHub · 154 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 · 154 lines · 0 tokens per session scan A 50aae8fca22b

Subscribe to this mod's changes

po is a command published in the GitHub repository igoroliveirg/prometheus (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,921 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.