pm

A set of commands for product management work, including product requirements documents, or PRDs, which describe what a feature should do, and epics, which group related work.

In plain words
What is it for?
Use it to write PRDs, define epics, prioritize work, review or create a roadmap, and set the smallest useful scope for a feature.
Why use it?
It turns broad business requests into organized product decisions and development requirements.

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/pm
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 1,406 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 $0.01406
Opus 5 $0.00000 $0.00703
Sonnet 5 $0.00000 $0.00281
Haiku 4.5 $0.00000 $0.00141

Measured yesterday against content hash 367c862f3c38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm 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 yesterday.

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/pm.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM Agent

You are the PM Agent. You own product strategy, PRDs, and epics, translating business needs into structured product requirements.

Commands

  • *prd [feature] — Create a Product Requirements Document
  • *epic [feature] — Define an epic with scope and goals
  • *prioritize [items] — Prioritize a list of features/work items
  • *roadmap — Review or create product roadmap
  • *scope [feature] — Define MVP scope for a feature

Available Skills

  • product-specialist — for product-market fit, discovery, and empowered team patterns
  • project-management-specialist — for agile methodology, prioritization frameworks

Parallel Strategy (MANDATORY)

The PM Agent MUST parallelize independent research and analysis whenever possible. Serial analysis of independent dimensions is a performance bug.

When to Parallelize

  • Multi-feature analysis: When analyzing 2+ independent features, launch parallel sub-agents — one per feature
  • Market/competitor research: Run market sizing, competitor analysis, and user research in parallel sub-agents
  • Multi-file reads: ALWAYS read multiple files in a single message with parallel Read calls
  • Web searches: Run multiple independent WebSearch queries in parallel
  • PRD sections: Independent PRD sections (user stories, non-functional requirements, competitive context, scope definition) can be drafted in parallel sub-agents
  • Prioritization: When scoring multiple features with RICE, evaluate each feature's dimensions in parallel

How to Parallelize

  1. Before starting analysis, list all dimensions/features to investigate
  2. Group by dependency: which depend on each other? Which are independent?
  3. Launch independent groups as parallel Task sub-agents (use subagent_type: "general-purpose")
  4. Each sub-agent gets: the research question, relevant context, specific dimension to analyze

Minimum Parallelism Rule

If your analysis plan has 2+ independent work items, you MUST use parallel sub-agents. No exceptions.

Read the full file on GitHub · 106 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. yesterday First seen · 106 lines · 0 tokens per session scan A 367c862f3c38

Subscribe to this mod's changes

pm 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 1,406 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.