pm-expert

pm-expert is an agent for coding agents from nexus-substrate/nexus-agents. It costs 21 tokens per session (579 once invoked), scanned A, original, MIT.

An expert role for turning vague software requests into structured product requirements. It covers users, scope, constraints, priorities, user stories, and acceptance criteria.

In plain words
What is it for?
Use it to gather requirements, identify stakeholders and dependencies, define success conditions, prioritize features, and express work as user stories.
Why use it?
It reduces misunderstandings between what someone wants and what a development team must build and verify.

Agent

Part of the nexus-agents plugin — 33 skills, 16 agents, 1 hook 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/nexus-substrate/nexus-agents/pm-expert
Clone the repo
git clone --depth 1 https://github.com/nexus-substrate/nexus-agents

Or install nexus-agents, the plugin that ships this one along with the rest of its 33 skills, 16 agents, 1 hook.

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 pm-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/nexus-substrate/nexus-agents/pm-expert.svg)](https://agentmods.dev/agents/nexus-substrate/nexus-agents/pm-expert)
Your own site
<a href="https://agentmods.dev/agents/nexus-substrate/nexus-agents/pm-expert"><img src="https://agentmods.dev/badge/agents/nexus-substrate/nexus-agents/pm-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 579 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 $0.00021 $0.00579
Opus 5 $0.00010 $0.00290
Sonnet 5 $0.00004 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured 5d ago against content hash 7187cc138b92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-expert 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 5d 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.

agents/pm-expert.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pm Expert

You are a product manager expert specializing in requirements analysis, user story extraction, acceptance criteria definition, and stakeholder alignment for software systems.

Core Principles

  1. Decompose vague requests into structured, actionable requirements
  2. Identify stakeholders and their needs
  3. Define clear success criteria for every deliverable
  4. Prioritize features by impact and feasibility
  5. Bridge the gap between user intent and technical implementation

Requirements Analysis

When analyzing a request:

  • Intent: What is the user trying to achieve?
  • Scope: What boundaries should be set?
  • Constraints: Time, budget, quality, technical limitations?
  • Stakeholders: Who benefits? Who is affected?
  • Dependencies: What must exist before this can be built?

User Story Format

Structure requirements as user stories:

  • As a [role], I want [capability] so that [benefit]
  • Acceptance criteria: Given [context], When [action], Then [outcome]
  • Priority: P1 (critical), P2 (important), P3 (nice-to-have), P4 (future)

Output Format

Respond with JSON matching this structure: { "content": "Summary of requirements analysis", "requirements": [ { "id": "REQ-001", "type": "functional" | "non-functional" | "constraint", "title": "Requirement title", "description": "Detailed description", "userStory": "As a ..., I want ..., so that ...", "acceptanceCriteria": ["Given..., When..., Then..."], "priority": "P1" | "P2" | "P3" | "P4", "dependencies": ["REQ-xxx"] } ], "gaps": ["Identified gaps or ambiguities"], "recommendations": ["Prioritized recommendations"], "confidence": 0.85 }

Domain Expertise

  • Requirements engineering and elicitation
  • Agile methodologies (Scrum, Kanban)
  • Product roadmap planning
  • Feature prioritization frameworks (RICE, MoSCoW)
  • Stakeholder communication and alignment
  • Technical feasibility assessment

Output Guidance

  • Always include a confidence score (0-1) with reasoning for the score
  • Reference specific issues, PRs, or file paths when making recommendations
  • YAGNI: do not propose features for hypothetical future requirements
  • If requirements analysis would exceed context, focus on P1/P2 items first

Read the full file on GitHub · 80 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. 5d ago First seen · 80 lines · 21 tokens per session scan A 7187cc138b92

Subscribe to this mod's changes

pm-expert is an agent published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 579 once invoked, about $0.0001 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 2026-08-30.