A product-planning tool that identifies the kinds of people a software project is meant to serve. It creates short user profiles based on the codebase or an interview, including people the project is not intended for.

Use it to create user profiles, describe the jobs those users need to do, and record an anti-persona—the type of user you deliberately choose not to serve.

It helps prevent building for an unclear or overly broad audience. It turns assumptions about users into written guidance for product decisions.

pm-personas — Skill for Claude Code by nmrtn: A product-planning tool that identifies the kinds of people…

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 skills/nmrtn/nanopm/pm-personas

Any agent

npx skills add nmrtn/nanopm --skill pm-personas

Clone the repo

git clone --depth 1 https://github.com/nmrtn/nanopm

Made for: Claude Code.

Or install nanopm, the plugin that ships this one along with the rest of its 26 skills, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nmrtn/nanopm/pm-personas.svg)](https://agentmods.dev/skills/nmrtn/nanopm/pm-personas)

Your own site

<a href="https://agentmods.dev/skills/nmrtn/nanopm/pm-personas"><img src="https://agentmods.dev/badge/skills/nmrtn/nanopm/pm-personas.svg" alt="Measured on agentmods" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,422 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.06422
Opus 5	$0.00035	$0.03211
Sonnet 5	$0.00014	$0.01284
Haiku 4.5	$0.00007	$0.00642

Measured 6d ago against content hash ba016b9b9244, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

pm-personas scanned grade C with 2 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 6d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

{ echo "ERROR: nanopm not installed. Run: curl -fsSL https://raw.githubusercontent.com/nmrtn/nanopm/main/setup | bash"; exit 1; }

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

{ echo "ERROR: nanopm not installed. Run: curl -fsSL https://raw.githubusercontent.com/nmrtn/nanopm/main/setup | bash"; exit 1; }

pm-personas/SKILL.md · 481 lines

How it starts

The opening of the file, as written. The whole thing — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-host portability rules. When invoking AskUserQuestion:

The header field MUST be a short noun phrase (≤ 12 characters). Mistral Vibe rejects longer headers with string_too_long. Pick from: Start, Target, Scope, Audience, Methodology, Feature, Question.

The options list MUST have at least 2 items. Vibe rejects empty/single-option calls. For free-text input, always provide ≥ 2 framing options (e.g. Yes, here's the input / Skip) — never call ask_user_question with options: [].

Preamble (run first)

source ~/.nanopm/lib/nanopm.sh 2>/dev/null || \
  source .nanopm/lib/nanopm.sh 2>/dev/null || \
  { echo "ERROR: nanopm not installed. Run: curl -fsSL https://raw.githubusercontent.com/nmrtn/nanopm/main/setup | bash"; exit 1; }
nanopm_preamble
_PERSONAS_FILE="$(nanopm_wiki_doc_path personas)"

What this skill does

/pm-personas answers one question: who are you actually building for? It produces the wiki Define page .nanopm/wiki/docs/personas.md — 1-3 proto-personas framed around the job-to-be-done, plus one explicit anti-persona (the tempting user you are deliberately NOT serving).

It runs in one of two modes, driven by whether the personas doc already exists. Refine mode — the doc exists: the skill anchors on your previous personas, pulls only the relevant cross-doc context via a retrieval subagent, and asks sharpening questions to update them. Create mode — the doc is missing: if there's a codebase, artifacts, or a public site it reverse-engineers a draft and asks validating questions before writing; if the repo is empty it interviews you from scratch. Either way it confirms with you — it never ships assumptions unchecked.

Personas are an input to the pipeline. The personas doc sharpens /pm-challenge-me ("who for"), /pm-objectives, /pm-strategy, and /pm-prd. Run it early.

Phase 0: Prior context

source ~/.nanopm/lib/nanopm.sh 2>/dev/null || source .nanopm/lib/nanopm.sh 2>/dev/null || true
nanopm_context_read pm-personas
nanopm_context_read pm-personas

Read the full file on GitHub · 481 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.

6d ago First seen · 481 lines · 70 tokens per session scan C ba016b9b9244

Subscribe to this mod's changes

pm-personas is a skill published in the GitHub repository nmrtn/nanopm (48 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 6,422 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

pm-personas