north-star

north-star is a command for Claude Code from lucasgaravelli/pm-skills-claude-code. It costs 0 tokens per session (4,134 once invoked), scanned A, a copy of north-star, MIT.

Um método para escolher a métrica principal que representa o sucesso de um produto e relacioná-la a métricas de entrada. A North Star Metric é esse indicador central; as métricas de entrada mostram as ações que podem influenciá-lo.

In plain words
What is it for?
Serve para classificar o negócio como Attention, Transaction ou Productivity, avaliar candidatas por sete critérios e montar um sistema de métricas. A saída inclui a métrica escolhida, sua justificativa, métricas de entrada e um dashboard recomendado.
Why use it?
Ajuda equipes que acompanham muitos números, ou usam apenas receita, a definir uma direção comum para decisões de produto. Também esclarece como o tipo de negócio muda a escolha das métricas.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Serve para classificar o negócio como Attention, Transaction ou Productivity, avaliar candidatas por sete critérios e montar um sistema de métricas. A saída inclui a métrica escolhida, sua justificativa, métricas de entrada e um dashboard recomendado.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/lucasgaravelli/pm-skills-claude-code/north-star
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.

Clone the repo
git clone --depth 1 https://github.com/lucasgaravelli/pm-skills-claude-code

Made for: Claude Code.

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 north-star

README.md
[![agentmods](https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/north-star/github.svg)](https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/north-star)
Your own site
<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/north-star"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/north-star/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for north-star

Your own site · 80×15
<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/north-star"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/north-star.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 4,134 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00000 $0.04134
Opus 5 $0.00000 $0.02067
Sonnet 5 $0.00000 $0.00827
Haiku 4.5 $0.00000 $0.00413

Measured 10d ago against content hash a886f37b32ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

north-star 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 10d 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.

Origin

This is a copy

100% identical to north-star — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/north-star.md · 438 lines

How it starts

The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/north-star

O que essa skill faz

Define North Star Metric (NSM) + constelacao de Input Metrics para guiar decisoes de produto. Classifica o tipo de negocio (Attention, Transaction, Productivity), avalia candidatos contra 7 criterios, e monta sistema de metricas acionavel.

Saida: NSM escolhida com justificativa, input metrics mapeadas, e dashboard recomendado.


Quando usar

  • Produto nao tem metrica clara de sucesso — cada time mede coisa diferente
  • Stakeholders pedem "qual o numero mais importante?"
  • Revenue e a unica metrica e voce sabe que isso e errado
  • Time precisa de foco — muitas metricas, nenhuma direcao
  • Revisao semestral de metricas (recomendado a cada 6-12 meses)

Input esperado

Minimo:

  • Produto: O que faz, para quem
  • Modelo de negocio: Como ganha dinheiro
  • Estagio: Early, growth, ou scale
  • Metricas atuais: O que mede hoje (mesmo que informal)

Opcional:

  • Revenue e unit economics
  • Engagement data (DAU, WAU, MAU, feature usage)
  • Retention curves
  • Segmentos de usuario
  • OKRs ou goals do trimestre

3 Business Games

Primeiro passo: classificar o tipo de negocio. Cada game tem NSM patterns diferentes.

1. Attention Game

O que importa: Tempo gasto no produto. Mais tempo = mais valor extraido (via ads, engagement, content consumption).

Exemplos: Facebook (DAU), Spotify (Time Listening), YouTube (Watch Time), Netflix (Viewing Hours), TikTok (Time Spent)

NSM patterns: Time spent, sessions/day, content consumed, DAU/MAU ratio

2. Transaction Game

O que importa: Volume e valor de transacoes. Cada transacao = valor entregue ao usuario.

Exemplos: Amazon (Purchase Frequency), Uber (Rides/Week), Airbnb (Nights Booked), Stripe (Payment Volume), DoorDash (Orders/Month)

NSM patterns: Transactions completed, GMV, items sold, bookings

3. Productivity Game

O que importa: Eficiencia — usuario faz mais em menos tempo ou com menos esforco.

Exemplos: Canva (Designs Created), Dropbox (Files Shared), Notion (Pages Created & Shared), Slack (Messages in Channels), Figma (Active Editors)

Read the full file on GitHub · 438 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. 10d ago First seen · 438 lines · 0 tokens per session scan A a886f37b32ba

Subscribe to this mod's changes

north-star is a command published in the GitHub repository lucasgaravelli/pm-skills-claude-code (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,134 tokens. A static security scan graded it A with 0 findings. It is 100% identical to north-star, differing in 0 lines, and is treated as a copy.