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.
git clone --depth 1 https://github.com/lucasgaravelli/pm-skills-claude-codeWrote 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.
[](https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/prioritize)<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/prioritize"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/prioritize/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.
<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/prioritize"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/prioritize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.03309 |
| Opus 5 | $0.00000 | $0.01655 |
| Sonnet 5 | $0.00000 | $0.00662 |
| Haiku 4.5 | $0.00000 | $0.00331 |
Grade A, and why
prioritize 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 9d 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.
This is a copy
100% identical to prioritize — 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.
How it starts
The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prioritize
O que essa skill faz
Aplica RICE scoring (Reach, Impact, Confidence, Effort) + contexto de negócio para priorizar backlog.
Saída: Backlog priorizado com scores, trade-offs explícitos, e recomendação de sequência.
Quando usar
- Tem 5+ features/ideias e não sabe por onde começar
- Stakeholders discordam sobre prioridade
- Precisa explicar por quê escolheu A antes de B
Input esperado
Mínimo:
- Lista de features/ideias: Nomes e breves descrições
- Contexto de negócio: Metas desse trimestre
- Constraints: Team size, deadline
Opcional:
- Dados de impacto (churn reduction, revenue, CAC)
- Dependências técnicas
- Recursos de discovery já feitos
Processo
- RICE scoring — Cada feature scores em 4 dimensões
- Ranking: Divide by effort, ordena por score
- Trade-offs: Se top 3 não cabem, qual deixa?
- Sequência: Ordem de execução considerando dependências
- Roadmap: Qual sprint faz qual feature?
Output
# Priorização: [Nome do Trimestre ou Iniciativa]
## Contexto
### Metas desse trimestre
- [Meta 1]
- [Meta 2]
- [Meta 3]
### Constraints
- Team: [X eng, Y design, Z PM]
- Timeline: [Semanas disponíveis]
- Dependências: [O que bloqueia]
---
## RICE Scoring
### Explicação de cada dimensão
**Reach** (alcance de usuários)
- 100+ = 3 pontos
- 10-100 = 2 pontos
- 1-10 = 1 ponto
**Impact** (tamanho do efeito em cada usuário)
- Massivo (+50% métrica) = 3 pontos
- Grande (+10-50%) = 2 pontos
- Pequeno (+1-10%) = 1 ponto
**Confidence** (quão certo você está dos números)
- Muito certo (dados/descoberta) = 100%
- Confiante (validação informal) = 80%
- Suposição (hipótese não testada) = 50%
**Effort** (semanas de trabalho)
- RICE = (Reach × Impact × Confidence) / Effort
- Maior score = maior prioridade
---
## Features Priorizadas
| # | Feature | Reach | Impact | Conf | Effort | Score | Razão |
|---|---------|-------|--------|------|--------|-------|-------|
| 1 | [Feature A] | 3 | 3 | 100% | 2 | **4.5** | Alinha com meta 1, dados sólidos |
| 2 | [Feature B] | 2 | 2 | 80% | 3 | **1.07** | Nice-to-have, menos urgente |
| 3 | [Feature C] | 3 | 1 | 50% | 5 | **0.3** | Risky, sem validação ainda |
---
## Top 3 Recomendados
### 1. [Feature A] — Score 4.5 ⭐ Recomendado
**Caso de negócio**
- Reach: 200+ usuários (30% da base)
- Impact: +25% engagement (de 60% para 75%)
- Esforço: 2 semanas
- Alinha com: Meta 1 (Aumentar engagement)
**Detalhe**
- Já temos descoberta completa
- Risk baixo (feature similar existe no competitor)
- Quick win 1º
**Se fizer agora**
- Go-live: Semana 2
- Impacto esperado: +X MRR em 30 dias
---
### 2. [Feature B] — Score 1.07 ⭐ Considerar se tempo sobra
**Caso de negócio**
- Reach: 50 usuários (7% da base)
- Impact: +15% NPS (de 35 para 50)
- Esforço: 3 semanas
- Alinha com: Meta 2 (Customer satisfaction)
**Detalhe**
- Valor alto para essas 50 users mas impacto baixo no todo
- Confiança: 80% (validação com 5 clientes)
- Medium risk (requer integração externa)
**Se fizer depois**
- Seria prioridade para Q2
- Mantém cliente quality alta
---
### 3. [Feature C] — Score 0.3 ❌ Defer para Q2
**Caso de negócio**
- Reach: 150+ usuários
- Impact: +5% conversão (de 10% para 15%)
- Esforço: 5 semanas
- Alinha com: Meta 3 (Growth)
**Detalhe**
- HUGE incerteza (hipótese não testada)
- Effort alto = risco
- Recomendação: Validar com experimento ANTES de PRD
**Se não fizer agora**
- Não afeta trimestre
- Ganho tempo para validar melhor no Q2
---
## Trade-offs Explícitos
### Cenário A: Time pode fazer 2 features em paralelo
Semana 1-2: Feature A (1ª eng + design) Semana 1-3: Feature B (2ª eng) Semana 4: Buffer/polish
✅ Vantagem: Máximo impacto, ambas saem no mês
❌ Desvantagem: Team estressado, possível delay
### Cenário B: Time faz 1 feature por vez
Semana 1-2: Feature A → go-live Semana 3-5: Feature B → go-live Semana 6: Buffer
✅ Vantagem: Menos stress, mais qualidade, time pode responder bugs
❌ Desvantagem: Feature B sai mais tarde, possível pierde market window
### Recomendação
**Scenario B** — Feature A é quick win, deixa time com morale boost. Feature B é lower priority assim.
---
## Roadmap recomendado
### Semana 1-2: Feature A (MVP)
- Lançamento: Final da semana 2
- Métrica target: 20% de users ativos
- Go/No-go: Se < 10% de users adoptam, voltar ao drawing board
### Semana 3-5: Feature B (se aprovado)
- Dependência: A saiu + feedback coletado
- Lançamento: Final da semana 5
- Métrica target: 50% de segment satisfaction
### Semana 6: Polish/buffer
- Bugs de A ou B
- Surpresas
---
## O que fazer com Feature C
**Não é "cancela", é "defer + validate"**
1. Semana 1: Desenhar experimento para testar hipótese de C
2. Week 2-3: Rodar experimento com 100 usuários
3. Week 4: Análise — se validado, goes para Q2 roadmap como P0
Dessa forma, Q2 começa com Feature C já validado, sem risco.
---
## Aprovação
- [ ] PM: Priorização alinhada com metas
- [ ] Eng Lead: Estimates realistas
- [ ] Executive: Trade-offs aceitáveis
**Decisão**: [Feature A] vai para próximo sprint
**Data**: ________
**Próxima review**: [2 semanas, ou quando nova ideia aparecer]
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.
- 9d ago First seen · 421 lines · 0 tokens per session scan A 5688afe811b6
prioritize 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 3,309 tokens. A static security scan graded it A with 0 findings. It is 100% identical to prioritize, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.