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/experiment-design)<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/experiment-design"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/experiment-design/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/experiment-design"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/experiment-design.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 | $0.02304 |
| Opus 5 | $0.00000 | $0.01152 |
| Sonnet 5 | $0.00000 | $0.00461 |
| Haiku 4.5 | $0.00000 | $0.00230 |
Grade A, and why
experiment-design 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 experiment-design — 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/experiment-design
O que essa skill faz
Desenha experimentos Lean para validar hipóteses de produto usando pretotyping (pré-MVP) ou A/B testing (pós-launch). Baseado no framework de Alberto Savoia ("The Right It") e princípios de Lean Experimentation.
Saída: Experiment Spec com hipótese XYZ, método, métricas, timeline e critérios go/no-go.
Quando usar
- Antes de construir: validar se a ideia merece investimento (pretotype)
- Pós-launch: otimizar conversão, retenção ou engajamento (A/B test)
- Quando tem opinião forte mas dados fracos sobre demanda
- Quando stakeholder pede "prova" antes de aprovar investimento
- Quando precisa decidir entre duas abordagens de feature
Input esperado
Mínimo:
- Hipótese: O que você acredita ser verdade sobre o mercado/usuário
- Estágio: Pré-MVP (0→1) ou pós-launch (1→100)
- Contexto: Produto, segmento, situação atual
Opcional:
- Dados existentes (surveys, analytics, feedback)
- Restrições de budget/timeline
- Métricas atuais (baseline para A/B)
- Tamanho da base de usuários
Formato de hipótese XYZ
Toda hipótese deve seguir o formato XYZ de Alberto Savoia:
"Pelo menos X% de Y vai Z"
- X% = porcentagem mínima do mercado-alvo (ex: 10%, 30%)
- Y = mercado-alvo específico (ex: "PMs de startups Series A")
- Z = como vão se engajar (ex: "se cadastrar na waitlist em 48h")
Exemplos de hipótese XYZ
- "Pelo menos 15% dos PMs que visitarem a landing page vão deixar email na waitlist"
- "Pelo menos 5% dos leads do email campaign vão fazer pre-order"
- "Pelo menos 40% dos usuários expostos ao novo onboarding vão completar o setup em 24h"
Princípios fundamentais (Savoia)
1. Skin-in-the-Game
Teste comprometimento REAL — tempo, dinheiro, ação — não apenas interesse declarado.
- RUIM: "Você usaria isso?" (opinião)
- BOM: "Coloque seu email para ser avisado" (ação leve)
- ÓTIMO: "Pague R$10 para garantir acesso antecipado" (comprometimento real)
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 · 274 lines · 0 tokens per session scan A b773c1290779
experiment-design 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 2,304 tokens. A static security scan graded it A with 0 findings. It is 100% identical to experiment-design, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.