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/hypothesis)<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/hypothesis"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/hypothesis.svg" alt="Measured on agentmods" 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 | $0.03282 |
| Opus 5 | $0.00000 | $0.01641 |
| Sonnet 5 | $0.00000 | $0.00656 |
| Haiku 4.5 | $0.00000 | $0.00328 |
Grade A, and why
hypothesis 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 8d 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 hypothesis — 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hypothesis
O que essa skill faz
Gera uma hipótese testável e estruturada com métricas de sucesso, avaliação de risco em 4 categorias (Value, Usability, Viability, Feasibility) e plano de validação. Transforma intuições vagas em statements falsificáveis com kill criteria.
Saída: Hypothesis card completa — pronta para alinhar o time e desenhar experimento.
Quando usar
- Tem uma ideia de feature e quer validar antes de construir
- Precisa estruturar o pensamento antes de pedir recursos ao time
- Quer definir critérios claros de sucesso e fracasso antes de começar
- Está usando Opportunity Solution Tree e precisa formalizar a hypothesis de uma solução
- Quer evitar o viés de confirmação — definir o que te faria desistir ANTES de testar
Input esperado
Mínimo:
- Ideia/mudança proposta: O que quer fazer ou mudar
- Usuário-alvo: Quem será impactado
- Problema que resolve: Qual dor ou necessidade endereça
Opcional:
- Dados de discovery (entrevistas, analytics)
- Baseline atual da métrica
- Constraints (timeline, budget, capacidade técnica)
- Experimentos anteriores relacionados
- Opportunity Solution Tree (se já existe)
Processo
-
Formular a crença (Belief) — Escrever a hipótese no formato: "Acreditamos que [ação/mudança] para [usuário-alvo] vai [resultado esperado] medido por [métrica] atingindo [target] em [prazo]." A hipótese DEVE ser falsificável — se qualquer resultado confirma, não é hipótese.
-
Especificar o usuário-alvo — Definir segmento específico, não "usuários". Incluir: quem é, qual o contexto, por que esse grupo especificamente. Quanto mais específico, mais útil o teste.
-
Definir resultado esperado — Descrever a mudança de comportamento do usuário (não métrica interna). Ex: "usuários vão completar onboarding" em vez de "vamos reduzir churn". O comportamento causa a métrica, não o contrário.
-
Estabelecer métricas de sucesso — Definir 3 tipos:
- Primary metric: A métrica principal que a hipótese move
- Secondary metric: Métrica complementar que confirma o mecanismo
- Guardrail metric: Métrica que NÃO pode piorar (efeito colateral)
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.
- 8d ago First seen · 321 lines · 0 tokens per session scan A 3642b66b4cf9
hypothesis 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 3,282 tokens. A static security scan graded it A with 0 findings. It is 100% identical to hypothesis, 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.