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/discovery)<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/discovery"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/discovery.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 | $0.01408 |
| Opus 5 | $0.00000 | $0.00704 |
| Sonnet 5 | $0.00000 | $0.00282 |
| Haiku 4.5 | $0.00000 | $0.00141 |
Grade A, and why
discovery 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 discovery — 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/discovery
O que essa skill faz
Estrutura um ciclo completo de discovery transformando um problema vago em hipóteses testáveis e um plano de experimentos.
Saída: Síntese de descoberta com framing, hipóteses validadas, e próximos passos.
Quando usar
- Problema está mal definido ou você tem múltiplas hipóteses
- Precisa validar antes de investir em PRD/spec
- Vai rodar experimentos e precisa de estrutura
Input esperado
Mínimo:
- Problema: Descrição do problema conforme entendido hoje
- Contexto: Tamanho do mercado, usuários afetados, ou constraints
- Restrições: Tempo, budget, dependências técnicas
Opcional:
- Dados existentes (churn, NPS, feedback)
- Competitors ou proxies
- Personas em mente
Processo
- Framing — Reescreve o problema em linguagem de JTBD (Jobs to Be Done)
- Hipóteses — Gera 3-5 hipóteses sobre raiz do problema (não soluções)
- Validação — Estrutura como testar cada hipótese (experimento, tamanho, tempo)
- Roadmap de experimentos — Sequencia dos testes em 2-4 semanas
- Critério de sucesso — Que resultado muda a decisão de produtos
Output
# Síntese de Discovery: [Problema]
## Framing (JTBD)
"Quando [contexto], eu quero [job], para que [outcome]"
## Hipóteses a validar
1. **Hipótese A** [texto]
- Risco: [alto/médio/baixo]
- Tamanho do impacto: [$X, Y users, Z% churn]
2. **Hipótese B** [texto]
- Risco: [...]
- Tamanho do impacto: [...]
3. **Hipótese C** [texto]
- Risco: [...]
- Tamanho do impacto: [...]
## Plano de experimentos (2-4 semanas)
### Semana 1
- **Experimento**: [método] com [amostra]
- **Hipótese testada**: Hipótese A
- **Critério de sucesso**: [métrica] > [threshold]
- **Esforço**: [1-3 dias PM]
### Semana 2
- **Experimento**: [método] com [amostra]
- **Hipótese testada**: Hipótese B
- **Critério de sucesso**: [métrica] > [threshold]
- **Esforço**: [1-3 dias PM]
## Próximos passos
1. Validar hipótese A com [experimento]
2. Se confirmado, design de solução
3. Se refutado, voltar para hipótese C
## Timeline
- Semana 1-2: Experimentos
- Semana 3: Análise e decisão
- Semana 4: Start de PRD ou pivot
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 · 162 lines · 0 tokens per session scan A 85c8b57a7b73
discovery 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 1,408 tokens. A static security scan graded it A with 0 findings. It is 100% identical to discovery, 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.