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/user-stories)<a href="https://agentmods.dev/commands/lucasgaravelli/pm-skills-claude-code/user-stories"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/user-stories/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/user-stories"><img src="https://agentmods.dev/badge/commands/lucasgaravelli/pm-skills-claude-code/user-stories.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 | $0.03232 |
| Opus 5 | $0.00000 | $0.01616 |
| Sonnet 5 | $0.00000 | $0.00646 |
| Haiku 4.5 | $0.00000 | $0.00323 |
Grade A, and why
user-stories 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.
This is a copy
100% identical to user-stories — 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 — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/user-stories
O que essa skill faz
Gera user stories no formato Mike Cohn com critérios de aceite, aplicando princípio INVEST (Independent, Negotiable, Valuable, Estimable, Small, Testable).
Saída: 5-8 user stories estruturadas prontas para eng estimar e implementar.
Quando usar
- Tem PRD aprovado e precisa quebrar em stories para eng
- Vai criar sprint backlog
- Precisa conversa clara entre PM e dev sobre escopo
Input esperado
Mínimo:
- PRD ou feature description: Contexto completo
- Personas: Quem usa cada feature
- Features principais: O que cada story cobre
Opcional:
- Designs mockups (para contextualizar)
- Métricas (para priorizar)
- Constraints técnicas
Processo
- Quebra de features em stories — Cada feature = 1-2 stories, cada story = 2-5 dias eng
- Formato INVEST — Cada story é independente mas encadeável
- Critérios de aceite — Given/When/Then + casos de edge
- Aceitação de prioridade — Qual story primeira?
- Estimativas — Pede para eng, mas estrutura ajuda
Output
# User Stories: [Feature Name]
## Priorização
| # | Story | Prioridade | Razão |
|---|-------|-----------|-------|
| 1 | [Story 1] | P0 | User não consegue começar sem isso |
| 2 | [Story 2] | P0 | Blocka story 1 |
| 3 | [Story 3] | P1 | Nice-to-have para MVP |
---
## Story 1: [Nome claro do user goal]
**Como um** [Persona]
**Eu quero** [Ação clara]
**Para que** [Resultado/Valor]
### Contexto
[Uma frase sobre por que isso importa. Vindo de descoberta/PRD.]
### Critérios de Aceite
#### Happy path
```gherkin
Given que [pré-condição]
When [ação do usuário]
Then [resultado esperado]
Edge case 1
Given que [variação]
When [ação similar]
Then [resultado diferente]
Edge case 2
Given que [variação 2]
When [ação similar]
Then [resultado diferente]
Notas técnicas
- [Restrição de implementação, se souber]
- [Integração necessária]
- [Performance requirement]
Tamanho estimado
[Solicitar de eng durante refinement — esse formato ajuda a estimar mais rápido]
Dependências
- Precisa de [Story X] ou [Ferramenta Y]
Story 2: [Nome claro do user goal]
Como um [Persona] Eu quero [...] Para que [...]
Contexto
[...]
Critérios de Aceite
Happy path
Given que [...]
When [...]
Then [...]
Edge cases
[...]
Notas técnicas
[...]
Tamanho estimado
[...]
Dependências
[...]
Story 3...N
[Mesmo formato]
Roadmap de Stories (sugestão de sequência)
Sprint 1 (Semana 1)
- Story 1
- Story 2
Sprint 2 (Semana 2)
- Story 3
- Story 4
Sprint 3 (Semana 3+)
- Story 5
- (Se sobrou time) Story 6
Definição de Done
Para uma story ser considerada feita:
- ✅ Critérios de aceite passaram em manual testing
- ✅ Code review aprovado
- ✅ Integrado em staging
- ✅ QA testou happy path + principais edge cases
- ✅ Documentado (se applicable)
- ✅ PM validou em staging
Notas para eng
- Critérios de aceite são contrato: Se algo não está lá, não é responsabilidade de eng
- "Para que" importa: Ajuda eng a tomar decisões criativas dentro do escopo
- Edge cases são reais: Vieram de descoberta ou são padrão do domínio
- Perguntas abertas? Avisar PM agora: Melhor clarificar que descobrir no meio do build
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.
- 10d ago First seen · 539 lines · 0 tokens per session scan A d7384a3e1351
user-stories 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 3,232 tokens. A static security scan graded it A with 0 findings. It is 100% identical to user-stories, 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.