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.
npx skills add pe-menezes/pm-chief-of-staff --skill processar-reuniaogit clone --depth 1 https://github.com/pe-menezes/pm-chief-of-staffWrote 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/skills/pe-menezes/pm-chief-of-staff/processar-reuniao)<a href="https://agentmods.dev/skills/pe-menezes/pm-chief-of-staff/processar-reuniao"><img src="https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/processar-reuniao/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/skills/pe-menezes/pm-chief-of-staff/processar-reuniao"><img src="https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/processar-reuniao.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 | $0.00099 | $0.01157 |
| Opus 5 | $0.00049 | $0.00579 |
| Sonnet 5 | $0.00020 | $0.00231 |
| Haiku 4.5 | $0.00010 | $0.00116 |
Grade A, and why
processar-reuniao 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Processar uma reunião
Semente do pm-chief-of-staff. Este arquivo é SEU: peça pro agente mudar o formato da nota ou as regras de propagação e ele edita esta skill na hora.
Escrita: siga o cânone do CLAUDE.md desta pasta. Na ausência dele: sem travessão (use vírgula, parênteses ou dois pontos), frases curtas e densas, 1 linha por item.
O valor não é resumir: é extrair o que muda o estado do sistema (decisão, task, sinal sobre pessoa ou projeto) e colocar cada coisa no lugar onde vai ser encontrada. Uma reunião processada e propagada vale mais que dez transcrições guardadas.
Passo 1: receber o material
Aceitar qualquer forma: transcrição colada, resumo automático (Gemini, Zoom, Granola), foto de quadro, notas cruas digitadas. Perguntar só o que não dá pra inferir: com quem foi e quando (se não estiver no material).
Se existir .claude/skills/_shared/capacidades.md com provider e como chamar na linha transcrição de reunião, oferecer buscar a transcrição por ali em vez de esperar o material colado. Sem o módulo, com a linha pela metade, ou sem resultado na busca, seguir pelo que a pessoa colar.
Transcrição é evidência do que foi DITO, não do que é verdade: afirmação factual relevante que só existe na fala entra na nota marcada como "a validar".
Passo 2: escrever a nota
Arquivo em reunioes/{pessoa-ou-ritual}/YYYY-MM-DD.md, mira de 25 linhas no máximo. O texto bruto (transcrição, resumo automático) NUNCA entra no vault operacional: guardado aqui dentro, vira distrator de toda busca futura. A nota é o destilado + 1 linha de ponteiro pra onde o bruto vive (pasta fria fora do vault, drive, ou a própria origem). A skill não move nem apaga o bruto: a pessoa decide onde ele fica.
---
tipo: nota-de-reuniao
com: {pessoa ou ritual}
data: YYYY-MM-DD
---
**Contexto:** {1 linha}
**Bruto:** {ponteiro em 1 linha pra onde o texto original vive}
## Decisões
- {1 linha por decisão: o que foi decidido + quem decidiu}
## Tasks
- [ ] {ação + dono + prazo se dito} (suas tasks também vão pro diário, ver propagação)
## Sinais
- {o que a conversa revelou sobre pessoa, projeto ou risco, 1 linha cada}
## Não resolvido
- {o que ficou aberto e volta na próxima}
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.
- 12d ago First seen · 70 lines · 99 tokens per session scan A 6af433fd66d9
processar-reuniao is a skill published in the GitHub repository pe-menezes/pm-chief-of-staff (2 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 1,157 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
next
Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".
create-slide-deck
Create beautiful HTML slide decks for product presentations. Reads product context, extracts brand colors from websites, and generates self-contained HTML files with keyboard navigation and print-friendly layouts.
pm-setup
Interactive onboarding wizard that creates the PM-OS knowledge base for your product. Asks questions, fetches company info, and populates all knowledge files.
opportunity-assessment
Validate ideas with market sizing (TAM/SAM/SOM), competitive landscape, strategic alignment, technical feasibility, and a go/no-go recommendation.
competitive-intel
Research a competitor from their URL or name. Fetch website, pricing, features, and news. Generate a battlecard with positioning, strengths, weaknesses, and strategic implications.
experiment-review
Analyze A/B tests and experiments with statistical rigor, assess significance, perform segment analysis, and produce a clear ship/kill/extend recommendation.