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 felipenalves/InvOS --skill analisar-dadosgit clone --depth 1 https://github.com/felipenalves/InvOSWrote 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/felipenalves/invos/analisar-dados)<a href="https://agentmods.dev/skills/felipenalves/invos/analisar-dados"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/analisar-dados/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/felipenalves/invos/analisar-dados"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/analisar-dados.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 | $0.00072 | $0.00647 |
| Opus 5 | $0.00036 | $0.00324 |
| Sonnet 5 | $0.00014 | $0.00129 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
analisar-dados 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 11d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/analisar-dados — Análise de Arquivo
Dependências
- Contexto do negócio:
_memoria/empresa.md(pra entender o que os dados representam) - Tom de voz:
_memoria/preferencias.md
Workflow
Passo 1 — Entender o contexto
Antes de analisar, perguntar se não estiver claro:
- "O que é esse arquivo? (vendas, anúncios, métricas, respostas de pesquisa...)"
- "Qual é a pergunta principal que você quer responder com esses dados?"
Se o contexto estiver óbvio pelo nome do arquivo ou pelo conteúdo, prossegue sem perguntar.
Passo 2 — Ler o arquivo
Ler o arquivo fornecido. Se for Excel (.xlsx), ler com as ferramentas disponíveis pra extrair o conteúdo das células.
Passo 3 — Análise
Identificar e reportar:
O que está bom:
- Métricas acima da média ou em crescimento
- Padrões positivos nos dados
- Top performers (produtos, campanhas, períodos, etc)
O que preocupa:
- Quedas, anomalias ou tendências negativas
- O que está abaixo do esperado
- Gargalos ou desperdícios visíveis
Comparações:
- Período atual vs período anterior (se houver)
- Top vs bottom performers
- Distribuição entre categorias
Insights não óbvios:
- Correlações interessantes
- Padrões que não aparecem na leitura superficial
Passo 4 — Output
Gerar um resumo executivo em prosa (não só bullet points):
# Análise — [Nome do Arquivo/Relatório]
*[Data da análise]*
## O que esses dados mostram
[2-3 parágrafos com o panorama geral]
## O que está funcionando
[lista com contexto]
## O que merece atenção
[lista com contexto]
## 3 recomendações
1. [ação concreta]
2. [ação concreta]
3. [ação concreta]
## Números-chave
| Métrica | Valor | Contexto |
|---------|-------|---------|
| ... | ... | ... |
Salvar em estudos/analise-[nome]-[data].md ou na pasta mais adequada pro perfil do usuário.
Perguntar se quer exportar o resumo em HTML pra compartilhar ou apresentar.
Regras
- Análise em prosa, não só listas — o usuário deve poder ler e entender sem abrir o arquivo original
- Nunca inventar dados que não estão no arquivo
- Se os dados estiverem incompletos ou com problemas, mencionar antes de analisar
- Tom conforme
_memoria/preferencias.md
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.
- 11d ago First seen · 96 lines · 72 tokens per session scan A 406a9c3856c5
analisar-dados is a skill published in the GitHub repository felipenalves/InvOS (6 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 647 once invoked, about $0.0004 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
hindsight-architect
Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.
create-agent
Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
hindsight-docs
Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.
hindsight-memory
Long-term memory for the agent via Hindsight. Use to recall relevant past context before answering, retain durable facts as you learn them, and reflect over accumulated memory for the "why" behind a decision. Load whenever continuity across sessions matters — the user refers to earlier work, states a lasting…
hindsight-recall
Search long-term memory for relevant context from past coding sessions using Hindsight MCP tools.