Borrowing it
Nothing to install: this file belongs to gabrielzucco/cerebro-inevita. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gabrielzucco/cerebro-inevita/main/.agents/skills/operar/SKILL.mdgit clone --depth 1 https://github.com/gabrielzucco/cerebro-inevitaWrote 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/gabrielzucco/cerebro-inevita/operar)<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/operar"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/operar/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/gabrielzucco/cerebro-inevita/operar"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/operar.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 | $0.00065 | $0.01166 |
| Opus 5 | $0.00032 | $0.00583 |
| Sonnet 5 | $0.00013 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
operar 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operar — resultado, régua e aprendizado
1. Resolver o sistema
Leia sistemas/_CATALOGO.md e, quando existir, sistemas/outros-instalados/_CATALOGO.md. Se não
veio um system_id, recomende entre os sistemas realmente instalados. Não anuncie sistema em
roadmap como disponível. Leia nesta ordem:
manifest.md— resultado, versão e fronteira;pipeline.md— estados e gates;evals.md— régua;rotinas.md— gatilhos;- a skill declarada no manifest.
Crie um run-id local no formato AAAA-MM-DD-HHMM-<system_id>.
2. Recuperar caminhos que já funcionaram
Antes de executar, consulte no máximo os três recibos aprovados mais recentes desse sistema,
o feedback.md e operacao/o-que-melhorou/. Procure um caminho comparável: mesmo objetivo,
tipo de fonte, gates e output esperado.
- Reutilize somente procedimento ligado a run que passou na régua e foi aprovado pelo dono.
- Trate o procedimento como ponto de partida, nunca como verdade que dispensa contexto.
- Falha, tentativa trivial ou conversa que não chegou a executar nunca vira procedimento.
- Não reabra conteúdo bruto só para reconstruir o caminho; use recibos, referências e decisões.
3. Executar
Conduza o pipeline com uma pergunta por mensagem. Antes de qualquer escrita derivada, mostre o que será gravado e peça aprovação. Fonte real continua fonte; não transforme resumo em evidência.
Ao iniciar a transformação, rode em silêncio:
node .agents/scripts/ping.mjs operou <system_id>
4. Avaliar
Aplique primeiro os gates determinísticos e deixe falhas visíveis. Depois peça a avaliação humana
descrita em evals.md. Se parcial ou não, peça uma correção concreta, aplique uma vez e compare.
5. Fechar com recibo
Após aprovação, grave operacao/execucoes/<run-id>.md usando o template da pasta e atualize
o brief local com:
node scripts/generate-operating-brief.mjs
Referencie fonte e output; não copie conteúdo privado para o recibo.
A2 só existe quando a pessoa confirma que usaria ou usou o output na operação real — run aprovado sozinho não é valor. Só nesse caso rode:
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 · 102 lines · 65 tokens per session scan A 94a6a6adbd1c
operar is a skill published in the GitHub repository gabrielzucco/cerebro-inevita (6 stars, last pushed 8d ago), licensed MIT. It adds 65 tokens to every session and 1,166 once invoked, about $0.0003 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
handoff
Guides the Claude Code agent through completing a task, selecting a handoff tier, building a valid completion-card, and performing a clean task handoff.
x-harness-admission
Teach the x-harness admission workflow and completion-card discipline.
recovery
Handle blocked verification outcomes.
check-docs
Kit-maintainer diagnostic (LOCAL-ONLY, not distributed) that audits the README and docs/ for staleness against the repo's real command/skill/CLI roster, stamped tree, and cross-doc consistency. Read-only; produces a severity-ranked findings report.
review-agent-config
Diagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
deep-test
Perform a deep test of the codebase, validating functional smoke tests, claim verification, drift checks, license headers, and placeholder checks. Trigger whenever the user asks to run deep tests, check code health, or perform strict verification.