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/metodo/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/metodo)<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/metodo"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/metodo/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/metodo"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/metodo.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 | $0.00071 | $0.00839 |
| Opus 5 | $0.00036 | $0.00419 |
| Sonnet 5 | $0.00014 | $0.00168 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
metodo 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engenharia de Contexto — o método do cérebro (explique e aplique)
O método tem nome: engenharia de contexto (o Karpathy, da OpenAI, popularizou — na era da IA o jogo é montar o contexto certo, não o prompt). Mencione isso pra dar lastro, mas vá direto ao prático.
Objetivo: a pessoa entender o método em 2 minutos e aplicar em algo real dela já. Sem jargão. Explique curto e, no fim, ofereça rodar num exemplo dela.
O ciclo (explique assim)
Primeiro a frase-mestra: o método são 5 verbos — capturar → destilar → estruturar → operar → medir (o METODO-COMPLETO.md conta a história inteira). No dia a dia, o cérebro executa isso em 4 movimentos:
- Organizar por uso, não por tema. Quatro horizontes: agora (
fios/, o que está quente) · áreas do negócio (oferta, icp, posicionamento, o-que-funciona, decisões) · referências (conhecimento/, o que vem de fora) · arquivo (o que esfriou). Você nunca decide "onde guardar" — o horizonte decide. - Capturar em átomos. Cada coisa que importa vira uma nota de uma ideia, com: a afirmação (um título-frase que diz o que ela afirma), a citação literal da fonte (a evidência), 1-2 linhas de por que importa, e elos pra outras notas. Nem tudo vira átomo — só o que tem sinal.
- Conectar leve. Você linka o óbvio; o cérebro sugere o resto. A IA amplia teu pensamento — não pensa por você.
- Buscar citando. Você pergunta em linguagem normal; o cérebro traz os trechos citados das tuas notas — nunca um amontoado, nunca invenção.
Os relógios (quando cada coisa acontece)
Contexto tem cadência — e cada relógio tem uma skill:
- Todo dia (10 min):
/daily— o dia vira contexto com a memória quente (teu julgamento sobre o que importou expira em ~48h). - Saiu de call:
/callem até 48h. - Toda semana (30-45 min):
/reindex— bandeja zerada, fios revisados, o resumo da semana (que nasce das dailies, nunca de reler tudo). - Todo mês:
/revisar(a verdade muda — nota velha se confirma, atualiza ou marcasuperado) e/teste(as tuas 5 perguntas-canário: a resposta evolui de em branco → estagiário → sócio).
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 · 31 lines · 71 tokens per session scan A 4e4f869f0230
metodo is a skill published in the GitHub repository gabrielzucco/cerebro-inevita (6 stars, last pushed 9d ago), licensed MIT. It adds 71 tokens to every session and 839 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
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.