cerebro-inevita: Skill for Claude Code

.agents/skills/revisar/SKILL.md

revisar is a skill for Claude Code, Codex from gabrielzucco/cerebro-inevita. It costs 60 tokens per session (565 once invoked), scanned A, original, MIT.

A monthly review process for checking whether business notes are still accurate. It finds old or conflicting notes and asks a person to confirm, update, or mark them as outdated.

In plain words
What is it for?
Use it to review notes in a business knowledge folder, resolve conflicting claims, and record which information remains valid.
Why use it?
It prevents old prices, offers, or decisions from being treated as current information.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is gabrielzucco/cerebro-inevita's own configuration. It tells Claude Code and Codex how to work on cerebro-inevita itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cerebro-inevita configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/gabrielzucco/cerebro-inevita/main/.agents/skills/revisar/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gabrielzucco/cerebro-inevita

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for revisar

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/revisar/github.svg)](https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/revisar)
Your own site
<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/revisar"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/revisar/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.

agentmods 80×15 button for revisar

Your own site · 80×15
<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/revisar"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/revisar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 565 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.00565
Opus 5 $0.00030 $0.00282
Sonnet 5 $0.00012 $0.00113
Haiku 4.5 $0.00006 $0.00056

Measured 12d ago against content hash e9255398db87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

revisar 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.

.agents/skills/revisar/SKILL.md · 23 lines

What it actually says

Revisar — frescor mensal (a verdade muda; a nota tem que acompanhar)

A nota mais perigosa do cérebro é a que morreu fingindo estar viva: o preço antigo, a oferta que mudou, a decisão revertida — contaminando cada resposta. Esta skill caça essas notas. Nada se deleta: se marca.

  1. Varra meu-negocio/ (fora arquivo/ e dailies/) e liste as suspeitas:
    • notas com confirmado:mais de 60 dias (ou sem o campo)
    • conflitos: duas notas afirmando coisas incompatíveis (ex.: dois preços, dois ICPs)
    • notas de fios/ paradas há mais de 30 dias
  2. Apresente a lista em ordem de risco (áreas centrais primeiro: oferta → icp → posicionamento) com o teor de cada uma em 1 linha.
  3. Uma por vez, três saídas — pergunte "isso ainda vale?":
    • Vale → atualize confirmado: <hoje> no frontmatter. Só isso.
    • Mudou → edite COM a pessoa (o novo teor precisa de evidência nova) + confirmado: <hoje>.
    • Morreu → marque status: superado no frontmatter e acrescente 1 linha no topo: "Superada em por [[nota-nova]]". A nota fica — vira histórico, sai do caminho.
  4. Conflitos são prioridade: mostre as duas citações lado a lado e pergunte qual é a verdade atual. Uma vence (confirmado:), a outra se marca (superado).
  5. Feche com o placar: "N confirmadas, N atualizadas, N superadas — teu cérebro está X% fresco" (fresco = confirmado há menos de 60 dias).

Regras: 20 minutos, teto — se a lista for longa, só as 10 mais arriscadas e o resto fica pro mês que vem · nunca delete nem "conserte" nota sozinho — quem sabe a verdade atual é a pessoa · nota superado nunca entra em resposta como fato vigente (só como histórico, dizendo que é histórico).

Changes

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.

  1. 12d ago First seen · 23 lines · 60 tokens per session scan A e9255398db87

Subscribe to this mod's changes

revisar is a skill published in the GitHub repository gabrielzucco/cerebro-inevita (6 stars, last pushed 9d ago), licensed MIT. It adds 60 tokens to every session and 565 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.