cerebro-inevita: Skill for Claude Code

.agents/skills/frameworks-visuais/SKILL.md

frameworks-visuais is a skill for Claude Code, Codex from gabrielzucco/cerebro-inevita. It costs 123 tokens per session (1,569 once invoked), scanned A, original, MIT.

A guide for turning notes into dark, clean Excalidraw diagrams, where Excalidraw is a tool for drawing editable hand-sketched diagrams.

In plain words
What is it for?
Use it to create visual frameworks such as pipelines, matrices, funnels, cycles, pyramids, or story-like diagrams from Obsidian notes.
Why use it?
It helps organize the source material visually while keeping every label and idea traceable to the original note.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; 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/frameworks-visuais/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 frameworks-visuais

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/frameworks-visuais"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/frameworks-visuais.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,569 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 $0.00123 $0.01569
Opus 5 $0.00062 $0.00785
Sonnet 5 $0.00025 $0.00314
Haiku 4.5 $0.00012 $0.00157

Measured 12d ago against content hash 2eb906463fd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

frameworks-visuais 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.

The scan reads SKILL.md. This mod also ships 1 executable file (gerar_excalidraw.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/frameworks-visuais/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frameworks visuais → Excalidraw a partir das tuas notas

O diagrama é uma vista derivada da nota: ele estrutura o que ela já diz, nunca inventa (regra "zero conteúdo inventado" do CLAUDE.md). Todo texto do canvas tem que ser rastreável à fonte — citação literal ou paráfrase que só reorganiza. O .excalidraw.md é uma nota como qualquer outra, com frontmatter e origem.

Requisito: precisa do plugin Excalidraw no Obsidian pra ver o canvas (Community plugins → Excalidraw). E do python3 (já vem no sistema; nada pra instalar).

Passo 1 — ler a fonte

Leia a nota fonte INTEIRA (com o frontmatter). O diagrama nasce ao lado dela, com o nome framework-<slug>.excalidraw.md (kebab-case, prefixo framework-).

  • PII fora: se a nota tiver e-mail/telefone/nome de cliente, não leve pro canvas (a regra de PII do cérebro vale aqui também).
  • Citação em inglês → tradução livre pra pt-BR, marcando "(tradução livre)" no autor.

Passo 2 — escolher o formato

A nota é rica (mais de um conceito/movimento)? Se sim, o padrão é historia — o canvas vira ATOS empilhados (número grande, título curto, UM visual central, texto mínimo), lidos em sequência como narrativa. Nunca empilhe tudo numa cena só — polui. E prefira metáfora visual a card de texto: o engine tem pictogramas (tornado, precipício+ponte, botão, casinhas, onda) — use quando a fonte der a imagem.

Pra um conceito pontual (uma estrutura só), abra taxonomia.md e escolha: pipeline · curva-com-abismo · matriz-2x2 · funil · piramide · ciclo · anatomia · contraste. Escolha o que responde à pergunta que o leitor faz ("em que ordem?" ≠ "o que escolher?"). Na dúvida, pergunte à pessoa.

Passo 3 — escrever o SPEC JSON

Escreva o spec num arquivo temporário (ex.: /tmp/spec-<slug>.json). Schema completo + exemplo de cada arquétipo: docstring do gerar_excalidraw.py. O spec carrega:

  • titulo (caixa alta, curto) · subtitulo (quem disse + credencial de 1 linha) · gancho (1-2 linhas em 2ª pessoa: por que VOCÊ deveria se importar) · como_ler (1 linha)
  • historiaatos: cada um com titulo, texto (1-2 linhas, opcional), cor e UM visual (curva-abismo-mini · precipicio-ponte · vinhetas · setas-tensao). 3 a 5 atos.
  • Single-shot → itens: cards completos, cada um conta a própria parte sem legenda. Máx. 5–9.
  • cor semântica: laranja = novo/risco · azul = agora/movimento · cinza = contexto · vermelho = dor/perigo · dourado = impacto.
  • definicao (nos cards) — a linha "o que É isso" na PRIMEIRA aparição de cada termo/sigla.
  • citacao — a frase de impacto da fonte, com ref (obrigatório se houver citação direta).
  • takeaway — "E AGORA? →" com 1-3 ações ancoradas na fonte (nunca invente ação).
  • frontmatterfonte, criado, origem: "[[nota-fonte]]".

Read the full file on GitHub · 90 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 90 lines · 123 tokens per session scan A 2eb906463fd6

Subscribe to this mod's changes

frameworks-visuais is a skill published in the GitHub repository gabrielzucco/cerebro-inevita (6 stars, last pushed 8d ago), licensed MIT. It adds 123 tokens to every session and 1,569 once invoked, about $0.0006 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.