update_brain

update_brain is a command for Claude Code from PedroHenrique0713/brain-template. It costs 37 tokens per session (1,314 once invoked), scanned A, original, MIT.

A command for migrating a note-taking vault from template version one to version two. A vault is the folder containing the notes and related files, and the migration changes its structure from skills to commands and from CLAUDE.md to AGENTS.md.

In plain words
What is it for?
Detecting old template structures, moving content to the new locations, keeping AGENTS.md as the main instruction file, and reporting the proposed changes before applying them.
Why use it?
It reorganizes the vault while preserving the user's notes and asks for confirmation before writing when there may be a conflict.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/pedrohenrique0713/brain-template/update_brain
Clone the repo
git clone --depth 1 https://github.com/PedroHenrique0713/brain-template

Made for: Claude Code.

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 update_brain

README.md
[![agentmods](https://agentmods.dev/badge/commands/pedrohenrique0713/brain-template/update_brain.svg)](https://agentmods.dev/commands/pedrohenrique0713/brain-template/update_brain)
Your own site
<a href="https://agentmods.dev/commands/pedrohenrique0713/brain-template/update_brain"><img src="https://agentmods.dev/badge/commands/pedrohenrique0713/brain-template/update_brain.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,314 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.01314
Opus 5 $0.00018 $0.00657
Sonnet 5 $0.00007 $0.00263
Haiku 4.5 $0.00004 $0.00131

Measured 3d ago against content hash 90287efadba3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update_brain 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 3d 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.

vault/.claude/commands/update_brain.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

update_brain

Migra um vault criado numa versão antiga do template para a estrutura atual, sem destruir o conteúdo da pessoa. É o complemento do update.sh:

  • update.sh (terminal) puxa o framework novo (commands, scripts) do GitHub.
  • /update_brain (aqui) reorganiza a estrutura local: move conteúdo do lugar antigo pro novo e ajusta os ponteiros.

Faça em etapas, confirme antes de cada escrita e nunca prossiga com dúvida sobre perda de dados.

Regras de ouro

  • NUNCA apague ou sobrescreva conteúdo do usuário: Memória/, 01 - PROJETOS/ (ou PROJECTS), 05 - REUNIÕES/, 07 - HANDOVERS/, 00 - INBOX/, notas soltas.
  • Mover, não recriar — ao migrar conteúdo, preserve o texto integral; não resuma nem reescreva.
  • AGENTS.md é o arquivo canônico. CLAUDE.md/GEMINI.md ficam finos, só apontando pra ele.
  • Em caso de conflito (já existe destino), pergunte — nunca decida sozinho sobrescrever.
  • Use o idioma da pessoa. Mostre um plano antes de aplicar.

1. Diagnóstico

Antes de qualquer mudança, leia o vault e detecte o que é v1. Reporte uma tabela do que será feito:

Sinal de v1 Detecção Ação proposta
Skills antigas existe .claude/skills/ mover para .claude/commands/
Cérebro no lugar errado CLAUDE.md tem conteúdo de perfil (mais que um ponteiro) e não existe AGENTS.md mover conteúdo → AGENTS.md, deixar CLAUDE.md fino
GEMINI.md gordo tem conteúdo próprio em vez de ponteiro reduzir a ponteiro
Pastas faltando sem 00 - INBOX/, 07 - HANDOVERS/Arquivo/, Tarefas/, Tarefas/Arquivo/ criar + .gitkeep
Memória sem índice sem Memória/INDEX.md criar índice base
Sem marcador de versão sem .claude/.brain-version criar ao final

Se nada de v1 for detectado, diga que o vault já está na estrutura atual e sugira rodar update.sh pra pegar commands novos. Pare aqui.

2. Plano e confirmação

Mostre o plano completo (o que move, o que cria, o que NÃO será tocado) e peça confirmação explícita: "Posso aplicar?". Só prossiga com um "sim".

Read the full file on GitHub · 88 lines

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. 3d ago First seen · 88 lines · 37 tokens per session scan A 90287efadba3

Subscribe to this mod's changes

update_brain is a command published in the GitHub repository PedroHenrique0713/brain-template (1 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,314 once invoked, about $0.0002 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.