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.
npx agentmods add commands/pedrohenrique0713/brain-template/update_braingit clone --depth 1 https://github.com/PedroHenrique0713/brain-templateWrote 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/commands/pedrohenrique0713/brain-template/update_brain)<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>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 | $0.00037 | $0.01314 |
| Opus 5 | $0.00018 | $0.00657 |
| Sonnet 5 | $0.00007 | $0.00263 |
| Haiku 4.5 | $0.00004 | $0.00131 |
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.
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/(ouPROJECTS),05 - REUNIÕES/,07 - HANDOVERS/,00 - INBOX/, notas soltas. - Mover, não recriar — ao migrar conteúdo, preserve o texto integral; não resuma nem reescreva.
AGENTS.mdé o arquivo canônico.CLAUDE.md/GEMINI.mdficam 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".
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.
- 3d ago First seen · 88 lines · 37 tokens per session scan A 90287efadba3
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.
Other commands, from other repositories
dump
Brain dump mode -- talk about anything, Claude organizes it.
today
Daily briefing -- tasks, recent captures, patterns, time-sensitive items.
om-self-review
Write your self-assessment for your company's review tool. Produces project impact descriptions, competency self-assessments (current level / next level), principles, and growth plan — all within character limits, fact-checked, strategically calibrated.
om-vault-audit
Deep structural audit of the vault. Checks indexes, folder placement, frontmatter, links, Bases, and consistency. Fix what can be fixed, flag what needs user input.
om-wrap-up
Full session review before ending. Review context, ways of working, files modified, consistency, and suggest improvements.
om-meeting
Prep for any meeting by topic — subject-forward briefing with open tasks, blockers, and brainstormed considerations the user may not have thought of yet.