agentmods.dev

init_newbrain

init_newbrain is a command for Claude Code from PedroHenrique0713/brain-template. It costs 24 tokens per session (959 once invoked), scanned A, original, MIT.

An interactive setup command for personalising a knowledge vault and its shared instruction files. It asks about the person's identity, work, projects, tools, interests, and preferred language before creating the initial structure.

In plain words
What is it for?
Use it when starting a new vault or adapting one to a specific person, including its project context, memory folders, and working preferences.
Why use it?
It prevents the vault from being configured around guesses about the person or their goals. It keeps the main instructions in one canonical file while leaving tool-specific instruction files brief.

Command for Claude Code

not rated 1 1mo ago A scan 24 tokens original MIT
View the source file PedroHenrique0713/brain-template
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/init_newbrain
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 init_newbrain

README.md
[![agentmods](https://agentmods.dev/badge/commands/pedrohenrique0713/brain-template/init_newbrain.svg)](https://agentmods.dev/commands/pedrohenrique0713/brain-template/init_newbrain)
Your own site
<a href="https://agentmods.dev/commands/pedrohenrique0713/brain-template/init_newbrain"><img src="https://agentmods.dev/badge/commands/pedrohenrique0713/brain-template/init_newbrain.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 959 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 $0.00024 $0.00959
Opus 5 $0.00012 $0.00479
Sonnet 5 $0.00005 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured 4d ago against content hash fcef819d5aed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init_newbrain 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 4d 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/init_newbrain.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

init_newbrain

Configura este vault para uma pessoa específica. Faça perguntas em blocos, espere as respostas, confirme o entendimento e só então gere os arquivos.

Regras

  • Use o idioma da pessoa.
  • Faça um bloco por vez.
  • Se a pessoa pular algo, use "a definir".
  • Não escreva em .claude/projects/.../memory/; a memória canônica fica em Memória/.
  • AGENTS.md é o arquivo canônico. CLAUDE.md e GEMINI.md devem continuar finos, apontando para AGENTS.md.

Blocos de perguntas

1. Identidade

Pergunte:

  1. Como devo te chamar?
  2. O que você faz?
  3. Qual é seu objetivo principal com este vault?
  4. Em que idioma prefere que eu responda?
  5. De 1 a 5, quão confortável você é com tecnologia?

2. Trabalho e projetos

Pergunte:

  1. Você trabalha para empresa, é freelancer, estuda, ou combina mais de uma coisa?
  2. Qual empresa/contexto principal e o que ela faz?
  3. Qual é seu papel no dia a dia?
  4. Quais ferramentas usa todo dia?
  5. Quais projetos ativos quer acompanhar? Peça até 5 nomes com uma linha de contexto.
  6. Existem rotinas recorrentes importantes?

3. Vida e conhecimento

Pergunte:

  1. Quais áreas da vida quer acompanhar aqui?
  2. Estuda algo atualmente?
  3. Tem projetos pessoais?
  4. Quer usar diário/journaling?
  5. Existe algum assunto que não quer que a IA acompanhe?

4. Estilo de colaboração

Pergunte:

  1. Prefere respostas curtas, balanceadas ou detalhadas?
  2. Tom formal, casual ou direto?
  3. Quer uma IA proativa, reativa ou equilibrada?
  4. Quer resumo ao fim de cada sessão?
  5. Quer memória entre conversas?
  6. Algum tema sensível a evitar?

5. Setup técnico

Pergunte:

  1. Vai usar Claude Code, Gemini CLI, opencode, ChatGPT/outro, ou várias ferramentas?
  2. Usa VS Code?
  3. Quais plugins Obsidian quer manter ou adicionar?
  4. Com que frequência pretende abrir o vault?
  5. Mais alguma coisa que a IA deve saber?

Geração

Depois dos 5 blocos, faça:

  1. Atualize AGENTS.md com:
    • quem é a pessoa;
    • projetos ativos;
    • áreas de vida;
    • estilo de colaboração;
    • ferramentas;
    • protocolo de memória e handoff preservado.
  2. Garanta CLAUDE.md e GEMINI.md finos: 
    # CLAUDE.md

Leia primeiro: `AGENTS.md`.

`AGENTS.md` é o arquivo canônico de contexto deste vault.
  3. Crie/atualize Memória/user-profile.md: 
    ---
name: user-profile
description: Perfil do usuário, trabalho e estilo de colaboração
type: user
scope: global
updated: YYYY-MM-DD
---

**Nome:** ...
**Profissão/contexto:** ...
**Objetivo do vault:** ...
**Idioma:** ...
**Nível técnico:** ...

**Como colaborar:**
- Tom: ...
- Verbosidade: ...
- Proatividade: ...
- Resumo de sessão: ...
- Memória entre conversas: ...
  4. Atualize Memória/INDEX.md: 
    - [Perfil do usuário](user-profile.md) — `global` — identidade, trabalho e estilo de colaboração
  5. Crie pastas de projetos em 01 - PROJECTS/, áreas em 02 - AREAS/ e estudos em 06 - KNOWLEDGE/, conforme respostas.
  6. Crie notas iniciais de projeto usando 03 - RESOURCES/Templates/projeto-template.md quando fizer sentido.

Read the full file on GitHub · 130 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. 4d ago First seen · 130 lines · 24 tokens per session scan A fcef819d5aed

Subscribe to this mod's changes

init_newbrain is a command published in the GitHub repository PedroHenrique0713/brain-template (1 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 959 once invoked, about $0.0001 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.

Memory and contextai-memoryclaude-codegemini-cliknowledge-basemarkdownobsidian
Related

Other commands, from other repositories

wiki-query

Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.

zosmaai/pi-llm-wiki · 18 tokens

wiki-req

Capture and decompose a concept into atomic, traceable wiki requirements. Clarifies ambiguous requirements, splits them into atomic pieces, and persists them as wiki/requirements/ pages with status tracking.

zosmaai/pi-llm-wiki · 38 tokens

wiki-ingest

Process new source packets and synthesize them into wiki knowledge pages.

zosmaai/pi-llm-wiki · 13 tokens

wiki-record

Capture the just-completed task's tool-call trajectory into the wiki as agent working-memory, then optionally distill it into a reusable skill.

zosmaai/pi-llm-wiki · 28 tokens

wiki-retro

Save an atomic insight from the current task into the wiki. Creates a single markdown file that layered recall surfaces in future sessions.

zosmaai/pi-llm-wiki · 25 tokens

wiki-run

Run the full wiki cycle: discover → ingest → lint. Optionally schedule for auto-updates.

zosmaai/pi-llm-wiki · 0 tokens