brain-setup

A command for setting up a personal knowledge vault and its supporting configuration. It can also connect an optional shared team vault.

In plain words
What is it for?
Use it for first-time setup, including choosing the vault location, creating its folders and starter files, registering it with the note app, and optionally configuring team storage.
Why use it?
It gives developers a consistent place to save notes, reflect on work, and retrieve useful context across sessions. It avoids having to create the folder structure and settings by hand.

Command

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/fiale-plus/fiale-claude-plugins/setup
Clone the repo
git clone --depth 1 https://github.com/fiale-plus/fiale-claude-plugins
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,934 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00023 $0.02934
Opus 5 $0.00012 $0.01467
Sonnet 5 $0.00005 $0.00587
Haiku 4.5 $0.00002 $0.00293

Measured 2d ago against content hash 6abbca136cb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

brain-setup scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/CLAUDE.md 2>/dev/null
plugins/brain/commands/setup.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.

First-time setup for the brain plugin. Run once. Covers vault creation, config, Obsidian registration, and team setup.

Steps

1. Detect environment

uname -s
echo $HOME
python3 --version
which claude

Report OS, home directory, Python version, and claude path.

2. Personal vault path

Ask:

"Where should your personal brain vault live? Default is ~/brain. Press Enter to accept or type a path."

If they press Enter or say "default", use ~/brain. Expand ~ to real home path. Call this VAULT_PATH.

3. Create vault structure

mkdir -p VAULT_PATH/_sessions
mkdir -p VAULT_PATH/atoms
mkdir -p VAULT_PATH/weekly
mkdir -p VAULT_PATH/Polaris

Create placeholder files only if they don't already exist:

VAULT_PATH/Polaris/top-of-mind.md (if missing):

# Top of Mind

What matters most right now. The /synthesize command reads this to assess session alignment.
Update this file when your focus shifts: start of a new project or sprint, after /brain-reflect
suggests drift, or whenever your context switches.

## Current focus


## Active projects


## What I'm trying to figure out


## What I want more of


## What I want less of

VAULT_PATH/Polaris/life-razor.md (if missing):

# Life Razor

Principles I use to make decisions quickly.

## If in doubt...


## I always...


## I never...


## My barometer for a good day:

Report which files were created vs already existed.

4. Auto-synthesize on session start?

Ask:

"Auto-synthesize pending sessions when you start a new Claude Code session? [Y/n]"

Default: yes. Store as auto_synthesize in config (bool).

5. Surface hints in session?

Ask:

"Surface related personal atoms when you're working on relevant tasks? [Y/n]"

Default: yes. Store as surface_hints in config (bool).

If no, explain: "You can still run /brain-search manually to find relevant atoms."

6. Write config

mkdir -p ~/.claude/brain

Write ~/.claude/brain/config.json:

{
  "vault_path": "VAULT_PATH",
  "auto_synthesize": true,
  "surface_hints": true,
  "team": {
    "enabled": false
  }
}

Read the full file on GitHub · 370 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. 2d ago First seen · 370 lines · 23 tokens per session scan B 6abbca136cb4

Subscribe to this mod's changes

brain-setup is a command published in the GitHub repository fiale-plus/fiale-claude-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 2,934 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.