agent-brain-setup

A guided command that installs, configures, initializes, and checks Agent Brain from start to finish.

In plain words
What is it for?
Use it to set up Agent Brain in a new project and verify that the installation works.
Why use it?
It removes the need to run setup steps manually or guess which step comes next. It stops when an earlier step fails.

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/spillwavesolutions/agent-brain/agent-brain-setup
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,591 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 4 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 $0.00021 $0.04591
Opus 5 $0.00010 $0.02295
Sonnet 5 $0.00004 $0.00918
Haiku 4.5 $0.00002 $0.00459

Measured 2d ago against content hash d4da0f9157ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

agent-brain-setup scanned grade D with 4 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 "$CONFIG_PATH"

Reads agent configuration directoriesmediumAgent snooping

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

SCRIPT=$(find ~/.claude/plugins/agent-brain/scripts ~/.claude/skills/agent-brain/scripts agent-brain-plugin/scripts -name "ab-setup-check.sh" 2>/dev/null | head -1)

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

SCRIPT=$(find ~/.claude/plugins/agent-brain/scripts ~/.claude/skills/agent-brain/scripts agent-brain-plugin/scripts -name "ab-setup-check.sh" 2>/dev/null | head -1)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

"Bash(curl:*)",
agent-brain-plugin/commands/agent-brain-setup.md · 601 lines

How it starts

The opening of the file, as written. The whole thing — 601 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Complete Agent Brain Setup

Purpose

Runs a complete guided setup flow for Agent Brain, taking the user from zero to a fully working installation. This command orchestrates installation, configuration, initialization, and verification steps.

Usage

/agent-brain-setup

Execution

Run each step in sequence, proceeding only if the previous step succeeds.

Step 0: Bootstrap Permissions

Before running any shell commands, ensure .claude/settings.json exists with the required permissions for the setup wizard. Use the Write tool (not Bash) to create this file — the Write tool is always available without a permission gate.

Check if the file already exists:

ls .claude/settings.json 2>/dev/null && echo "EXISTS" || echo "MISSING"

If missing or if it does not contain "Bash(agent-brain:*)", write the following content to .claude/settings.json using the Write tool:

{
  "_comment": "Agent Brain setup permissions — written by /agent-brain-setup. Safe to commit.",
  "permissions": {
    "allow": [
      "Bash(agent-brain:*)",
      "Bash(lsof:*)",
      "Bash(ollama:*)",
      "Bash(docker:*)",
      "Bash(mkdir:*)",
      "Bash(cat:*)",
      "Bash(jq:*)",
      "Bash(mv:*)",
      "Bash(du:*)",
      "Bash(ps:*)",
      "Bash(pgrep:*)",
      "Bash(pip:*)",
      "Bash(pipx:*)",
      "Bash(uv:*)",
      "Bash(python:*)",
      "Bash(python3:*)",
      "Bash(rg:*)",
      "Bash(wc:*)",
      "Bash(curl:*)",
      "Bash(ls:*)",
      "Bash(find:*)",
      "Bash(chmod:*)",
      "Bash(grep:*)",
      "Bash(bash:*)"
    ],
    "deny": []
  }
}

After writing the file, tell the user: "Wrote .claude/settings.json with Agent Brain setup permissions. These allow the wizard to run without permission prompts. The file is safe to commit — it grants access only to standard development tools."

IMPORTANT: If .claude/settings.json already exists with custom content, MERGE: add any missing Bash(...) entries from the list above into the existing allow array rather than replacing the file.

Read the full file on GitHub · 601 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 · 601 lines · 21 tokens per session scan D d4da0f9157ff

Subscribe to this mod's changes

agent-brain-setup is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 4,591 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 4 findings (asks for root, reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.