agent-brain-start

A command that starts the Agent Brain server for a project. The server stores and indexes documents and supports keyword, meaning-based, and combined searches.

In plain words
What is it for?
Use it to start the server for the current project, choose its project path or port, run it in the foreground, enforce provider checks, or request JSON output.
Why use it?
It provides the running service that other Agent Brain searches need in order to access project knowledge.

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-start
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,911 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 $0.00013 $0.01911
Opus 5 $0.00006 $0.00955
Sonnet 5 $0.00003 $0.00382
Haiku 4.5 $0.00001 $0.00191

Measured 2d ago against content hash d626d7bf2be6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

agent-brain-start 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.

Asks for rootmediumPrivilege escalation

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

chmod 755 .agent-brain
agent-brain-plugin/commands/agent-brain-start.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Brain Start

Purpose

Starts the Agent Brain server for the current project. The server provides:

  • Document indexing and storage
  • Hybrid, semantic, and keyword search
  • Multi-instance support with automatic port allocation

Usage

/agent-brain:agent-brain-start [--path <dir>] [--host <host>] [--port <port>] [--foreground] [--strict] [--json]

Parameters

Parameter Required Default Description
--path, -p No auto-detect Project path
--host No 127.0.0.1 Server bind host (overrides config)
--port No auto-select (8000-8100) Server port (overrides config)
--foreground, -f No false Run in foreground (don't daemonize)
--timeout No 30 Startup timeout in seconds
--strict No false Fail on critical provider config errors
--json No false Output as JSON

Execution

Pre-flight Check

Verify the project is initialized:

# Check for .agent-brain/ directory
ls -la .agent-brain/

If not initialized:

agent-brain init

Start Server

# Start in background (default, recommended)
agent-brain start

# Start on a specific port
agent-brain start --port 8080

# Start in foreground for debugging
agent-brain start --foreground

# Start with strict mode (fail on missing API keys)
agent-brain start --strict

# Start for a specific project path
agent-brain start --path /my/project

# JSON output for scripting
agent-brain start --json

Verify Server Started

agent-brain status

Output

Successful Start

Agent Brain Server Running
URL: http://127.0.0.1:8000
PID: 12345
Project: /home/user/my-project
Log: /home/user/my-project/.agent-brain/logs/server.log

Next steps:
  - Query: agent-brain query 'search term' --url http://127.0.0.1:8000
  - Stop: agent-brain stop

JSON Output

{
  "status": "started",
  "base_url": "http://127.0.0.1:8000",
  "pid": 12345,
  "project_root": "/home/user/my-project",
  "log_file": "/home/user/my-project/.agent-brain/logs/server.log"
}

Read the full file on GitHub · 331 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 · 331 lines · 13 tokens per session scan B d626d7bf2be6

Subscribe to this mod's changes

agent-brain-start is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 1,911 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.