agent-brain-install

A command that installs the Agent Brain Python packages, using pipx, uv, pip with a virtual environment, or conda. These are different tools for managing Python software and environments.

In plain words
What is it for?
Use it when setting up Agent Brain for the first time or selecting an installation method for a global, isolated, virtual-environment, or conda-based setup.
Why use it?
It gives you installation steps suited to your preferred Python setup and requires you to choose the method before commands are run.

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-install
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,617 The whole file, excluding the scripts and references it only reads on demand.
Security scan E 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 $0.00020 $0.01617
Opus 5 $0.00010 $0.00809
Sonnet 5 $0.00004 $0.00323
Haiku 4.5 $0.00002 $0.00162

Measured 2d ago against content hash 4929378274e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade E, and why

agent-brain-install scanned grade E 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -LsSf https://astral.sh/uv/install.sh | sh

Reads agent configuration directoriesmediumAgent snooping

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

PYPI_VERSION_SCRIPT=$(find ~/.claude/plugins/agent-brain/scripts ~/.claude/skills/agent-brain/scripts agent-brain-plugin/scripts -name "ab-pypi-version.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.

PYPI_VERSION_SCRIPT=$(find ~/.claude/plugins/agent-brain/scripts ~/.claude/skills/agent-brain/scripts agent-brain-plugin/scripts -name "ab-pypi-version.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.

VERSION=$(curl -sf https://pypi.org/pypi/agent-brain-rag/json | python3 -c "import sys,json; print(json.load(sys.stdin)['info']['version'])")
agent-brain-plugin/commands/agent-brain-install.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Install Agent Brain Packages

STOP - READ THIS FIRST

DO NOT RUN ANY INSTALLATION COMMANDS YET.

You MUST ask the user which installation method they prefer using the AskUserQuestion tool BEFORE doing anything else.

Step 1: Ask User for Installation Method

THIS IS MANDATORY. DO NOT SKIP THIS STEP.

Use the AskUserQuestion tool with this exact structure:

{
  "questions": [{
    "question": "Which installation method do you prefer for Agent Brain?",
    "header": "Install via",
    "options": [
      {
        "label": "pipx (Recommended)",
        "description": "Install globally in an isolated environment. No activation needed."
      },
      {
        "label": "uv",
        "description": "Fast, modern Python tool installer. Good for power users."
      },
      {
        "label": "pip (venv)",
        "description": "Install into a local virtual environment. Requires activation."
      },
      {
        "label": "conda",
        "description": "For conda users. Creates a conda environment with pip inside."
      }
    ],
    "multiSelect": false
  }]
}

STOP HERE AND WAIT FOR THE USER'S RESPONSE.

Do not proceed until you have called AskUserQuestion and received the user's selection.


Step 1.5: Resolve Version

After receiving the user's installation method choice, resolve the latest version from PyPI:

# Resolve helper script path (installed plugin or local repo)
PYPI_VERSION_SCRIPT=$(find ~/.claude/plugins/agent-brain/scripts ~/.claude/skills/agent-brain/scripts agent-brain-plugin/scripts -name "ab-pypi-version.sh" 2>/dev/null | head -1)

if [ -n "$PYPI_VERSION_SCRIPT" ]; then
  VERSION=$("$PYPI_VERSION_SCRIPT")
  echo "Latest available: $VERSION"
else
  echo "ab-pypi-version.sh not found — falling back to inline version lookup"
  VERSION=$(curl -sf https://pypi.org/pypi/agent-brain-rag/json | python3 -c "import sys,json; print(json.load(sys.stdin)['info']['version'])")
  echo "Latest available: $VERSION"
fi

Read the full file on GitHub · 249 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 · 249 lines · 20 tokens per session scan E 4929378274e9

Subscribe to this mod's changes

agent-brain-install is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 1,617 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it E with 4 findings (downloads and executes remote code, 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.