agent-brain-install-agent

An installer that converts the Agent Brain plugin into the file format required by different AI coding tools.

In plain words
What is it for?
Use it to install Agent Brain for Claude Code, OpenCode, Gemini CLI, Codex, or a generic skill runtime at project or user level.
Why use it?
It avoids manually adapting plugin files for each runtime and can show the planned changes before installation.

Command

Part of the agent-brain-plugin plugin — 29 commands, 3 agents shipped together

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-agent
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain

Or install agent-brain-plugin, the plugin that ships this one along with the rest of its 29 commands, 3 agents.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,101 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 $0.00022 $0.02101
Opus 5 $0.00011 $0.01051
Sonnet 5 $0.00004 $0.00420
Haiku 4.5 $0.00002 $0.00210

Measured 3d ago against content hash f71c182c7bc4, 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-install-agent 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 3d 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.

# ...for Codex (→ ~/.codex/config.toml, TOML [mcp_servers.agent-brain])
agent-brain-plugin/commands/agent-brain-install-agent.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Brain Install Agent

Purpose

Installs Agent Brain plugin files for a specific AI coding runtime. Converts the canonical plugin format into the target runtime's native format and writes the files to the appropriate directory.

Supported runtimes:

  • Claude Code — copies plugin as-is with path normalization
  • OpenCode — converts tool lists to boolean objects, maps tool names to lowercase
  • Gemini CLI — remaps tool names (e.g., Bash->run_shell_command), removes unsupported fields
  • Codex — creates skill directories under .codex/skills/agent-brain/ and generates AGENTS.md
  • skill-runtime — generic converter producing skill directories with SKILL.md frontmatter (requires --dir)

Usage

agent-brain install-agent --agent <runtime> [--project|--global] [--plugin-dir <path>] [--dir <path>] [--dry-run] [--json] [--path <path>]

Parameters

Parameter Required Default Description
--agent / -a Yes - Target runtime: claude, opencode, gemini, skill-runtime, or codex
--project No Yes Install to project directory (default)
--global No No Install to user-level directory
--plugin-dir No Auto-detect Custom canonical plugin source directory
--dir No* - Target skill directory (*required for skill-runtime)
--dry-run No No List files without writing
--json No No Machine-readable JSON output
--path / -p No cwd Project path for --project scope

Install Directories

Runtime Project Scope Global Scope
Claude .claude/plugins/agent-brain/ ~/.claude/plugins/agent-brain/
OpenCode .opencode/plugins/agent-brain/ ~/.config/opencode/plugins/agent-brain/
Gemini .gemini/plugins/agent-brain/ ~/.config/gemini/plugins/agent-brain/
Codex .codex/skills/agent-brain/ ~/.codex/skills/agent-brain/
skill-runtime Requires --dir Requires --dir

Read the full file on GitHub · 243 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. 3d ago First seen · 243 lines · 22 tokens per session scan B f71c182c7bc4

Subscribe to this mod's changes

agent-brain-install-agent is a command published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 2,101 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 2026-08-30.