brain

A local 3D visualization that shows detected AI-agent behavior as activity across nine brain-like regions in a browser. It runs a local web server and can create a shareable snapshot URL.

In plain words
What is it for?
Use it to monitor agent behavior in real time, open the visualization on a chosen port, or capture a shareable snapshot.
Why use it?
It makes an agent’s detected behavior visible while the agent works, instead of requiring you to infer activity from terminal output. It can also connect to supported IDE agents in the same directory.

Skill for Claude CodeCodex

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 skills/productstein/holomime/brain
Any agent
npx skills add productstein/holomime --skill brain
Clone the repo
git clone --depth 1 https://github.com/productstein/holomime

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 299 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00058 $0.00299
Opus 5 $0.00029 $0.00150
Sonnet 5 $0.00012 $0.00060
Haiku 4.5 $0.00006 $0.00030

Measured yesterday against content hash 5ff1d36d81a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brain scanned grade A with 0 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

integrations/claude-code-skill/skills/brain/SKILL.md · 37 lines

What it actually says

Brain Visualization

Launch the NeuralSpace 3D brain visualization to watch behavioral patterns fire in real-time.

Usage

npx holomime brain $ARGUMENTS

Opens http://localhost:3838 in your browser.

Features

  • 9 brain regions mapped to behavioral dimensions
  • Real-time pattern detection — watch detectors fire as the agent works
  • Auto-detects IDE agents — Claude Code, Cline, Cursor, OpenClaw
  • Shareable snapshots--share generates a public URL

Options

  • --port 3838 — custom port (default 3838)
  • --share — generate a shareable snapshot URL at app.holomime.com/brain/<id>

Gotchas

  • Runs as a local web server — keep the terminal open while viewing
  • Works best in Chrome/Edge for WebGL performance
  • The brain auto-connects to running agent processes in the same directory
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. yesterday First seen · 37 lines · 58 tokens per session scan A 5ff1d36d81a6

Subscribe to this mod's changes

brain is a skill published in the GitHub repository productstein/holomime (1 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 299 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.