What is claude-cobrain?

A macOS background service that captures active-window screens and summarizes them with a local vision-language model, an AI system that understands images.

Use it to collect screen-based activity summaries and support a local memory workflow.

It provides a record of computer activity that can help the agent remember what was happening on screen.

claude-cobrain — Plugin for Claude Code by cyrus-cai

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.

Clone the repo

git clone --depth 1 https://github.com/cyrus-cai/claude-cobrain

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/cyrus-cai/claude-cobrain/plugin/github.svg)](https://agentmods.dev/plugins/cyrus-cai/claude-cobrain/plugin)

Your own site

<a href="https://agentmods.dev/plugins/cyrus-cai/claude-cobrain/plugin"><img src="https://agentmods.dev/badge/plugins/cyrus-cai/claude-cobrain/plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/cyrus-cai/claude-cobrain/plugin"><img src="https://agentmods.dev/badge/plugins/cyrus-cai/claude-cobrain/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 7 skills, 1 command, 1 hook cost 107 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

claude-cobrain 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 2mo 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.

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.

plugin/.claude-plugin/plugin.json · 18 lines

What it actually says

{
  "name": "claude-cobrain",
  "version": "0.4.4",
  "description": "Screen activity memory daemon - captures active windows and summarizes them using local VLM",
  "author": {
    "name": "cyrus-cai"
  },
  "repository": "https://github.com/cyrus-cai/claude-cobrain",
  "license": "MIT",
  "keywords": [
    "memory",
    "screen-capture",
    "vlm",
    "macos",
    "daemon"
  ]
}

Contents

What it installs

The manifest is a name and a version. 7 skills, 1 command, 1 hook travel with it, and installing the plugin installs all of them — 107 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

2mo ago First seen · 18 lines scan A d4f0003046c8

Subscribe to this mod's changes

claude-cobrain is a plugin published in the GitHub repository cyrus-cai/claude-cobrain (5 stars, last pushed 8mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Claude Code Memory and context claude claude-skills

claude-cobrain next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-cobraincyrus-cai/claude-cobrain	Plugin	5	8mo ago	MIT	A	—	Claude Code
project-templates-toolkitjamditis/claude-skills-journalism	Plugin	448	2d ago	MIT	A	—	Claude Code
autocontextjamditis/claude-skills-journalism	Plugin	448	2d ago	MIT	A	—	Claude Code
cross-code-organizermcpware/cross-code-organizer	Plugin	386	2d ago	MIT	A	—	Claude Code
open-knowledge-vaultglebis/claude-skills	Plugin	409	yesterday	MIT	A	—	Claude Code
context-leveltobihagemann/turbo	Plugin	419	14d ago	MIT	A	—	Claude Code
knowledge-and-memoryoaustegard/claude-skills	Plugin	158	4d ago	MIT	A	—	Claude Code