# argus

> argus — korisame-argus. Use this tool when you need to automate tasks on macOS using vision-grounded technology, solving problems such as repetitive computer interactions and workflow optimization. Argus takes input from Apple Vision OCR and outputs automated actions, integrating with 40 tools and git for seamless workflow management. It's ideal for use cases requiring hybrid automation, replacing traditional computer use on macOS.

Canonical page: https://skillsregistry.net/skills/korisame-argus  
JSON: https://api.skillsregistry.net/v1/skills/korisame-argus

## Description

Vision-grounded macOS automation as a Claude Code MCP plugin (40 tools). Hybrid AX + Apple Vision OCR + CDP + Moondream cascade. Replaces Computer Use on macOS.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/korisame/argus)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "korisame-argus"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/korisame-argus` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/korisame-argus/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt