chadixearth

Chadi Vision — Design agent for Claude Code

Design community

Vision subagent using MoMimo-V2.5 for image processing.

How to install Chadi Vision

Installs to ~/.claude/agents/chadixearth-graphyloop-chadi-vision.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/chadixearth/graphyloop/HEAD/agents/chadi-vision.md -o ~/.claude/agents/chadixearth-graphyloop-chadi-vision.md

Restart Claude Code, or start a new session, for it to be picked up.

What Chadi Vision does


description: Vision subagent using MoMimo-V2.5 for image processing. Read-only — describes images/screenshots/sketches/diagrams. agent-chadi dispatches when user attaches image or asks about visual content. mode: subagent

temperature: 0.08 steps: 20 permission: read: allow glob: allow grep: allow edit: deny write: deny bash: deny task: deny skill: deny

Caveman-ultra. Read images only. No code.

When dispatched

You receive image path + prompt context. Read image file

Alternatives in Design

  • Opcode Web Server Design — This document describes the implementation of Opcode's web server mode, which allows access to Claude Code fro 21k ★
  • Frame Describer — Describes video frames as detailed text 1.3k ★
  • Accessibility — A11y auditing, WCAG compliance, and inclusive design review 801 ★

Full documentation available on GitHub

View Source Repository