Vision Tools

Vision Tools is an AI Engineering skill for Claude Code, published by Anionex in codex-vision-proxy.

388 stars19 forkson Anionex/codex-vision-proxyAdded 2026/08/11+40% in starsRepository updated 2026/08/09

agentagent-skillsclaude-codeclicodexcomputer-usedeepseekglmharness-engineeringkimillmmultimodalopencodetext-only-llmvisionvision-language-model

Install in seconds

Install Vision Tools

Copy Vision Tools into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Anionex/agent-vision-toolkit/tree/main/skills/vision-tools ~/.claude/skills/vision-tools

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Anionex/agent-vision-toolkit.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/vision-tools/SKILL.md in Anionex/codex-vision-proxy
Installs to: ~/.claude/skills/vision-tools
Collection: The only skill cataloged from this repository
Category: AI Engineering — 2451 skills

What Vision Tools does

Local vision CLIs (glance, ground, detect, trace, crop) give text-only agents the ability to describe, OCR, locate elements, extract shapes, and crop images. Also includes scripts for long screenshot OCR, HTML-to-image, and more. Use for any task involving an image — from reading text to GUI automation.

Vision Tools is cataloged under AI Engineering on DirSkills. Vision Tools comes from a repository tagged agent, agent-skills, claude-code, cli and codex.

Documentation

README

Excerpt

vision-tools

Five local CLIs that give a text-only agent eyes. They read one shared vision config (VISION_API_KEY / VISION_BASE_URL / VISION_MODEL / LANG) — no extra credentials.

Pick the tool by the question you are answering:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Vision Tools

How does Vision Tools compare to other AI Engineering skills?
Vision Tools ranks #2208 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Vision Tools against them. Open each page to compare what they document and how they install.