ModLens

Skill

Give text-only coding agents vision: pass an image path and get structured JSON with OCR, layout and semantics back.

by liustack Listed Feb 22, 2026

Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.

Product badge

Share this product's name and rating in your README or on your website.

Updates may be delayed by image caching.

About ModLens

ModLens is a vision bridge for models that cannot read images, built first for DeepSeek's harness and usable from other text-only agents.

When an image path or URL shows up in the conversation, the skill sends it through ModLens and hands the agent structured evidence about the text, layout and meaning of the picture.

Used ModLens?

No reviews yet

Used it? Write the first review.