AI for Developers
Agent skill (SKILL.md) Open source MIT 4.8k

modlens

A vision plugin that lets text-only coding agents read images.

Install

For this project
$ npx skills add liustack/modlens -a claude-code
For every project
$ npx skills add liustack/modlens -a claude-code -g

Or copy the skill folder into .claude/skills/ (project) or ~/.claude/skills/ (all projects).

For this project
$ npx skills add liustack/modlens -a codex
For every project
$ npx skills add liustack/modlens -a codex -g

Or copy the skill folder into .agents/skills/ (project) or ~/.agents/skills/ (all projects).

For this project
$ npx skills add liustack/modlens -a opencode
For every project
$ npx skills add liustack/modlens -a opencode -g

Or copy the skill folder into .agents/skills/ (project) or ~/.config/opencode/skills/ (all projects).

For this project
$ npx skills add liustack/modlens -a antigravity
For every project
$ npx skills add liustack/modlens -a antigravity -g

Or copy the skill folder into .agents/skills/ (project) or ~/.gemini/config/skills/ (all projects).

For this project
$ npx skills add liustack/modlens -a kimi-code-cli
For every project
$ npx skills add liustack/modlens -a kimi-code-cli -g

Or copy the skill folder into .agents/skills/ (project) or ~/.agents/skills/ (all projects).

Run npx -y skills add liustack/modlens --skill modlens --global.

When to use

Use it when your agent runs on a text-only model and you want it to read screenshots, mockups or error dialogs.

ModLens is a vision plugin for text-only coding agents. DeepSeek's flagship chat models and GLM-5.3 can't read images, and ModLens gives them sight. You paste an image straight into the chat, with no need to save it to a file and pass a path, and the agent gets back structured JSON covering OCR, layout and semantics.

It targets DeepSeek Harness first, where one command adds it, and works with any text-only coding agent after that. The README links to configuration, troubleshooting and security pages.

Related skills

All skills