Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract.
Install
npx skills add liustack/modlens --skill modlensnpx skills add liustack/modlens --skill modlens -a claude-code -gnpx skills add liustack/modlens --skill modlens -a codex -ggemini skills install https://github.com/liustack/modlens.git --path skills/modlensgh skill install liustack/modlens modlensgit clone --depth 1 https://github.com/liustack/modlens /tmp/liustack__modlens
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/liustack__modlens/skills/modlens ~/.claude/skills/modlens # Claude Code
cp -R /tmp/liustack__modlens/skills/modlens ~/.agents/skills/modlens # Codex, Cursor, Gemini CLI, Copilot, OpenCode