The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | The most powerful DeepSeek Harness vision plugin, adding vision capabilities to text-only models such as DeepSeek and GLM; paste an image to get structured JSON evidence (OCR, layout, semantics).
ModLens is a vision plugin that lets text-only coding agents analyze images pasted into chat and return structured evidence such as OCR, layout, and semantic information. It is designed for DeepSeek Harness and provides visual input to models that cannot read images directly. The catalogue skill and instruction support using this plugin.
This repository also configures its own agents. See what modlens tells them →
Skill Claude Code
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: ] line, or inside a tag) and you cannot see that image's content, run this skill on it…