Vision & Input
modlens
Gives text-only DeepSeek models plug-in vision: paste a screenshot, get structured evidence.
What it is
A vision bridge for text-only coding agents. Paste an image into the chat and modlens converts it into structured JSON evidence — full transcription, layout regions in reading order, entities and relations — instead of a model’s guess.
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).
Why it matters for design
- UI screenshots become element-by-element walkthroughs the agent can act on.
- Dense charts and data visualizations are read completely: axes, scales, palettes, highlighted regions.
- Paste several references at once and it identifies the shared visual family before describing each one.
What it covers
- Highlights
- Installation
- Usage
- See it work
- Documentation
How to install
modlens
-
Run this in a terminal.
npx -y @deepseek-ai/dsh plugin --profile web add @liustack/modlens@latest -
Restart dsh web so it picks up the plugin.
-
Then describe the design you want. The harness picks up the plugin’s tools.
How to run it with DeepSeek Harness
-
Install the plugin; the model picker gains DeepSeek-V4 variants with modlens vision.
-
Paste a screenshot, mockup or chart straight into the conversation.
-
Ask design questions against the structured evidence instead of re-describing the image.
Every plugin here is free to install and links to its real upstream source.
More in the DeepSeek Harness repo ↗More DeepSeek Harness design plugins
Vision & Input What it does dsh-vision-toolkit Ten vision tools for UI restoration, grounding and pixel-diff verification. 
Vision & Input What it does dsh-ui-spec Turns UI screenshots into implementation-grade specs: tokens, spacing scale, layout grid. 
Vision & Input What it does dsh-media-skills Free eyes and a free paintbrush: paste-image reading plus watermark-free image generation. 
Canvas & Generative UI What it does dsh-openpencil The agent designs on a real, editable vector canvas instead of returning static images. Next step
Design with NEXGERCORE, without the setup
Install this plugin yourself, or run a whole curated design layer around DeepSeek Harness with NEXGERCORE. Bring your own key, own your output.