# modlens — DeepSeek Harness plugin install manifest

> Generated: 2026-09-13 19:10 · Source: https://deepseekmodel.com/plugins

## Overview

A vision plugin that gives text-only models sight: paste an image and get structured JSON with OCR, layout and semantics, handy for screenshot debugging and frontend work.

## What it does

- Pasted images become temp file paths in the composer, read by the read image tool
- Switch to a (modlens vision) model variant to keep thumbnails visible, closer to Codex App
- Variants are auto-generated per provider route; only metadata-confirmed text-only models are wrapped

## Plugin info

| Category | Maintainer | GitHub stars | License | Primary language | Last push |
| --- | --- | --- | --- | --- | --- |
| Tools & Capabilities | liustack | 3,930 | MIT | TypeScript | 2026-09-07 |

## Install

```bash
dsh plugin add github:liustack/modlens
```

## Steps

1. Install and start DeepSeek Harness (DSH, MIT-licensed open-source agent runtime) — `npx @deepseek-ai/dsh web`
2. Run the command above; the CLI resolves the plugin and verifies its source
3. Confirm with dsh plugins list; restart Harness if needed

> To pin a revision, append #commit to the repository spec.

## Audit before installing

Plugins run with your dsh process permissions and may execute code during installation. Read the repository source and license first, check for destructive commands or excessive access, and pin a commit hash for reproducible installs. This manifest is compiled by DeepseekModel from a public plugin catalog for reference only and does not vouch for third-party plugins.

---

- Repository: https://github.com/liustack/modlens
- Plugin page: https://deepseekmodel.com/plugin-detail?id=modlens
- Source: https://deepseek-harness-plugin.com/zh-CN/plugins/ · Generated 2026-09-13