modlens
SkillGitHubActiveTypeScript
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). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
Description provenance: Original source
Measured: Oct 20, 2026 · 65 observations
Domains & Uses
- Domains
- Agents, skills and MCP
- Uses
- Agent skills, Code assistants
Installation
git clone https://github.com/liustack/modlens ~/.claude/skills/modlensCheck at the source
Compatibility and prerequisites must be checked in the official documentation.
https://github.com/liustack/modlensClassifications
- Nature
- Tool
Measurement history
Comparable readings are grouped by signal and unit.
Stars
4,341stars · Oct 20, 2026
+102 (+2.4 %)since Oct 14, 2026
Exact values · 7 readings
| Measured | stars | Change |
|---|---|---|
| 4,341 | +24 | |
| 4,317 | +8 | |
| 4,309 | +21 | |
| 4,288 | +16 | |
| 4,272 | +13 | |
| 4,259 | +20 | |
| 4,239 | · |