DeepSeek Harness Vision Bridge
liustack/modlens · skills
Add OCR, layout analysis, and semantic understanding to text-only coding agents, with structured visual evidence as output.
★ 3,916GitHub stars
41Forks
2026-08-15Last updated
TypeScriptLanguage
MITLicense
Key features
- Updating is the same command again.
- The harness you are talking in right now.
- Paste an image and it reads it.
- No saving to a file and passing a path first.
- The lightest touch on the market.
Install command
dsh plugin --profile web add github:liustack/modlens