ModLens
A vision bridge: turns pasted images into structured OCR, layout and semantic evidence fed back to the text model; requires your own vision-model API key.
This command pulls code from a third-party repo and runs it on your machine. Check the source and permissions first; don't test on production.
- One-line function
- A vision bridge: turns pasted images into structured OCR, layout and semantic evidence fed back to the text model; requires your own vision-model API key.
- Use case
- You want more controllable vision and are willing to configure a vision-model key rather than use a key-free channel.
- Source repo
- See the repo
- Maintenance status
- Community-maintained
- Supported host version
- Unverified
- Permissions needed
- Per the repo's declaration; read its permission notes before installing
- Our verification status
- Not yet tested
- Source of info
- Capability description from community plugin directory; not a verified conclusion of this site.
- Last verified
- 2026-11-14
Install (distribute, don’t download)
dsh plugin --profile web add github:modlensCommand from community sources, not reproduced on this site; verify the package name and version on the original repo before running.
We don't host or mirror any installer; there are no download links on the page. Files always come from the original repo.
How to verify after install
After installing, run one test in the described scenario and record whether it delivers and any anomalies.
Known issues
Community descriptions are not the same as this site's verified conclusions; judge before installing.
Uninstall & rollback
Disable and remove the plugin, restart, confirm the session is back to normal; back up profile config first.