DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

ModLens

A DeepSeek Harness vision plugin that turns pasted images into structured OCR, layout, and semantic evidence for supported text-only models.

VisionDeveloper Tools
3.9kGitHub Stars115ForksUpdated2026-09-01

Install

No clear install command was found in the current repository evidence.

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
ModLens is an installable DSH plugin and CLI vision bridge. It adds vision-oriented DeepSeek model variants and a native read_image workflow for pasted images, using configurable external vision providers or explicitly enabled reusable local CLI sessions.

Key Capabilities

  • Installs into DeepSeek Harness through the DSH plugin command.
  • Processes pasted images through a native read_image tool workflow.
  • Produces structured image evidence including transcription, layout regions, entities, and relations.
  • Adds DeepSeek-V4-Flash and DeepSeek-V4-Pro ModLens vision model variants.
  • Supports Gemini API, OpenAI-compatible, Anthropic, Antigravity CLI, and Claude CLI vision sources.
  • Supports configurable provider preference, pinned providers, proxy settings, and failover attempts.
  • Provides a modlens CLI for configuration and health checks.

Useful For

  • Reading screenshots, UI layouts, charts, and documents in a text-only DeepSeek session.
  • Extracting OCR and structured visual evidence from pasted images.
  • Connecting an OpenAI-compatible vision endpoint such as a self-hosted gateway or supported third-party provider.
  • Adding image-reading support while retaining a text-model workflow.

Who It Fits

  • DeepSeek Harness users working with text-only DeepSeek or GLM models.
  • Developers and coding-agent users who need OCR or image understanding in chat workflows.
  • Users with existing vision-provider credentials or supported local agent CLI sign-ins.

Documented Limitations

  • Requires Node.js 22.19 or later according to package metadata.
  • Vision processing depends on configuring or accessing an external provider or supported local CLI session.
  • The DSH wrapper is described as covering DeepSeek and GLM text models; their native vision models are excluded.
  • Upstream provider terms, quotas, and credentials remain the user's responsibility.
  • The repository states that it does not accept pull requests.

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 2 runtime, 6 development, 0 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
liustack/modlens
Registry source
Registry curated
Registry classification
Plugin
Source checked
926a6be · 2026-09-06

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
3.9kGitHub stars
Forks
115
Open issues
6
Last commit
2026-09-01
Last release
2026-09-01
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app