loudMore/dsh-drop-to-path
dsh-drop-to-path is a tool for DeepSeek Harness. DSH plugin: images and files straight to text-only models — images keep the native attachment experience, PDF/Office/archives/video/audio show as square chips in the attachment rail, auto-converted to workspace paths on send; pairs with dsh-vision-toolkit for paste-to-view. A DSH plugin that delivers images AND files to text-only models as workspace paths: images keep the native attachment UI, other files show as square chips in the rail, paths append on send — pairs with dsh-vision-toolkit.
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Solves a real pain point for text-only models in DSH, but lacks visible tests or CI to confirm engineering rigor.
README shows a clear mermaid architecture diagram and explicit file-type/limit tables, but no tests, CI badges, or dev setup docs are visible, so engineering rigor cannot be verified.
No download-and-execute, plaintext secrets, or excessive permissions are described; files are copied to a local workspace/.drops/ directory, but the install command references a local path and no security details are given, so a neutral score applies.
Directly addresses a documented DSH preflight rejection ('The current model does not support images') and the manual save-then-type-path workflow, with paste/drag support and pairing with dsh-vision-toolkit.
Last updated 2026-08-14, not archived, MIT licensed, and 12 stars indicate an actively maintained but small project.
README includes bilingual links, demo GIFs, a mermaid flow diagram, supported file-type tables with size limits, a comparison with similar plugins, and pairing instructions, though the install command uses a placeholder local path.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
dsh plugin --profile web add /path/to/dsh-drop-to-pathThis command was extracted from an explicit README install reference and is display-only; the DSH host will not execute it automatically.
PROJECT TOPICS
VALIDATION LADDER
FAQ
DSH plugin: images and files straight to text-only models — images keep the native attachment experience, PDF/Office/archives/video/audio show as square chips in the attachment rail, auto-converted to workspace paths on
dsh-drop-to-path has 12 stars and 2 forks on GitHub, last updated 2026-08-14.
dsh-drop-to-path is distributed under the MIT license.
dsh-drop-to-path is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:attachments、drag-and-drop、file-upload、vision。
liustack
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). | The strongest vision add-on plugin for DeepSeek Harness, adding vision capability to text-only models like DeepSeek and GLM, paste an image and get structured JSON evidence (OCR, layout, semantics).
tong-io
TongFlow — Multimodal GenAI Studio
Anionex
[dsh] A more powerful visual toolkit for text-only models: one-line install and use, paste images for direct recognition, multi-image Q&A, screenshot-to-frontend UI restoration, and more｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
DDDMUC
Free web search provider for DeepSeek Harness - DuckDuckGo backend, no API key needed
anysearch-team
AnySearch web search provider and advanced search tools for DeepSeek Harness (DSH)
omdsh-dev
Connect DSH to your database for conversational data analysis and actionable business insights.