Deliver images and files straight to text-only models — PDF/Office/archives/videos become attachment blocks and auto-convert to workspace paths on send.
I use a text-only model (deepseek) in DeepSeek Harness and frequently need to send screenshots to the agent.
dsh-drop-to-path is a DeepSeek Harness ecosystem resource maintained by loudMore. Deliver images and files straight to text-only models — PDF/Office/archives/videos become attachment blocks and auto-convert to workspace paths on send.
Source code and usage instructions are available at https://github.com/loudMore/dsh-drop-to-path. Follow the repository README for the correct setup steps.
dsh-drop-to-path is a community open-source project released under the MIT license. Review the repository license and documentation before use.
Tools & Capabilities
Give text-only coding agents eyes: image Q&A, long-screenshot OCR, frontend UI restoration and GUI automation, as a vision toolkit plus a skill, with optional drop-in support for Codex, Claude Code and more.
View details → 
Anionex
Tools & Capabilities
An open-source Smartisan-style notes app: self-hostable with one click via Docker, supports skill invocation and dsh plugin, even generates WeChat-official-account format output.
View details → 
zhaoolee
Tools & Capabilities
Detect and download video and audio from pages inside DeepSeek Harness.
View details → 
zimai233