Windows-only DSH screen sampling with saved screenshots and optional automatic follow-ups.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-10-31
License
Not specified by the author
01What can it help you accomplish?
Capture screen changes for a DSH conversation
Screenshot paths and foreground-window titles
Windows DSH users who want screen-aware companionship
02How to install into DeepSeek Harness
Prerequisites
- Windows; the README names Pillow and Win32 foreground-window titles.
Installation steps
- 01
Run `dsh plugin --profile web add github:pairun325/dsh-whale-sense`.
$ dsh plugin --profile web add github:pairun325/dsh-whale-sense
Verify the integration
- Call `sense_state()` to inspect helper status, configuration and recent errors.
03DSH integration and capability boundaries
DSH web-profile plugin with a Windows screenshot helper.
Screen sampling and manual capture
A Python helper compares sampled thumbnails and saves changed frames; sense_snap returns an image path and foreground-window title.
Screenshots are saved under storages/whale-sense/frames/.
04Who is it for? When not to use it?
Good for
- Windows DSH users who want screen-aware companionship
Not for
- Automatic watching is off by default: each spoken response starts a model turn and consumes tokens.
05Compatibility, maintenance and safety notes
- Automatic watching is off by default: each spoken response starts a model turn and consumes tokens.
- The plugin performs no OCR or image understanding; the model must use read_image.
No license statement appears in the fetched README.
06Frequently asked questions
How do I install Whale Sense in DSH?
Run `dsh plugin --profile web add github:pairun325/dsh-whale-sense` on Windows.
Does DSH automatically watch my screen after installation?
Automatic watching is off by default because each comment consumes a model turn and tokens. Manual capture is available.
Does this DSH plugin recognize text in screenshots?
No. It does not perform OCR or understand the image; the model uses read_image.
07Related DSH workflows
modlens
by liustack
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
agent-vision-toolkit
by anionex
Vision toolkit and skills that give text-only LLMs eyes — multi-image understanding, image Q&A, OCR, frontend UI restoration and GUI automation, with optional agent integration.
dsh-vision-router
by ysr666
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
dsh-image-gen
by shanliuling
Adds in-chat multimodal image generation via a `generate_image` tool with multi-provider support (Gemini/OpenAI/Seedream), interactive preview, copy/download, and session-attached results.
08Data and sources
dsh plugin --profile web add github:pairun325/dsh-whale-sense
只支持 Windows（Pillow + Win32 前台窗口标题）。
通过 `agent.followup()` 把「主人屏幕变了 + 截图路径」塞回会话
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-10-31. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.