dsh-screenshot
Zero-dependency screen capture for DSH: Lightweight — zero deps, zero binaries; Stage & shoot — one-click full screen, window layout, hover-snap capture of occluded windows; Agent self-service — path-only delivery; paths are universal, pair with modlens (optional) for one-call structured evidence.
DSH 轻量截图插件：轻——零依赖零二进制；摆——一键全屏、窗口排版、悬停吸附截取被遮挡窗口；自助——Agent 可自助截屏，传路径不传图，路径通用，接上 modlens（选装）一步读出结构化内容。
How to install
dsh plugin add @paicat1/dsh-screenshot About
dsh-screenshot 独立截图插件，为 DeepSeek Harness（dsh）提供屏幕捕获能力。**不是 modlens 的替代品**——它是从 @liustack/modlens 的 dsh 插件中拆分出来的独立包（该功能上游未采纳，见 liustack/modlens#48），目的是让截图功能**不随 modlens 更新而被覆盖**。 致谢 本插件的截图能力最初是作为 @liustack/modlens（作者 Leon Liu）的 dsh 插件增强实现的。**衷心感谢原作者为 DSH 提供了识图能力**——modlens 让纯文本模型（DeepSeek/GLM）能够"看见"图片，本插件的 modlens_screenshot 工具正是复用 modlens 的识图管线，把"截屏 + 识图"合成一步。截图功能本身从 modlens 中拆分出来独立维护，但识图能力始终归功于 modlens 项目。 能力 **浏览器热键**（在 dsh 网页中）： Ctrl+Alt+S — 区域截图（弹出选择框，鼠标左键在桌面空白处按下开始，拖拽选框，Esc 取消） Ctrl+Shift+Alt+S — 全屏截图（无交互，直接捕获整个虚拟桌面） **Agent 工具**：modlens_screenshot — AI 可自主截屏并识图（若本机装有 modlens CLI） 截图 PNG …
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 5
- mo. downloads
- 1.8K
- Last push
- 2026-09-08
- Created
- 2026-08-16
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh-plugin, screenshot, vision
Related plugins
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-web
zhu1090093659/dsh-web-ui/tree/main/packages/dsh-tool-describe-image
A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.
dsh-vision-router
ysr666/dsh-vision-router
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
dsh-vision-toolkit
Anionex/dsh-vision-toolkit
Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.