dsh-plugin-appshot
Codex Appshots for DSH: capture the frontmost active window via global shortcut and seamlessly mount it into the composer for agent queries.
DSH 版 Codex Appshots：全局快捷键精准捕获当前工作窗口，零摩擦挂载至 Composer 作为上下文向 Agent 提问。
How to install
dsh plugin add dsh-plugin-appshot About
dsh-plugin-appshot macOS 全局快捷键「一键截图**当前窗口**」，自动作为图片上下文挂入 DeepSeek Harness (DSH) 的 Composer —— 把当前工作窗口零摩擦交给 Agent。 English · 中文 安装（一条命令） sh dsh plugin --profile web add dsh-plugin-appshot npm 包为**预构建产物**：宿主插件 + 客户端模块 + Native Agent 已全部打包，**无需本地编译、无需构建授权**； 安装后**重启 dsh**，启动日志出现 [dsh-plugin-appshot] plugin applied successfully、native agent ready 即加载成功； 首次触发截图时 macOS 会弹出授权引导，需授予**屏幕录制**与**辅助功能**权限（见权限）。 从源码安装（开发/贡献者）：在插件目录 pnpm install && pnpm build && pnpm build:native，然后在插件**父目录**执行 dsh plugin --profile <name> add ./dsh-plugin-appshot（dsh plugin add 的相对路径锚定调用目录）。 这是什么 DSH 版的「Codex Appshots」：为 De…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 5
- mo. downloads
- 0
- Last push
- 2026-09-18
- Created
- 2026-08-16
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- dsh-plugin
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.