实时扫描最新社区关于 DeepSeek Harness 发布的插件

Report DeepSeek Harness agent activity (working / blocked / idle) to the herdr pane hosting this dsh process

Codex-style conversation turn timeline tree and history overview on the left border of chat messages in DSH Web UI

DeepSeek Harness homepage-style background skin: WebGL fluid, dot grid and digital whale. Dark and light variants included.

DSH plugin: honcho long-term memory tools (memory_store / memory_search) over a self-hosted Honcho v3 backend

Runtime hot-swap for DeepSeek Harness: hot enable/disable/restart Cordis plugins and auto hot-mount bundles from the Web GUI — no dsh restart.

Environment housekeeper for DeepSeek Harness: toolchain inventory, agent scratch/cache scan with safe one-click cleanup, and the machine rules file (AGENTS.md) view/edit - all in the Web GUI settings. Zero runtime dependencies.

DSH plugin: structured HTTP request tool (http_request) built on the Node built-in fetch.

A HUD status panel for DSH web: git status, MCP servers, skills, model and token usage in a floating side panel

HP / MP / TIME status HUD for the DeepSeek Harness sidebar (formal plugin bundle)

中文文本人味化 bundle 插件：强制深层改写工作流（十维叙事审计 + 功能路径 + 15 层分布）+ 内容忠实守卫。编辑辅助，非 AI 检测器。

DSH 视频创作技能插件：注册 HyperFrames by HeyGen 官方移植技能五件套（hyperframes / hyperframes-cli / hyperframes-registry / website-to-hyperframes / gsap），安装即用。

ADHD 友好输出风格（移植自 i-have-adhd）

DeepSeek Harness bundle: inject the user's IDE context (open editors + current selection) into each turn, via the Claude Code IDE WebSocket bridge (IntelliJ IDEA & VS Code).

IDE-style workspace switcher sidebar for DSH (DeepSeek Harness): floating workspace dropdown, session filtering, done/pending status lights, workspace & session search, and workspace rename/delete/archive/add.

Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。

Let image-incapable LLM models receive image messages in DeepSeek Harness (dsh): replace image blocks with text placeholders + local paths, then describe via a vision script (qwen)

Image-generation tool plugin for DeepSeek Harness: qwen-image-3.0 (Aliyun MaaS) and doubao-seedream (Volcano Ark) providers

GPT Image 2 generation with progressive Codex-style previews for DeepSeek Harness

Let the model render an image into the DSH web chat flow (QQ/WeChat style) via a show_image tool: the message content keeps only the path text, the image never enters model context, and the browser shows the picture inline, scrollable with history.

DeepSeek Harness plugin: let text-only models (deepseek-v4-flash, ...) receive image messages as 'Saved attachments: <path>' text at dispatch, so vision skills (claude-vision-skill's vision.js) can read the durable files

Give DeepSeek Harness agents the ability to read images directly: a model-facing read_image tool that answers questions about an image through any OpenAI-compatible vision endpoint.

DSH web plugin: set a background image and adapt the theme colors (background + text + brand + borders) to the image palette.

DSH model tool that converts images to text (OCR + description) via configurable vision API providers, with image intake support for text-only models.

image_gen and image_vision model tools for the DeepSeek Harness, powered by the ChatGPT subscription (no API key).