Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
Editor: a CodeMirror 6 text/code editor tab type for the vn-harness right bar (dsh-rightbar). Opens text files editable instead of in the read-only preview - Markdown included, with a Preview/Edit toggle between the editor and the rendered view - starts a blank document from the tab strip's + control, names and creates new files through the shared dsh-modal dialog, and saves through an authenticated plugin route. The editor follows the app's light/dark theme, and the rendered Markdown page resets what the preview's plain-text scrollport imposes (its hard-break whitespace and mono font). Alpha.
Interface extensions · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:vecnode/vn-harness#e3d0a4205c684d51302acd69490a7c83eb67b1ab&path:packages/dsh-editor
Editor selection focus awareness for DeepSeek Harness: captures the VS Code selection (path + line range, never file text) over a paired WebSocket channel and surfaces it to the agent as durable plugin-attributed ambient context; ships pairing approval UI, a focus chip with a privacy toggle, and device management.
Effort bars for DeepSeek Harness — click signal-style sticks next to the model button to switch the reasoning effort instantly; the model menu opens straight to the searchable list.
Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:imdeniil/dsh-effort-bars
DSH plugin: context-aware per-step reasoning-effort routing. Classifies each step (trivial/standard/engineering/hard) from the task brief and live session evidence, escalates on tool errors, stabilizes with hysteresis, clamps to the target model's advertised efforts, and injects an 'Auto' mask into the native model selector. Ships a settings card that fills default reasoningEfforts for hand-declared llm-pi-ai custom models with per-model gateway wire-value mapping.
Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:neo805/dsh-effort-router
科幻推理等级滑条:把推理档位做成一条能量滑条,附加 Ultra 档、闪电编排模式与子代理 tok/s 读数 / A sci-fi reasoning-effort slider for DeepSeek Harness (DSH), with an Ultra level, a lightning orchestration mode and a live subagent tok/s readout
Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yuhub233/dsh-effort-slider
DeepSeek Harness 推理档位皮肤:把 @hytime/dsh-thinking-effort 的推理等级控件重绘成蓝紫渐变、带星点与流光的档位条。 / A skin for the DSH reasoning-tier control: a blue→violet pill with a starfield and a sheen sweep.
Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LoveIrishCoffee/dsh-effort-ultra-skin
Deterministic network egress gate for DeepSeek Harness: web fetches and searches are checked against a destination allowlist before they run — content scanning guards what agents read, this guards where data may flow
Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhengqiuyang/dsh-egress-gate
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-electrical-safety
Find the right plugin, then get started
Search by task
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
Check and install
Review compatibility, dependency ranges and instructions, then copy the available install command.
Questions about DSH Hub
What is DSH Hub?
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
Does inclusion mean a plugin is tested and compatible?
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
How do I install a plugin?
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.