dsh-tool-statsEvery tool call is counted, and the ones that never fire are named so you can remove them.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hj01857655/dsh-tool-statsDiscover The Best DSH plugins
30657results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-tool-statsEvery tool call is counted, and the ones that never fire are named so you can remove them.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hj01857655/dsh-tool-statsdsh-tool-subagent-batchRolling-window batch orchestration for DeepSeek Harness subagents with synchronous and asynchronous modes, user-owned concurrency, and per-task acceptance reports.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YixiangTang/dsh-tool-subagent-batchdsh-tool-subtitleSubtitle toolkit for DeepSeek Harness: transcribe audio to timed cues, convert between SRT/VTT/ASS, and shift, merge or validate a timeline.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yuehancn/dsh-tool-subtitledsh-tool-summaryDSH Web plugin: collapse each turn's tool calls into one group with a summary card, truncated output, and read-only filtering.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:statem-li/dsh-tool-summarydsh-tool-surface-proofOffline content-addressed DSH model-visible tool surface conformance evidence
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dongsheng123132/dsh-tool-surface-proofdsh-tool-sysinfoSystem information tool for DeepSeek Harness: OS, CPU, memory, uptime, and network facts the agent can read when diagnosing the local environment
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:shiyi-0x7f/dsh-tool-sysinfodsh-tool-tddTDD test runner tool for DeepSeek Harness: run test commands, parse structured failures (Jest/Vitest/Pytest/Go/Rust/TAP/tsc), and drive a red-green loop
dsh-tool-terminal-searchterminal_search tool for dsh: locate lines in large persistent-terminal scrollback by regular expression, composed over the public terminal read seam.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ystyle/dsh-tool-terminal-searchdsh-tool-ths同花顺 (Tonghuashun / iFinD) 行情与数据连接插件 for DeepSeek Harness —— public 免登录行情通道 + 官方 iFinD HTTP API 通道,注册 ths_* 工具族
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Xiaobai01/dsh-tool-thsdsh-tool-visibilityControl which tool schemas are injected into the DeepSeek Harness model context. Registers a tool_visibility manager tool AND a settings-page UI (Settings → 工具注入控制) with per-tool toggles; backed by the framework-native tools.restrict filter and persisted to a JSON state file.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:rayfalling/dsh-tool-visibilitydsh-tool-visionDeepSeek Harness 外置视觉模型插件:inspect_image 把本地图片或 http(s) 图片 URL 发给任意 OpenAI 兼容端点,视觉模型看图的文字回答直接带回对话;附 Web UI 设置栏。
dsh-tool-visionModel-facing image_describe (识图) tool for DeepSeek Harness: describe a local image through the DashScope OpenAI-compatible API (qwen3.7-flash). Bring your own DASHSCOPE_API_KEY.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wanshichenguang/dsh-tool-visiondsh-tool-web-searchPersistent DSH model tools for Bing and SearXNG web search plus bounded webpage fetching.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gao-gao-zai/dsh-tool-web-searchdsh-tool-workspaceDeepSeek Harness 工作区管理工具集:查看、创建注册、重命名、删除工作区记录(纯注册,不触碰磁盘目录);破坏性操作(删除注册、改注册路径)走用户审批 fail-closed。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wangxing-git/dsh-tool-workspacedsh-tool-zgDeepSeek Harness 原生 zvec-grep (zg) 代码语义搜索工具插件,支持按预设动态过滤与极简低 Token 交互
dsh-toolbeltEight DeepSeek Harness plugins: persona, language guard, vision fallback, python workdir guard, windows encoding guard, cross-agent memory, image generation, and skill shell injection.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:cking000bigdemon/dsh-toolbeltdsh-toolboxdsh 增强工具集:会话管理(删除/移动/复制/重设工作区根)、子目录管理、预设编辑、编辑器增强、自研搜索、官方搜索开关
dsh-toolboxDSH 工具箱插件:侧边栏独立页面 + /toolbox 命令 + 配置驱动的 agent 确定性工具。约 35 个纯本地工具(文本/编码/数据/安全/提取/转换/网络/效率),数据不出机器。参考 devtoolbox.online 设计。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jean3690/dsh-toolboxdsh-toolboxDSH 工具箱插件:股票盯盘(东方财富行情)+ 本地 txt 小说阅读器(UTF-8/GBK 自动识别、进度保存)
dsh-toolbox-bundleDSH plugin bundle: one command installs four deterministic, offline plugins (46 tools) covering JSON/YAML/CSV/diff/regex/encoding chores plus JVM, Python and Windows production diagnostics. Ships no code of its own — it inserts the four bundle rows, and the four plugins stay independently versioned.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ax2/dsh-toolbox-bundledsh-toolcall-stream-repairRepairs malformed streaming tool-call deltas from OpenAI-compatible gateways in DeepSeek Harness, before they assemble into an undispatchable call
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:udsy19/dsh-toolcall-stream-repairdsh-toolkitDSH bundle:图片生成面板(generate_image 工具 + 侧边栏图库/提示词库)与 Token 用量、成本、活跃度面板。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dongshan1999/dsh-toolkitdsh-toolkitDeepSeek Harness 开发者工具箱插件:侧边栏入口 + 底部终端面板,可开始/终止进程、手工输入命令,并浏览 AI 输出结果。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lispking/dsh-toolkitdsh-toolkitDSH 小功能合集:QQ 远程驾驶、跨会话提问、界面暂停按钮、重启与重启后自动续跑、贵时段纪律按时间注入
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MSSZSD3925/dsh-toolkitUse a feature keyword or category, then sort by recent updates or GitHub stars.
Read the description, AI analysis and original README to understand what a plugin does.
Review compatibility, dependency ranges and instructions, then copy the available install command.
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.
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.