dsh-usage-statsDeepSeek Harness 消耗统计插件:设置页「消耗统计」展示 Token 用量 KPI、半年活跃贡献热力图、按模型堆叠柱状图与模型环形图(Host 预热扫描 + RPC,只读重算会话日志)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AlfredChaos/dsh-usage-statsDiscover The Best DSH plugins
5832results
Find task management, document processing and everyday workflow automation plugins.
dsh-usage-statsDeepSeek Harness 消耗统计插件:设置页「消耗统计」展示 Token 用量 KPI、半年活跃贡献热力图、按模型堆叠柱状图与模型环形图(Host 预热扫描 + RPC,只读重算会话日志)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AlfredChaos/dsh-usage-statsdsh-usage-statsDeepSeek Harness plugin: aggregate token usage + estimated cost across all sessions, by day/week/model/workspace/session.
dsh-usage-statsDeepSeek Harness Web 插件:侧边栏「使用统计」按钮 + zcode 风格用量页(按天/按模型的 tokens、会话、消息、活跃热力图)。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Triple3h/dsh-usage-statsdsh-usage-statsToken usage statistics for the DeepSeek Harness web UI: a sidebar-footer entry above Settings with time filters (today / 24h / 7d / 30d) and a durable localStorage ledger that survives session deletion.
dsh-user-addonsDSH user addons: file drop-upload, archived-session manager, model/token usage dashboard (auto-loads with the web profile)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Yur0918/dsh-user-addonsdsh-user-managerDeepSeek Harness (dsh) plugin: user management (database or LDAP) plus per-user session isolation. Adds a login gate, HTTP-level authorization of /api methods, and an admin user console.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:awol2005ex3/dsh-user-managerdsh-user-message-jumpDSH Web 客户端插件:在会话左侧显示用户消息快速跳转竖带(类 Codex 会话目录)。
dsh-user-mirrorLet the AI know you. 让模型主动记下你的判断依据(原则/红线/工作方式),跨会话复用 —— 有容量、会遗忘、每条都说得出为什么记。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:webkubor/dsh-mirrordsh-v-token-insightV Token Insight · Token 洞察 —— DSH Web 会话 token 统计插件:第三页签(KPI/图表/每轮明细)+ 回复尾部轻量消耗显示 + 跨会话 Token统计总览(侧栏座位入口,全会话 KPI/工作区/会话/时间/模型维度 + 本地逐步账本)+ 按可维护价目表的费用折算
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:victor10035445/dsh-v-token-insightdsh-vaultDeepSeek Harness plugin: persist every conversation and log inside the workspace folder so copying that folder to a new machine restores all sessions (including the workspace name)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:XiaoWind/dsh-vaultdsh-verifyDSH 收尾裁决面插件:任务收尾 claims 清单交给机器裁决(build/api/file/manual),被证据反驳的 claim 自动记入失败样本库
dsh-verify-gateEngineering verify gate for DeepSeek Harness: configured commands are authority; dirty receipts block conclude.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:blueWhalei/dsh-verify-gatedsh-verify-judgeGoal-completion verification gate for DeepSeek Harness: intercept update_goal(complete), run workspace verification commands, and only let the goal close when they pass
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zriyox/dsh-verify-judgedsh-verify-refluxThree-plane probabilistic verifier for DeepSeek Harness: session-model scoring with tiered logprob/sample/template judges, seeded tournament best-of-N, and layered context reflux.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zouyuanqing/dsh-verify-refluxdsh-vibe-modeomp-style vibe mode for DeepSeek Harness: the session becomes a read-only director that drives persistent fast/good worker subagents
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:inrainbws/dsh-vibe-modedsh-vibegapSelf-contained vocabulary flashcards for DeepSeek Harness web sessions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ktao732084-arch/dsh-vibegapdsh-vim-scrollDeepSeek Harness plugin: vim-style conversation paging in the web UI (d / u / gg / Shift+G).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:orzyyyy/dsh-vim-scrolldsh-visionGlobal upload + configurable vision recognition for DeepSeek Harness (DSH): a composer upload button in every session, automatic image recognition with a user-selected vision model, and fallback chain support.
dsh-visionDSH Computer Use (vision + desktop control, auto-detects Windows native or WSL): see the Windows screen through the agent vision channel, drive mouse/keyboard with a Codex-style blue overlay (Esc to abort), plus a composer status pill.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zzy6-a/vision-usedsh-vision-androidVision + Android UI automation plugin for DeepSeek Harness: gpt-5.6-luna screenshot understanding and real-tap mobile app testing via adb
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:superclaude1/dsh-vision-androiddsh-vision-benchVision 台架:会话区调试/上位机点表(按段添加地址),共享任务与时间线,并安装「台架模式」Agent 预设。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xingyingyuzhui/dsh-vision-benchdsh-vision-guardTransparent image guard + vision analysis for DeepSeek Harness: text-only models read pasted images without the 400 session deadlock.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:good-boy4069/dsh-vision-guarddsh-vision-resident常驻视觉服务:直连视觉模型(默认 opencode-go/minimax-m3,回退 zai-coding-cn/glm-4.6v)。describe_image / subagent_vision 工具 + 粘贴图片自动转译(llm/stream 钩子)+ 输入框视觉状态小胶囊与详情页(活动日志:指令/思考过程/输出)。零子代理、零 agent 上下文开销,按会话记忆窗支持视觉追问与验收。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AnnanRen/dsh-vision-residentdsh-vision-subagentVision for text-only DeepSeek Harness agents: delegate image reading to a one-shot subagent on a configurable vision route (MiniMax / Kimi / any OpenAI-compatible provider), keeping image bytes and the vision model's context out of the main session.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ruby1304/dsh-vision-subagentUse 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.