dsh-task-capsuleDSH 任务两件套:会话 header 运行任务胶囊(圆点颜色分态、点击跳转对应会话、多任务下拉列表)、任务通知卡(显式按钮跳转、提示音、可选系统通知)。从 dsh-dock 最常用的功能提取精简而成;token 统计交给 DSH 自带会话统计条,不重复做。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wzn16/dsh-task-capsuleDiscover The Best DSH plugins
29754results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-task-capsuleDSH 任务两件套:会话 header 运行任务胶囊(圆点颜色分态、点击跳转对应会话、多任务下拉列表)、任务通知卡(显式按钮跳转、提示音、可选系统通知)。从 dsh-dock 最常用的功能提取精简而成;token 统计交给 DSH 自带会话统计条,不重复做。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wzn16/dsh-task-capsuledsh-task-chimeRing a real system sound when a DeepSeek Harness agent finishes a task OR needs your input: custom sounds, 4 intensity levels, auto escalation, and a settings card in the GUI.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ruazero/dsh-task-chimedsh-task-clarifierTurn one sentence into a precise task brief through a short guided Q&A. · 一句话变成精准任务书:左侧栏任务澄清器,少问几轮、少烧 token。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Sun-0306/dsh-task-clarifierdsh-task-completion任务完成约束自动化插件:监听 AI 回合结束,检测回复是否含 ✅ 任务完成,按「推送许可」开关自动 commit+push 交付物。带 HTTP API(status/config)与 agent 工具(task_completion_status / task_completion_config)。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EIGHTfs/dsh-task-completiondsh-task-completion-beepPlay five short beeps in the browser when a DSH web task completes.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:flyhigao/dsh-task-completion-beepdsh-task-consoleDSH client plugin — flip to the back of the page for a floating glass task console: live background jobs, subagents, session overview and workspace of the current session, with mouse-draggable and mouse-resizable cards (bottom-right handle, size persisted per card). Maximizing a card unrolls its controls onto the card's own canvas, where every control is a draggable, editable item and the board card stays a live thumbnail whose control order follows that arrangement; built-in cards open as a fullscreen view. The top-right card conversation calls a temporary agent session to refactor each card's style and internal controls from natural language, and any conversation can author cards via [taskcard] blocks (text/heading/note/stats/progress/trend/kv/links/chips/checklist/counter/button/table/code/toggle/countdown/bars/image/embed). Embedded web apps can be marked 受控 and routed through the bundled local page bridge (bridge/server.mjs), which injects an agent into the page so the workbench — and the agent — can click, type, scroll and read inside it through [page] action blocks; the app height is dragged on its bottom edge, accurate on the zoomed canvas too. Cards can be published as copies onto a fullscreen infinite canvas with named boards, share strings and a zero-dependency WebSocket relay for multi-user editing, and a right-hand dock renders the project's archify architecture diagram (embedded, sandboxed, resizable).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:He2way/dsh-task-consoledsh-task-controlDeepSeek Harness 插件:pip/GitHub 下载卡死一键急停 + 下载进度检测 + 卡死识别 + 隐形追加条件。Emergency stop for stuck downloads, download progress, stuck detection and invisible append-condition for DSH.
dsh-task-detailsTask details sidebar for DeepSeek Harness: a 'View task details' button under every finished turn opens a resizable right-sidebar panel listing the task's input files, intermediate artifacts, output files, tools and skills used, languages, and model usage.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zzt0818/dsh-task-detailsdsh-task-digestDeepSeek Harness plugin: a nightly per-task token, cost, and result digest for the previous day's Sessions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:nwasvsad/dsh-task-digestdsh-task-dispatcherTask dispatcher for DeepSeek Harness: use TickTick (滴答清单) 5️⃣AI as the daily task dispatcher — a cordis timer pulls today's due tasks each morning, writes them to the workspace task file, and notifies (flomo + macOS) so the agent works through them and writes results back to TickTick
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhengjy01/dsh-task-dispatcherdsh-task-effortAuto-adjust model reasoning effort per task: off/low/high/max with task classification, peak-pricing-period capping, countdown notices, and in-turn error escalation
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhangzhenwen1/dsh-task-effortdsh-task-estimate任务时间估算
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-task-estimatedsh-task-feedbackLive session status on the browser tab favicon — green idle, blue running, red when waiting for you.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Pudge1996/dsh-task-feedbackdsh-task-ganttAgent-team task Gantt chart for the DSH sidebar — teammates on the y-axis, real session time on the x-axis, task title and summary in every bar. · DSH 侧边栏的 agent team 任务甘特图。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xx529/dsh-task-ganttdsh-task-guardDeepSeek Harness plugin that keeps a todo_write plan advancing with the agent's work: an advisory notice when a whole-list write leaves pending work with no active task, and a stale-plan notice after a few tool calls.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MCviseron/dsh-task-guarddsh-task-mascotmetsh · Task Mascot — 真跟着 Agent 每一步工具调用在动。A DeepSeek Harness Web plugin whose mascot acts out every live tool call (read / write / edit / search / run / plan / sub-agent / wait / error) with step cards in chat. Swappable character packs (大肥鱼, Claude娘).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sherconan/dsh-task-mascotdsh-task-memoryDeepSeek Harness plugin: workspace-scoped task memory. Reusable procedures are stored one card per task, the card catalog is the index, and card bodies load on demand.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xjhao-heim/dsh-task-memorydsh-task-modelsEnhanced DSH subagent tools with per-call model and reasoning-effort selection
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:TTTPOB/dsh-task-modelsdsh-task-notifyTask-completion system notifications for DeepSeek Harness — macOS Notification Center, Windows Toast, and mobile push via Bark / ntfy / ServerChan / webhook
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DeepseekHarnessPlugins/Notificationdsh-task-notifyDSH会话停止/阻塞时提醒:右上角 toast + 提示音(WebAudio)+ 系统通知(Windows/macOS 通知中心,页面失焦时弹)。
dsh-task-notifyDeepSeek Harness plugin: pop a desktop toast (bottom-right, like opencode) when a task / agent run completes or fails.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:weijianguizhou/dsh-task-notifydsh-task-notifyNative OS system notification when DeepSeek Harness finishes a task (goal completion or agent turn end): Windows toast, macOS Notification Center, Linux libnotify.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YuMo226/dsh-task-notifydsh-task-orchestratorTODO-first orchestration with isolated workers, a two-lane queue, and saved model/reasoning choices for each role.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add https://github.com/hasan-aghayev/dsh-task-orchestrator/releases/download/v1.2.1/dsh-task-orchestrator-1.2.1.tgzdsh-task-orderTask-order discipline: opening checkup, check-before-build triage, ledger freshness inspection, handoff pickup — order before action. 任务顺序闸:开场体检、先查后造三查、台账活性巡检、交接捡活。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xushilianzhuren/dsh-task-orderUse 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.