Discover The Best DSH plugins
7551results
Explore agent orchestration, multi-agent collaboration and task execution plugins.
dsh-proxy-router订阅链接 → 本地代理内核 → 直连优先、直连失败自动切代理；内核自动探测/自动下载，用户只需填订阅地址。 | Subscription link to a local core: direct-first fetching with automatic proxy fallback; the core is auto-detected or auto-downloaded, so the subscription link is the only input.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Lequait/dsh-proxy-routerdsh-proxy-switchDSH 网络代理开关：直连失败自动回退到 HTTP/SOCKS5 代理，设置面板可配置代理地址
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sg88/dsh-proxy-switchdsh-proxy-switcherHot-switch the outbound proxy of a running DeepSeek Harness (dsh): direct / system-env / custom proxy, multiple saved proxies, switchable from the dsh settings page with no restart.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JinSuperOfficial/dsh-proxy-switcherdsh-pure-chatPure chat mode for DeepSeek Harness: hide every global tool so the agent only talks. Toggle per session with /pure-chat on|off.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kiryuOvO/dsh-pure-chatdsh-pushPush DeepSeek Harness agent lifecycle notifications to configurable channels
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kiim-wong/dsh-pushdsh-pwsh-progress对话流实时任务进度：后台任务（pwsh/bash/subagent 等 run_in_background）显示状态、耗时、进度条、预计剩余时间与停止按钮；非消费式 jobs.get 跟踪，模型 job_output 不受影响。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sssueason/dsh-pwsh-progressdsh-python-developmentSQL 优化模式：EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents（38k★ MIT）启发。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-python-developmentdsh-qboson-ising-solverQBoson Kaiwu/SPQC Ising Matrix solver plugin for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DYF-zs/dsh-qboson-ising-solverdsh-qianyuanConnect DeepSeek Harness to the QianYuan MCP server (shared pitfall/result records and capability lookup for agents).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qianyuan-ltd/dsh-qianyuandsh-qingagentDeepSeek Harness × 青简写作桥：QingML 起草工具与右侧宣纸预览。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:void2anything/dsh-qingagentdsh-qq-bot把 QQ 接到 DSH Agent 的插件：通过 NapCat 等 OneBot 11 实现收发消息，每个 QQ 会话对应一个 DSH Agent。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:arrow1031/dsh-qq-botdsh-qq-botQQ Bot integration for DeepSeek Harness: a model-facing qq_send_message tool plus optional inbound WebSocket message driving
dsh-qq-botBridge QQ official bot private messages (C2C) into DeepSeek Harness (dsh) agent sessions
dsh-qq-botDeepSeek Harness plugin bridging QQ official Bot API (QQ 开放平台) to dsh agents. No third-party bot framework required.
dsh-qq-bridgeBridge one fixed DSH session to QQ (OneBot/NapCat) and keep its context: fail-closed whitelist, @/nickname wake, configurable-probability wake, everything else only recorded. 把一个固定的 DSH 会话接到 QQ（OneBot/NapCat）：白名单 + @/昵称必唤醒 + 概率唤醒，其余只记录，保留原上下文。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sj244/dsh-qq-bridgedsh-qqbotDeepSeek Harness × QQ：支持 OneBot 11（NapCat/Lagrange 等正向 WebSocket）与 QQ 官方开放平台机器人（q.qq.com AppID/AppSecret）双通道。私聊/群聊/频道即问即答，每个 QQ 会话对应一个持久 Agent（带文件/Shell/联网等完整工具），支持 Agent 主动发消息（qq_send）。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:leliln52/dsh-qqbotdsh-qqchatDeepSeek Harness 的 QQ 私聊/群聊插件，支持扫码授权、原生 Session、群记忆与工具权限。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Coffeiz/dsh-qqchatdsh-qrulesGlobal and workspace rules for DeepSeek Harness agents: configurable storage paths, system-prompt injection and a rules_read model tool.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:2128627267/dsh-qrulesdsh-quality-gateDeterministic quality gate for DeepSeek Harness: host-configured test/typecheck/lint commands, PASS/WARN/BLOCK verdicts, a post-write lint feedback loop and a turn-stop gate that refuses to let an agent declare completion on red.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kovey/dsh-engineering-suite#4a618ac4376c4a075c99c92b69895163bb21b0ce&path:packages/dsh-quality-gatedsh-quality-scoreQuality scorecard for DeepSeek Harness (dsh) plugins: 0-100 score with grade and per-component breakdown (manifest, peer resolvability, dist-tag health, dead ranges, freshness, docs, dsh-tools peer compat). Zero runtime dependencies, read-only. CLI + agent-callable quality_score tool.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zoahdev/dsh-quality-scoredsh-quant-backtest量化回测与风险指标：规避前视/幸存者偏差、考虑交易成本、walk-forward 分析、风险指标计算。受 wshobson/agents（38k★ MIT）启发。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-quant-backtestdsh-question-panel-collapse提问面板折叠：agent 提问时把问答面板折叠成一条紧凑条（保留标题与取消），展开后回答草稿不丢。Collapse the DSH question panel into a compact strip; the unsent answer draft survives expand.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Townrain/dsh-question-panel-collapsedsh-queue-directorDSH web plugin: reorder queued messages (up / down / top / bottom) before the agent processes them.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:loklamlok/dsh-queue-directordsh-queue-mergeQueue Consolidation for DeepSeek Harness: when the agent is busy and you queue several follow-up messages, the next turn runs with ONE consolidated formal prompt — the model rewrites the batch into a single prompt and executes once, instead of piecemeal one-message-per-turn rework.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:keyiadiannao/dsh-queue-mergeUse 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.