Discover The Best DSH plugins
25610results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-model-testerModel availability tester panel in the Models settings page: one-click real streaming test per added model with TPS / first-token / elapsed metrics
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:masknull/dsh-model-testerdsh-model-thinking-levelsExpose per-model thinking levels (reasoningEfforts) and manual model ordering inside the Models settings card for a custom model API route.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Zessi-C/dsh-model-thinking-levelsdsh-model-tidyDeepSeek Harness plugin: keep the model selector tidy by choosing which models show up, without touching any provider configuration or running session.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:star-Cosmo/dsh-model-tidydsh-model-ultraModel Ultra — DSH plugin for llm-pi-ai provider lifecycle: create/edit, custom headers, enable/disable with uninstall-restore safety, per-model thinking effort, OpenRouter provider routing, smart routing, composites, observability, and per-model connectivity tests
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MrCashmere/dsh-model-ultradsh-modelprintDeepSeek Harness plugin: fingerprint the provider, model id, sampling, offered tool schemas, and system-prompt prefix of each request, and diff the live card against a pinned one through the modelprint_check tool
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jwilson411/dsh-modelprintdsh-modelsModel menu for the dsh web GUI: search-first model picker + reasoning-effort selector, per-session subagent model routing, dim-powered price badges and new-model discovery, and a settings-page management card
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:taxueseek/dsh-modelsdsh-models-filterFilter input for the composer model menu: case-insensitive list filtering with combobox keyboard navigation, rendered with the shipped menu design
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:odelbos/dsh-models-filterdsh-models-radarModel capability radar for the DeepSeek Harness web GUI: a Settings tab that charts codexradar crowd-benchmark scores per model tier — task-composition bars, 7-day IQ trend, efficiency badges
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hi-fangj/dsh-models-radardsh-modernize-codeDSH 技能包：遗留代码现代化/简化工作流（preflight → assess → map → transform），含 Cordis 挂载插件、离线 Python 脚本与冒烟测试。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:988hj7tczd-oss/dsh-modernize-codedsh-modesView and manage DeepSeek Harness agent modes (presets) in Web Settings: toggle the plugins each mode loads, edit its system prompt, and create modes from starter templates.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiaohai-78/dsh-modesdsh-modpackPCL 式 DSH 整合包：勾选已安装的第三方插件，导出小体积 .dshpack.zip 与一键安装命令串；导入先预览再按 spec 重新下载安装。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:M1r0er/dsh-modpackdsh-mods-enhancedDSH 增强功能静态化常驻包(bundle):余额查询/会话完成提醒/费用预估与账单明细/粘贴图片转文字/Token 用量统计;仓库另含模型选择器增强等插件源码与一键安装脚本
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:koji-xiaoer/dsh-pluginsdsh-modular-scale字号阶梯（模块化比例）计算器
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-modular-scaledsh-moe-cleanLightweight blue-white glass theme for DeepSeek Harness: muted whale-maid artwork, frosted panels, custom new-session and plugin icons.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:KurosawaGeeker/dsh-moe-cleandsh-moe-plugin萌属性 Persona system for DSH (DeepSeek Harness): 10 preset character-trait cards (傲娇/毒舌/元气/天然呆/病娇/冰美人/暗恋型/大小姐/姐姐型/猫咪系), bilingual prompts, free-text recommendation, custom card editing, persistent persona storage.
dsh-momo-learningDeepSeek Harness plugin bundle: the 墨墨学习 mirror MCP server (mcp__maimemo__*) plus the momo-daily-learning skill
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ryukirin/dsh-momo-learningdsh-monacoDeepSeek Harness plugin: serves the Monaco editor distribution over a host HTTP route, so an editor plugin needs no CDN and no extra bundler outputs
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DevViking-Persike/dsh-monacodsh-monaco摩纳哥国
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-monacodsh-moneyDeepSeek Harness 费用追踪插件：显示账号余额、当前对话费用与每次回复费用，金色标签风格，支持币种切换
dsh-monitorDeepSeek Harness 会话计费 + 通用提供方用量查询插件：会话费用角标、按模型提供方配置的用量面板（DeepSeek 官方余额 / OpenCode 5小时·周·月套餐额度 / 自定义 HTTP 用量查询）。Session billing and per-provider usage quota plugin for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Coco-king/dsh-monitordsh-monitor-ppi显示器PPI
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-monitor-ppidsh-monorepoMonorepo 管理：仓库结构、依赖管理、构建缓存、CI 策略。受 wshobson/agents（38k★ MIT）启发。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-monorepodsh-month-name月份名称
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-month-namedsh-month-tokensSidebar counter for one calendar month of provider-reported token usage: this DSH home plus opencode, from local data only, resetting at 00:00 on the 1st.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:greyhackintoch-dev/dsh-month-tokensUse 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.