Discover The Best DSH plugins

DeepSeek Harness plugins — Page 1103

29334results

Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.

dsh-subagent-model-router

Model-selectable subagents with per-task reasoning effort and guided model routing setup for DeepSeek Harness 0.1.7 and 0.2.x

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:pumbleblock/dsh-subagent-model-router
dsh-subagent-model-switch

给 DSH 的队友/子代理会话头部加一个模型切换器:不重开会话、不丢上文,切换后下一 turn 即用新模型。

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YuMo-233/dsh-subagent-model-switch
dsh-subagent-model-sync

Give subagents, agent-team teammates and nested children a hand-switchable model route and thinking effort, or let the parent session sync them all with one switch.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:123123liang/dsh-subagent-model-sync
dsh-subagent-model-visibility

DeepSeek Harness plugin that shows the actual provider/model used by each subagent inside native tool-call rows and the native subagent catalog.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AGSQ11/dsh-subagent-model-visibility
dsh-subagent-models

Set the provider, model and reasoning effort DSH subagents run with: one profile-wide default in Settings, plus a per-conversation override from a chip beside the composer.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Garybot126/dsh-subagent-models
dsh-subagent-output-sanitizer

Open-source DSH plugin: dsh-subagent-output-sanitizer

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:vb2250158/dsh-subagent-output-sanitizer
dsh-subagent-panel

DSH plugin: render every subagent as a clickable card in the main conversation that opens the child as an ordinary session — OpenCode-style subagent visibility, without re-rendering the shell's session view.

Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:BiKing567/dsh-subagent-panel
dsh-subagent-pi-plus

One-shot Pi subagent provider and true-gateway over the Pi RPC protocol

Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:february2015/dsh-subagent-pi-plus
dsh-subagent-pool

DSH named-subagent pool: maintain a library of reusable subagents (model, reasoning effort, agent preset) on a settings page and call them by name with subagent_run

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiagaogaozi/dsh-subagent-pool
dsh-subagent-progress

Live subagent progress dock for DeepSeek Harness: folds each child session's events into a subagentProgress projection (turn/step, last tool, latest assistant preview, notify_user updates) and renders a frosted-glass status dock above the parent conversation composer.

Agent collaboration · Notifications · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:edgeseeker7/dsh-subagent-progress
dsh-subagent-reasonix

One-shot Reasonix subagent over the Agent Client Protocol, using Reasonix's native authentication and settings

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SivanCola/dsh-subagent-reasonix
dsh-subagent-response-promoter

Promote subagent settlements and parent relays at safe Agent step boundaries in DeepSeek Harness.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JachinShen/dsh-subagent-response-promoter
dsh-subagent-role-router

Route DSH subagent delegations to configured models: 3-role routing (explore / plan / patch), round-robin or random distribution, cross-provider failover, fork window slicing, and agent-teams exemption.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:643048695/dsh-subagent-role-router
dsh-subagent-route-badges

在 DSH 已打开子代理的 Header 展示 provider、model 和 reasoning effort

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:alaxrpg/dsh-subagent-route-badges
dsh-subagent-setting

Configure the default provider, model and reasoning effort for new subagents from the Web settings page; optionally apply changes to existing idle subagents. · DSH 插件:在设置页可视化配置 subagent 默认的提供商、模型与思考等级,新创建的 subagent 立即生效,可选的让空闲 subagent 也跟随新设置。

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:marshfolx/dsh-subagent-setting
dsh-subagent-team

DeepSeek Harness 子代理团队插件:9 个分工明确的子代理(读/写/代码/文档/修复/审查/识图 + 统筹)+ 代码质量流水线 + 长任务(continuable) + Token 动态可调 + 性能优化;含编译型 half(team_run 并行聚合 / team_note 黑板 / team_stat 观测 / team_budget 预算)。

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xuqingsakura/dsh-subagent-team
dsh-subagent-toggle

DSH plugin: a Settings switch that disables the subagent tool family (subagent/subagent_fork/workflow/ralph/list_subagent_models/send_message) and tells the model to use Agent Teams instead.

Agent collaboration · Interface extensions · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mimajiushi/dsh-plugins#1aa8b9d851070af475ca10703d84c000562ef8d7&path:plugins/dsh-subagent-toggle
dsh-subagent-vision

dsh bundle: subagent_vision — delegate image reading to a vision-capable model from a text-only session, plus paste-to-path so pasted images reach the subagent as file paths.

Agent collaboration · Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:niuniuaba/dsh-subagent-vision
dsh-subagent-watchdog

DSH plugin: safe auto-continue-once recovery for native continuable subagents that end with explicit max-tokens termination. No timers, no polling, no private APIs.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:quaner1234-cmd/dsh-subagent-watchdog
dsh-subprocess-remote

DeepSeek Harness ctx.subprocess provider backed by the remote-sandbox sidecar: managed process trees with real signals, bounded output, tree-scoped termination, and backend-native terminals.

Agent collaboration · Integrations · Productivity
dsh-subprocess-win32

Managed Windows subprocess runtime and user presets for DeepSeek Harness

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:delightedMaster/dsh-subprocess-win32
dsh-subscription-antigravity

Google Antigravity subscription reuse for DeepSeek Harness: browser PKCE sign-in, loopback OpenAI-compatible proxy to Cloud Code Assist, and Gemini/Claude/GPT-OSS model routes. Unofficial; no telemetry.

Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:shaomingbo/dsh-subscription-antigravity
dsh-subscription-login

Subscription sign-in console for DeepSeek Harness: sign in to ChatGPT (Codex), Claude, GitHub Copilot and OpenRouter through DSH's own authorization flows, from one page that lists every registered flow instead of one provider.

Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:woodfood111/dsh-subscription-login

Find the right plugin, then get started

  1. Search by task

    Use a feature keyword or category, then sort by recent updates or GitHub stars.

  2. Explore capabilities

    Read the description, AI analysis and original README to understand what a plugin does.

  3. Check and install

    Review compatibility, dependency ranges and instructions, then copy the available install command.

Questions about DSH Hub

What is DSH Hub?

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.

Does inclusion mean a plugin is tested and compatible?

No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.

How do I install a plugin?

Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.