DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Models & Usage DSH plugins — Page 37

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1040Memory & Context1309Coding & Developer Tools2819UI & Customization3673Integrations & Communication1918Vision & Media619Search & Research869Security & Access1267Models & Usage1691Productivity & Workflow2249

All plugins

1688 plugins
v1.1.0
dsh-deepseek-offpeak-indicator

Deepseek Offpeak Indicator

DeepSeek Harness plugin: a small dot left of the model name in the composer tool row — yellow for DeepSeek peak hours, green for off-peak (half price). Rendered only when the session's model provider is DeepSeek.

models-usageui-customization★ 0↓ 0
Updated 10/12/2026
Lv0.1.0
dsh-llm-oc-free

Llm Oc Free

Use OpenCode’s free models as a DSH Provider: the plugin includes an isolated runtime and protocol translation, with no Electron shell or relay proxy required.

models-usage★ 0↓ 0
Updated 10/12/2026
Vv0.1.0
dsh-valley-meter-sidebar

Valley Meter Sidebar

DeepSeek peak/valley timeline plus account balance, pinned in the DSH left sidebar above the workspace region. Port of dsh-valley-meter for DSH >= 0.2.0-rc.2.

models-usageui-customization★ 0↓ 0
Updated 10/12/2026
Cv0.1.0
dsh-cost-breakdown

Cost Breakdown

DSH cost and context insights: account-wide token and cost statistics + context composition, official RMB peak/off-peak pricing (including statutory holidays), and a persistent cost readout below the input box.

models-usageui-customization★ 0↓ 0
Updated 10/12/2026
Pv0.2.1
dsh-priceflow

Priceflow

Official DeepSeek pricing and off-peak message scheduling for DeepSeek Harness.

models-usageintegrations-communicationproductivity-workflow★ 0↓ 0
Updated 10/11/2026
Ov0.1.5
dsh-openai-responses-web-search

Openai Responses Web Search

Configurable OpenAI Responses API provider for DSH web search.

search-researchmodels-usage★ 0↓ 0
Updated 10/11/2026
Uv1.2.0
dsh-ui-cost-meter

Ui Cost Meter

DeepSeek Harness Web GUI plugin: real-time spend for the current session, priced from per-model token rates and shown as a pill under the composer

models-usageui-customization★ 0↓ 0
Updated 10/11/2026
v0.5.8
dsh-better-reasoning-effort-fish

Better Reasoning Effort Fish

Configure reasoning intensity and input modalities for third-party models (DeepSeek Harness plugin, Fish supplement): declare reasoning levels and image input per model, with automatic adaptation based on the built-in model knowledge base and wire-protocol inference. Edit directly in the cards on th

models-usage★ 0↓ 0
Updated 10/11/2026
Mv0.3.3
dsh-model-smart-config

Model Smart Config

Smart model setup for DeepSeek Harness third-party API providers: recognize a model ID and fill in context window, input modalities and reasoning levels.

models-usage★ 0↓ 0
Updated 10/11/2026
Zv0.1.0
dsh-zimage-gen

Zimage Gen

DeepSeek Harness tool plugin: generate images with Alibaba Cloud Bailian Z-Image-Turbo (zimage_generate), and track usage counts and costs locally (zimage_quota).

vision-mediamodels-usage★ 0↓ 0
Updated 10/11/2026
Mv1.0.1
@moruteaven/dsh-model-quickslots

Model Quickslots

One-click model preset buttons for the DeepSeek Harness (DSH) composer — switch provider, model and reasoning effort instantly.

models-usage★ 0↓ 0
Updated 10/11/2026
Uv0.3.0
dsh-usage-dash-board

Usage Dash Board

用量统计 for DeepSeek Harness: daily token usage, request count, cache hit rate and estimated cost, shown as a native settings section.

models-usage★ 0↓ 0
Updated 10/11/2026
Av0.2.0
agnes-ai-for-dsh

Agnes Ai For Dsh

Agnes AI integration for DeepSeek Harness - LLM provider with multimodal support and GUI settings panel

models-usage★ 0↓ 0
Updated 10/11/2026
Lv0.1.0
@snnh/dsh-llm-service-lite

Llm Service Lite

Community plugin for DeepSeek Harness: a lighter LLM service with self-contained provider profiles, a declared model catalog, and the chat-completions, Anthropic Messages, and OpenAI Responses wires on the harness LLM seam.

models-usage★ 0↓ 0
Updated 10/11/2026
Cv0.2.0
dsh-context-usage-guard

Context Usage Guard

Keeps the chat context-usage ring honest: an empty usage sample from a failed attempt no longer collapses the reading to 0% across a retry, and the ring's percentage matches the figures beside it.

models-usage★ 0↓ 0
Updated 10/11/2026
Mv0.1.2
dsh-model-reasoning-levels

Model Reasoning Levels

Per-model reasoning effort levels in Settings → Models: a levels editor beside context window and input types that converts each selection into the model's reasoningEfforts in the profile's cordis.patch.yml.

models-usage★ 0↓ 0
Updated 10/11/2026
Pv0.3.4
dsh-provider-model-picker

Provider Model Picker

Composer model control that names the provider beside the model ("DeepSeek Demo/DeepSeek-V4.1-Flash") while keeping the provider-grouped picker

models-usageui-customization★ 0↓ 0
Updated 10/11/2026
Iv0.2.0
@local/dsh-independent-auto-review

Independent Auto Review

Use and configure a separate model for DSH Auto Review. Keep the main model unchanged.

models-usagedeveloper-tools★ 0↓ 0
Updated 10/11/2026
v0.1.0
onekey-models

Onekey Models

OneKey-Models — one-click access to the 108 latest models on TokenDance inside DeepSeek Harness: OAuth sign-in stores the API key for you, the model catalog syncs live, and you choose which models are visible, including image generation, Jev typed decisions and multimodal input. API support powered

models-usagesecurity-access★ 0↓ 0
Updated 10/11/2026
v0.5.0
dsh-llm-gateway-compat

Llm Gateway Compat

OpenAI-compatible gateway adapter and dialect fixes for DeepSeek Harness

models-usage★ 0↓ 0
Updated 10/11/2026
Nv0.2.2
npm-usage

Npm Usage

用量统计 for DeepSeek Harness: daily token usage, request count, cache hit rate and estimated cost, shown as a native settings section.

models-usage↓ 0
Updated 10/11/2026
Wv0.3.1
@dsh-external/dsh-whale-companion

Whale Companion

Additive whale-maid persona and automatic near-limit session continuation for DeepSeek Harness

models-usagememory-context★ 0↓ 0
Updated 10/10/2026
Av0.1.2
dsh-arckep

Arckep

Balance and spending of an arckep.ru account inside the DeepSeek Harness (DSH) web UI. Unofficial community plugin.

models-usage★ 0↓ 0
Updated 10/10/2026
Cv0.5.0
dsh-connect-zcode

Connect Zcode

Integrate ZCode（Z.ai / 智谱 BigModel）into DeepSeek Harness: Coding Plan uses the standard anthropic channel, while Start Plan / promotional gifted credits use the official agent app-server channel; includes model visibility controls, 200K/1M context budgets, reasoning level/image capability panel, and

models-usage★ 0↓ 0
Updated 10/10/2026
Mv1.0.0
dsh-model-show

Model Show

Composer model selector shows Provider/Model — 对话框模型选择器显示「供应商/模型」

ui-customizationmodels-usage★ 0↓ 0
Updated 10/10/2026
Ov0.1.0
dsh-opencode-go-pool

Opencode Go Pool

DeepSeek Harness plugin: pool several OpenCode Go subscriptions behind one provider route, serve each request with the healthiest key, and fail over when a quota window is spent.

models-usage★ 0↓ 0
Updated 10/10/2026
v1.1.0
dsh-session-billing

Session Billing

Per-session LLM cost meter for the DeepSeek Harness Web UI: folds provider usage into uncached input / cache read / cache write / output per model and prices it against DeepSeek and Xiaomi MiMo pay-as-you-go rates (DeepSeek peak-idle tiering included).

models-usage★ 0↓ 0
Updated 10/10/2026
Cv1.0.1
dsh-coding-plan-balance

Coding Plan Balance

Coding Plan quota pill for the DSH Web composer dock: the billing cycle's USD usage and the rolling 5-hour window, read with the credential your ctrip model provider already uses.

models-usage★ 0↓ 0
Updated 10/10/2026
Sv0.2.0-alpha.2
@alaxrpg/dsh-sensenova-provider

Sensenova Provider

Unofficial DeepSeek Harness LLM provider plugin for SenseNova (OpenAI-compatible). Registers the 'sensenova' provider route with multi-account API-key rotation, a Models-page card, and a live model catalog.

models-usagesecurity-access★ 0↓ 0
Updated 10/10/2026
v0.1.2
dsh-plugin-subagent-model-route

Plugin Subagent Model Route

Annotate every subagent with the model route it actually ran on: a badge line in each parent-catalog row and a readout in a child session's own header.

models-usageagents-orchestration★ 0↓ 0
Updated 10/10/2026
← Previous1…3536373839…57Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in