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.

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All categories

All pluginsAgents & Orchestration1.5kMemory & Context2.1kCoding & Developer Tools4kUI & Customization5.6kIntegrations & Communication3kVision & Media925Search & Research1.2kSecurity & Access1.8kModels & Usage2.5kProductivity & Workflow3.7k

All plugins

2462 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.

↓ 55★ 0
Updated 11/4/2026
v0.1.0
@sylvainatelier/dsh-agent-hub

Agent Hub

DeepSeek Harness plugin integrating multiple agents (Claude, Codex, MiniMax, ...): subscription usage today, multi-agent task coordination next

↓ 27★ 1
Updated 11/4/2026
v0.2.0
dsh-langfuse

Langfuse

dsh-langfuse: Langfuse LLM observability for DeepSeek Harness — one OpenTelemetry trace tree per agent session, with feedback scores and subagent lineage.

↓ 27★ 1
Updated 11/4/2026
v0.3.1
deepseek-harness-openai-oauth

Deepseek Harness Openai Oauth

DeepSeek Harness LLM provider for Codex models using managed ChatGPT OAuth

↓ 54★ 0
Updated 11/4/2026
v0.1.1
dsh-deepseek-usage-monitor

Deepseek Usage Monitor

DeepSeek Harness plugin for token usage and account balance monitoring.

↓ 54
Updated 11/4/2026
v0.4.2
dsh-llm-session-header

Llm Session Header

DeepSeek Harness plugin: attaches a stable per-conversation session header to model requests routed to configured providers. Header name is configurable, so one plugin serves SMG (X-SMG-Routing-Key), OpenCode (x-opencode-session), and any other header-bas

↓ 53
Updated 11/4/2026
v0.2.0
dsh-miopiik-model-auth

Miopiik Model Auth

Model authorization gate: subagent model/provider pulls must be in the user-controlled allowlist. 模型授权闸：子代理拉模型必须 ∈ 用户 allowlist

↓ 26★ 1
Updated 11/4/2026
v0.3.0
dsh-cost-line

Cost Line

DSH web plugin: a real-pricing usage-cost line beside the official token stats — per-model cost breakdown with a verified price table. / DSH 费用统计行：在官方 Token 用量行旁按模型显示真实费用（按模型分别标注，价格均来自官方定价页）。

↓ 26★ 1
Updated 11/4/2026
v0.3.5
@syncended/dsh-usage

Usage

Token usage, model cost analytics, trends, and activity heatmaps for DeepSeek Harness

↓ 52★ 0
Updated 11/4/2026
v0.1.0
dsh-llm-auto-route

Llm Auto Route

Provider discovery, matching, health checks, and pre-output failover for DeepSeek Harness.

↓ 51★ 0
Updated 11/4/2026
v0.5.0
dsh-model-selector

Model Selector

DeepSeek Harness model selector upgrade: one-level model & reasoning-effort picker with 5 Liang tiers, custom model aliases, and peak/off-peak price countdown.

↓ 51★ 0
Updated 11/4/2026
v0.1.9
dsh-request-log

Request Log

DeepSeek Harness plugin that records every LLM provider request/response, viewable per call in the web UI.

↓ 49★ 0
Updated 11/4/2026
v0.2.5
@kevensun/dsh-oai-oauth

Oai Oauth

ChatGPT Plus/Pro OAuth and GPT model provider for DeepSeek Harness

↓ 24★ 1
Updated 11/4/2026
v0.4.0
@javierni/balance-show

Balance Show

Balance & usage card plugin built on the DeepSeek Harness for its Web GUI (not affiliated with DeepSeek): account balance with color tiers, plus live per-conversation token usage and cost (peak/off-peak priced).

↓ 49★ 0
Updated 11/4/2026
v0.1.12
dsh-dev-crew

Dev Crew

A DeepSeek Harness plugin that mounts one subagent delegation tool per configured role and model, each bound to its own model provider route.

↓ 48★ 0
Updated 11/4/2026
Cv0.1.3
@sroada/dsh-confirm-gate

Confirm Gate

Bounded-run framework for DeepSeek Harness: per-turn persistent-operation counter that reminds, then instructs the model to stop, then asks the user for confirmation.

↓ 0★ 48
Updated 10/22/2026
v0.1.0
dsh-plugin-auto-retry

Plugin Auto Retry

DeepSeek Harness plugin that takes over a model-request failure the built-in retry executor declined, continuing its backoff curve, and surfaces the full failure detail the transcript discards.

↓ 47★ 0
Updated 11/4/2026
v1.5.1
@lolkda/dsh-agent-team-model-pin

Agent Team Model Pin

DSH Host/Web plugin: choose Team models, reasoning effort and creation-time Agent presets with native command menus

↓ 47
Updated 11/4/2026
v0.2.0
dsh-cost-gate

Cost Gate

Spend gate for DeepSeek Harness: refuses over-budget model calls on the llm/stream waterfall, before they are billed. Auto-downgrade past a soft limit.

↓ 47★ 0
Updated 11/4/2026
v0.1.0
dsh-plugin-thinking-mode

Plugin Thinking Mode

DeepSeek Harness plugin: per-request thinking-mode switch (enable_thinking) for Qwen3-family models on OpenAI-compatible endpoints

↓ 23★ 1
Updated 11/4/2026
v0.2.6
dsh-account-pool

Account Pool

Aggregate multiple WorkBuddy / Trae accounts into an account pool for DeepSeek Harness: automatic switching, rate limiting, circuit breaking and backoff, secure credential persistence

↓ 46★ 0
Updated 11/4/2026
v0.4.7
@kindred7/dsh-usage-stats

Usage Stats

Usage statistics plugin: adds a Usage Statistics section in DSH settings — cumulative/peak token & request counters, daily streaks, a 1-year activity heatmap, per-model daily line charts, and per-model monthly stacked-bar charts. Request counts are shown

↓ 22★ 1
Updated 11/4/2026
v0.1.1
@acc1143/dsh-vision-bridge

Vision Bridge

DSH dual-model routing plugin: keeps the main conversation in DeepSeek, automatically routes image tasks to an explicitly configured vision model, and returns the analysis results to DeepSeek to continue.

↓ 22★ 1
Updated 11/4/2026
Mv0.2.4
@fhxgs/dsh-model-hub

Model Hub

DeepSeek Harness plugin: provider sign-in, model catalog, and selection routing over a loopback-only /model-hub channel

↓ 45★ 0
Updated 11/4/2026
v0.1.0
dsh-token-dashboard

Token Dashboard

Token usage dashboard for DeepSeek Harness: cache, context, efficiency, per-step details, and cross-session comparison

↓ 45★ 0
Updated 11/4/2026
v0.3.0
dsh-model-meta-autofill

Model Meta Autofill

DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).

↓ 44★ 0
Updated 11/4/2026
v0.2.17
dsh-usage-stats-alhabor

Usage Stats Alhabor

Usage statistics for DeepSeek Harness: aggregated token and cost metering per session, per day, per week, per month and over custom date ranges, with per-model breakdown, peak-hour pricing, durable daily history, a Settings usage panel and the /usage comm

↓ 43★ 0
Updated 11/4/2026
v0.1.1
dsh-session-cost-cny

Session Cost Cny

DeepSeek Harness plugin: Displays the current session’s DeepSeek usage cost (CNY) in real time in the status bar below the input box. Click the amount to expand the input / cache / output cost breakdown. Pricing is sourced from the DeepSeek official website and calculated according to peak and off-p

↓ 42★ 0
Updated 11/4/2026
v0.0.7
dsh-model-reasoning-defaults

Model Reasoning Defaults

DSH (DeepSeek Harness) plugin: Configure a default reasoning level (reasoningEffort) for each LLM model and automatically fill it according to routing rules before requests enter the underlying call chain.

↓ 41★ 0
Updated 11/4/2026
v0.1.0
dsh-temperature-picker

Temperature Picker

DeepSeek Harness plugin: a temperature picker button left of the model selector — ticked slider (0–1.2, step 0.1) plus range-checked input, applied to every provider via the agent/request waterfall, persisted through the profile patch.

↓ 41★ 0
Updated 11/4/2026
← Previous1…1617181920…83Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in