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 31

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1033Memory & Context1318Coding & Developer Tools2800UI & Customization3677Integrations & Communication1909Vision & Media619Search & Research864Security & Access1273Models & Usage1688Productivity & Workflow2249

All plugins

1691 plugins
Cv0.9.0
dsh-context-show

Context Show

Real-time context occupancy meter for DSH Web: draggable compact/detail panel, per-tool usage, settings-editable cost table (CNY/USD, flat or peak/off-peak), per-provider usage and token totals

models-usageui-customization★ 1↓ 0
Updated 8/25/2026
Wv0.1.0
@dsh-external/dsh-web-search-openai

Web Search Openai

OpenAI Responses API-backed web search provider for dsh: registers into ctx.web (web_search tool with server-side retrieval), plus a Web settings card for endpoint/model/key. Hot-pluggable — mounted via profile bundle patch, no dsh source changes.

search-researchmodels-usage★ 1↓ 0
Updated 8/25/2026
Mv0.1.1
dsh-multiprovider

Multiprovider

Provider-neutral multi-account scheduling, affinity, health, and Settings UI for DeepSeek Harness

models-usage★ 1↓ 0
Updated 8/24/2026
Bv1.0.0
dsh-billing-dashboard

Billing Dashboard

DeepSeek Harness Usage Dashboard (Permanent Plugin): account balance, today’s spending and token usage, a 7-day spending trend chart, one-click recharge access, and a fully Chinese interface.

models-usageui-customization★ 1↓ 0
Updated 8/24/2026
Lv1.1.1
dsh-llama-responses

Llama Responses

DeepSeek Harness plugin: run subagents on a local llama.cpp model via the OpenAI Responses (/v1/responses) protocol, with a subagent delegation skill

agents-orchestrationmodels-usage★ 1↓ 0
Updated 8/24/2026
Qv0.4.2
quota-meter

Quota Meter

Session quota monitoring (dsh bundle enhanced version): accounting based on official DeepSeek prices, quota exhaustion blocking + progress bar UI above the input box (same-origin protection + inputWrite billing tier + balance calibration floating window in the upper-right corner of the screen)

models-usageui-customization★ 1↓ 0
Updated 8/24/2026
Ev0.1.0
dsh-effort

Effort

DeepSeek Harness plugin: Select the model’s reasoning effort in the Web GUI. Displays available levels (such as Off / High / Max) based on the current model’s adapter directory, and applies the selection to the session’s model with one click.

models-usage★ 1↓ 0
Updated 8/24/2026
Dv0.1.0
dsh-deepseek-model-router

Deepseek Model Router

Auto-switch DeepSeek models for DeepSeek Harness: routes every model request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual per-session overrides.

models-usagevision-media★ 1↓ 0
Updated 8/24/2026
Mv0.1.0-rc.1
dsh-model-controller

Model Controller

Semantic model routing plugin for DeepSeek Harness

models-usage★ 1↓ 0
Updated 8/24/2026
v0.1.2
dsh-model-gate

Model Gate

Single-model disable gate: hides denied models from every discovery path, blocks dispatch with an in-protocol error chunk, and exposes a settings-section UI for the denylist

security-accessmodels-usage★ 1↓ 0
Updated 8/24/2026
Av0.1.0
dsh-adaptive-model-router

Adaptive Model Router

Deterministic per-turn adaptive model routing for DeepSeek Harness

models-usage★ 1↓ 0
Updated 8/24/2026
Sv0.1.0
dsh-subscriptions

Subscriptions

DeepSeek Harness plugin: use your own Claude and ChatGPT/Codex subscriptions as model providers, over each vendor OAuth flow

models-usagesecurity-access★ 1↓ 0
Updated 8/23/2026
Pv0.1.0
dsh-plugin-model-quota

Plugin Model Quota

Display CLIProxyAPI subscription quotas in DeepSeek Harness.

models-usage★ 1↓ 0
Updated 8/23/2026
Ov0.4.0
dsh-openai-server-compaction

Openai Server Compaction

OpenAI Responses adapter and durable server-side compaction bundle for DeepSeek Harness.

models-usage★ 1↓ 0
Updated 8/23/2026
Dv0.1.0
@dsh-external/ds-balance

Ds Balance

A minimal DeepSeek account balance widget for the DeepSeek Harness web GUI

models-usageui-customization★ 1↓ 0
Updated 8/22/2026
Uv1.0.0
dsh-usage-analytics

Usage Analytics

Personal usage analytics & activity dashboard for the DeepSeek Harness (dsh) web GUI: token totals, session activity, GitHub-style contribution heatmap, model / reasoning-effort / tool / skill / plugin rankings, streaks and insights. Aggregates real session events through ctx.sessionPersistence; no

models-usageui-customization★ 1↓ 0
Updated 8/22/2026
Av0.1.0
dsh-account-balance

Account Balance

DeepSeek account balance dashboard for dsh web: shows your DeepSeek API balance above the chat window, auto-refreshed.

models-usageui-customization★ 1↓ 0
Updated 8/22/2026
Bv1.2.0
dsh-better-retry

Better Retry

DSH (DeepSeek Harness) Cordis plugin: retry ANY model-request failure (any error code) with exponential backoff — retry budget adjustable from Settings → General via a slider (0–64, default 8).

models-usage★ 1↓ 0
Updated 8/22/2026
Mv1.1.0
dsh-model-quota-usage

Model Quota Usage

DeepSeek Harness model quota and token statistics panel: displays only the DeepSeek account balance and provides daily totals of token usage for all Providers and models.

models-usageui-customization★ 1↓ 0
Updated 8/22/2026
Cv2.4.1
dsh-consult

Consult

Cross-provider second-opinion advisor for dsh. v2 (simple-extensible-configurable-stable): DEFAULT ROUTE = official DeepSeek (deepseek-official/deepseek-v4-flash); model param optional everywhere; one-page visual settings panel; honest audit trail. Scout mode = official + live web_search. OpenAI-com

models-usagesearch-research★ 1↓ 0
Updated 8/22/2026
Bv0.1.1
dsh-balance-tasks

Balance Tasks

Balance-to-task conversion: a floating card in the bottom-right corner displays the DeepSeek account balance, current peak/off-peak rate tier and countdown, and estimates how many tasks the balance can still run based on historical average usage (1 task ≈ 1 session, including peak/off-peak pricing)

models-usageui-customization★ 1↓ 0
Updated 8/22/2026
Ov0.1.0
dsh-openai-responses-bridge

Openai Responses Bridge

DeepSeek Harness bundle for Google Generative AI and third-party OpenAI Responses providers.

models-usageintegrations-communication★ 1↓ 0
Updated 8/22/2026
v0.1.3
dsh-text2img-compress

Text2img Compress

把长文本渲染成图片发送来压缩 LLM 输入 token(DeepSeek 视觉模型、每图 384 token 封顶)— text-as-image token compression for DeepSeek Harness

vision-mediamodels-usage★ 1↓ 0
Updated 8/22/2026
Bv0.1.8
dsh-balance-by-token

Balance By Token

DeepSeek balance & token-cost plugin for DeepSeek Harness (dual-face): query official balances of every DeepSeek provider (multi API key), compute costs (last question / session / today-project / today-all) from token usage with a user-editable price table. Unified modal UI, bilingual (zh/en)

models-usage★ 1↓ 0
Updated 8/22/2026
Tv0.2.0
dsh-task-models

Task Models

Enhanced DSH subagent tools with per-call model and reasoning-effort selection

agents-orchestrationmodels-usage★ 1↓ 0
Updated 8/22/2026
Iv0.1.2
dsh-image-vision-bridge

Image Vision Bridge

DSH host plugin: automatically sends images in user messages to a vision model (default mimo-v2.5 on opencode-go) and feeds the returned text description to the main text model (e.g. deepseek-v4-pro), without touching the visible chat transcript.

vision-mediamodels-usage★ 1↓ 0
Updated 8/22/2026
Av0.1.0
dsh-allrouter

Allrouter

Register AllRouter as a DSH provider: one base URL and one key for Kimi K3, Claude, GPT, Grok, GLM, DeepSeek, MiniMax-H3. Switch models without managing separate providers; every call reports real cost.

models-usage★ 1↓ 0
Updated 8/22/2026
Lv0.1.0
luxueliu-reasoning-efforts

Luxueliu Reasoning Efforts

Reasoning-effort ladders for every non-ds model on a local LLM gateway route in DeepSeek Harness: declares selectable thinking levels (off/low/medium/high/xhigh/max) for hand-declared gateway models that would otherwise show no reasoning control at all, and re-applies them to the live profile settin

models-usage★ 1↓ 0
Updated 8/21/2026
Pv0.1.0
dsh-providers

Providers

Model providers for DeepSeek Harness: sign in with OAuth or an API key, and keep every provider's model catalog current

models-usagesecurity-access★ 1↓ 0
Updated 8/21/2026
Bv0.1.0
dsh-balance-whale

Balance Whale

Floating whale-girl balance widget for dsh: polls https://api.deepseek.com/user/balance on the Host side, shows a bottom-right floating card with a whale-girl icon.

models-usageui-customization★ 1↓ 0
Updated 8/21/2026
← Previous1…2930313233…57Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in