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 27

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1038Memory & Context1307Coding & Developer Tools2811UI & Customization3668Integrations & Communication1918Vision & Media620Search & Research870Security & Access1270Models & Usage1681Productivity & Workflow2247

All plugins

1692 plugins
Sv0.1.0-alpha.10
dsh-sensenova-freeapi

Sensenova Freeapi

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★ 1↓ 0
Updated 10/2/2026
Mv3.16.6
dsh-modlens

Modlens

Plug-in vision for text-only LLMs — a DeepSeek Harness (dsh) fork of ModLens adding multi-engine support (Gemini, Volcengine Ark/Doubao, Claude) and per-call engine selection

vision-mediamodels-usage★ 1↓ 0
Updated 10/2/2026
Lv1.14.0
@local/dsh-localmodels-tokensavior

Localmodels Tokensavior

DSH-LocalModels-TokenSavior —— Provides a dedicated “Local Models” section in Settings: the panel allows directly enabling or disabling the feature and selecting a model (volatile Config), and delegates read-only data collection tasks to a local Ollama model (source text is not included in the conte

models-usage★ 1↓ 0
Updated 10/1/2026
B
v0.1.1
@wyxcn445/dsh-balance

Balance

DSH plugin: Display the DeepSeek account balance (recharge balance + bonus credits) in real time in the input box toolbar, with click-to-expand details and usage/recharge access.

models-usageui-customization★ 1↓ 0
Updated 10/1/2026
Gv0.1.4
dsh-grok-image

Grok Image

DeepSeek Harness plugin: Grok Imagine image generation as a model tool (subscription)

vision-mediamodels-usage★ 1↓ 0
Updated 10/1/2026
Cv1.2.0
dsh-commandcode-usage

Commandcode Usage

CommandCode 用量与余额面板 — 在 DSH 侧边栏底部（设置按钮旁）显示 API 用量、信用额度、5小时/每周/月额度。 · CommandCode usage & balance panel for DeepSeek Harness: usage, credit balance and 5-hour/weekly/monthly windows from the sidebar footer.

models-usageui-customization★ 1↓ 0
Updated 10/1/2026
Cv0.3.0
dsh-context-governor

Context Governor

Session context governor for DeepSeek Harness: prompt size and per-step cost in dollars (cache-read/cache-write aware), cache-hit, context bands, a per-session compaction threshold derived from the model window, DeepSeek balance and peak/off-peak tariff, and a one-click handoff. It never calls a mod

models-usagememory-context★ 1↓ 0
Updated 10/1/2026
Cv1.6.8
dsh-cost-gauge

Cost Gauge

DeepSeek Harness cost meter: A square floating window near the upper-left displays DeepSeek API session costs, with a pointer indicating the current peak/off-peak rate (standard/doubled). A red light at the top flashes when the balance falls below the threshold.

models-usageui-customization★ 1↓ 0
Updated 10/1/2026
Sv0.2.0
dsh-subagent-setting

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。

models-usageagents-orchestration★ 1↓ 0
Updated 9/30/2026
v0.2.1
@leaves615/dsh-llm-ctl

Llm Ctl

DSH plugin — rate-limit queuing, provider cooldown, and standalone request recovery on the llm/stream and agent/request-error seams

models-usage★ 1↓ 0
Updated 9/30/2026
Cv0.1.1
dsh-composer-balance

Composer Balance

DeepSeek balance persistent input field: small-text balance + refresh button + low-balance alert + deepseek_balance model tool. The key is not written to disk (passed to curl via stdin).

models-usage★ 1↓ 0
Updated 9/30/2026
Rv0.2.0-rc2.1
@zhourenke/dsh-reasoning-mode

Reasoning Mode

Configure Responses reasoning mode and summary per provider/model in DeepSeek Harness

models-usage★ 1↓ 0
Updated 9/30/2026
Tv0.2.0-rc2.1
@zhourenke/dsh-tool-call-limit

Tool Call Limit

Per-agent per-step ToolRuntime call limits for DeepSeek Harness

agents-orchestrationmodels-usage★ 1↓ 0
Updated 9/30/2026
Uv1.0.0
@kxdyh/dsh-usage-meter

Usage Meter

Sidebar meter for DeepSeek Harness: live context/token usage and the signed-in account balance.

models-usageui-customization★ 1↓ 0
Updated 9/30/2026
Av0.2.0-rc2.1
@zhourenke/dsh-agent-rate-limit

Agent Rate Limit

Agent loop rate limiter — prevents TPM/RPM limit violations by intercepting the LLM streaming pipeline and adding adaptive delays between requests

models-usage★ 1↓ 0
Updated 9/30/2026
Cv0.3.4
@2jumpsina/dsh-context-guard

Context Guard

DSH context-pressure guard: when a session's next request would carry a dangerously large prompt, tell the user at turn end to write the handoff and start a new session. Consumes the official token-meter contextPressure projection; injects no prompt, registers no model-facing tool, so its context ta

models-usagememory-context★ 1↓ 0
Updated 9/30/2026
v0.2.0
@kelearns/dsh-token-usage

Token Usage

Token usage heatmap for the dsh web GUI. Reads session history through DSH's public persistence service and mounts through the official plugin mechanism.

models-usageui-customization★ 1↓ 0
Updated 9/30/2026
Pv0.2.0
dsh-plugin-ollama-usage

Plugin Ollama Usage

Show Ollama Cloud account usage in the conversation, and configure its baseURL and credential mode.

models-usagesecurity-access★ 1↓ 0
Updated 9/30/2026
Vv0.3.2
dsh-vision-tool

Vision Tool

dsh plugin: vision capability proxy. Routes image understanding for text-only main models to a small multimodal model, and backs off entirely when the active model declares multimodal support (inputModalities includes 'image').

vision-mediamodels-usage★ 1↓ 0
Updated 9/30/2026
Av0.1.0
dsh-agents

Agents

DSH 侧的 23 个专职角色 × 模型档位路由：把 oh-my-claudecode 的角色体系移植成 DSH 工具（agent_roles / agent_taskbook / agent_spawn），按角色钉死模型档位（LOW/MEDIUM/HIGH ← haiku/sonnet/opus）并一步派活。

agents-orchestrationmodels-usage★ 1↓ 0
Updated 9/30/2026
Sv0.2.0-rc.2
dsh-show-balance

Show Balance

Show account balance directly in the status bar.

models-usageui-customization★ 1↓ 0
Updated 9/30/2026
Mv1.0.0
model-catalog

Model Catalog

dsh plugin: automatic model catalog discovery — automatically fetches model lists, pricing, and capabilities from OpenAI-compatible API hosts, normalizes them, and generates ready-to-use configuration.

models-usage★ 1↓ 0
Updated 9/29/2026
Av0.1.2
dsh-amd-free-model

Amd Free Model

AMD Free Model — Automatically detects the free model list from AMD Radeon Token Factory daily (paid models are always excluded). Enter an API Key in dsh to use free AMD GPU Cloud models such as DeepSeek V4, MiMo V2.6, and Qwen3.8; the catalog refreshes with upstream updates, availability is detecte

models-usage★ 1↓ 0
Updated 9/29/2026
Lv0.2.0
dsh-llm-quota-retry

Llm Quota Retry

Keep a DeepSeek Harness agent step alive through an exhausted account quota: after the base provider retry policy gives up on a QUOTA failure, retry the same request once per hour without an attempt limit, and publish the entering, leaving, and current state of that long-term retry to other plugins.

models-usageagents-orchestration★ 1↓ 0
Updated 9/29/2026
Mv0.2.0-rc.2
@jcy2387/dsh-models-input-modalities

Models Input Modalities

Set image input and reasoning levels for third-party provider models.

vision-mediamodels-usage★ 1↓ 0
Updated 9/29/2026
Tv0.3.0
@hjdd14/dsh-toolong-warning

Toolong Warning

DSH plugin: counts completed compactions per session and raises a floating reminder — with bilingual UI — only after repeated compactions plus heavy extra token spend.

models-usageproductivity-workflow★ 1↓ 0
Updated 9/29/2026
Pv0.7.1
dsh-plugin-local-model

Plugin Local Model

DeepSeek Harness local model plugin: a separate “Local Models” page in settings; automatically starts llama.cpp for the first conversation and unloads it after 5 minutes of inactivity to free resources.

models-usage★ 1↓ 0
Updated 9/29/2026
Pv0.1.3
dsh-pricing-badge

Pricing Badge

Quick reference for DeepSeek official API peak/off-peak periods, current model output prices, and account balance (DeepSeek Harness plugin, tool only, does not call models)

models-usage★ 1↓ 0
Updated 9/29/2026
Cv0.4.2
dsh-continue-on-limit-host

Continue On Limit Host

Host-side global max-tokens auto-continuation for DeepSeek Harness with Follow-up and selectable transparent Steer tool-call policies.

models-usage★ 1↓ 0
Updated 9/28/2026
Wv0.4.3
dsh-wsl-hostsvc

Wsl Hostsvc

From WSL, probe Windows-host Ollama / LM Studio / vLLM / llama-server; openAiModels apiReady vs TCP.

models-usagedeveloper-tools★ 1↓ 0
Updated 9/28/2026
← Previous1…2526272829…57Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in