DeepSeek Harness Plugin Hub

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

Explore

Plugins Presets Docs News

Community

Publish a plugin Contact Report an issue

Resources

Plugin Hub on GitHub DeepSeek Harness System status Privacy 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 plugins Agents & Orchestration1.5k Memory & Context2.1k Coding & Developer Tools3.9k UI & Customization5.6k Integrations & Communication3k Vision & Media914 Search & Research1.2k Security & Access1.8k Models & Usage2.4k Productivity & Workflow3.6k

All plugins

2436 plugins

@jcy2387/dsh-codex-provider

Codex Provider

Connect a ChatGPT account, choose a proxy, and view usage and reset credits.

Updated 11/4/2026

dsh-web-search-glm

Web Search Glm

Zhipu GLM-backed search provider (native web_search via the Anthropic-compatible API) for the DeepSeek Harness web capability seam (ctx.web)

★ 1

Updated 11/4/2026

dsh-model-fold

Model Fold

模型选择器按来源分组：悬停来源右侧滑出该来源模型子面板，当前模型与来源一眼可见，面板内可切换模式与字号。| Group the DSH model picker by provider: hover a source to slide its models out, see the active source and model at a glance, switch mode and font size right in the menu.

Updated 11/4/2026

Autotier

Automatic strong/cheap model-tier routing for DeepSeek Harness: intent-gated tier landing on the agent/request waterfall, plan-mode handoff (strong plans, cheap implements), deterministic high-risk guards on tools/pre-execute, failure escalation with TTL

Updated 11/4/2026✓ Scan passed

@goodandready/dsh-key-limits

Key Limits

DeepSeek Harness plugin: API key / subscription quota limits (float chip, composer bar, settings).

Updated 11/4/2026

dsh-media-lens

Media Lens

Media evidence lens + provider router for DeepSeek Harness: media_read_video / media_read_audio / media_read_image turn local media into structured evidence (timeline / transcript / regions) via host-registered multimodal models first, configured OpenAI-c

Updated 11/4/2026✓ Scan passed

dsh-session-cost

Session Cost

dsh plugin: show the estimated DeepSeek API cost of the current session in the web GUI stats strip (token usage × official pricing, peak/off-peak aware)

Updated 11/4/2026✓ Scan passed

dsh-yolo-mode

Yolo Mode

dsh-yolo-mode — DeepSeek Harness dual-package plugin: when a session is in writable sandbox mode and the approval policy is ask, it uses a large language model to automatically adjudicate sandbox privilege escalation requests. Supports built-in presets and custom permission levels, and provides host

Updated 11/4/2026✓ Scan passed

dsh-model-balance

Model Balance

Multi-provider account balance display for the DeepSeek Harness Web GUI. Queries real billing APIs (DeepSeek, StepFun, Kimi Coding, OpenRouter, MiniMax, xAI) and shows balance/quota in front of the model selector. Providers without an API-level billing en

Updated 11/4/2026✓ Scan passed

@goodandready/dsh-opencode-provider

Opencode Provider

OpenCode / OpenCode Go LLM provider plugin for DeepSeek Harness (dsh).

Updated 11/4/2026✓ Scan passed

dsh-subagent-profile

Subagent Profile

Dispatch one-shot subtasks to derived subagents with per-task overrides (preset/model/provider/reasoningEffort/persona/tool whitelist), a runtime-derived cost guard, a subagent-profiles service, observability metadata, and a web-GUI settings page plus a d

Updated 11/4/2026✓ Scan passed

@lemcae/dsh-balance

Balance

DeepSeek Open Platform balance and session consumption readout (host + web client)

Updated 11/4/2026✓ Scan passed

dsh-deepseek-quota-bar

Deepseek Quota Bar

DeepSeek API quota widget for the dsh web GUI: floating bottom-right card with a blood-bar of remaining balance vs month-opening balance, plus today/month spend and current conversation cost (fork of dsh-deepseek-quota).

Updated 11/4/2026✓ Scan passed

dsh-llm-xai-oauth

Llm Xai Oauth

Use a SuperGrok / X Premium subscription inside DeepSeek Harness. Device-code OAuth, grok-bridge token reuse, no xAI API key. Works in headless, web, and any TUI.

Updated 11/4/2026✓ Scan passed

deepseek-harness-quota-monitor

Deepseek Harness Quota Monitor

Multi-provider quota monitor for DeepSeek Harness: balance type (query + JS parser) and window type (local sliding-window metering), with first-class Command Code support. Sidebar widget + Plugins page.

Updated 11/4/2026

@angelyeye/dsh-cost-tracker

Cost Tracker

DeepSeek Harness (DSH) plugin: LLM token usage & cost tracking with a settings dashboard, agent tools, HTTP API, persistent storage, multi-device cloud sync, session-log history import, official price sync and a multi-vendor price catalog.

Updated 11/4/2026✓ Scan passed

smart-compaction

Smart Compaction

dsh plugin: a compact_now tool letting the model trigger compaction itself at a safe point, plus a context_status tool so it can check real token usage against its context window, instead of only the automatic token-threshold trigger.

Updated 11/4/2026✓ Scan passed

dsh-sidebar-session-provider-icon

Sidebar Session Provider Icon

DeepSeek Harness plugin: show the brand logo of the model selected in each sidebar session, updated live from the composer selector, with a last-request fallback for history sessions

Updated 11/4/2026✓ Scan passed

dsh-usage-panel

Usage Panel

DeepSeek Harness usage statistics plugin: the “Usage Statistics” settings page displays Token usage KPIs, a six-month activity contribution heatmap, a stacked bar chart by model, and a model doughnut chart (Host projection aggregation + read-only session log recalculation, never writes back)

Updated 11/4/2026

dsh-token-total

Token Total

DSH web plugin: token usage dashboard + single-session (main agent + sub-agent) usage statistics. Provides filters for today, last 3 days, last 7 days, last month, last 3 months, and custom ranges; six summary cards; an activity heatmap; a cache hit rate line chart and per-model bar chart; and Top 5

Updated 11/4/2026✓ Scan passed

@ponydev/dsh-model-usage

Model Usage

DSH Web 插件：实时显示模型供应商额度与用量（DeepSeek / GLM Coding Plan / OpenRouter / Kimi Coding Plan + 自定义适配器）

Updated 11/4/2026✓ Scan passed

dsh-chatgpt-sub

Chatgpt Sub

Sign in with your ChatGPT account to use ChatGPT models in DSH.

Updated 11/4/2026✓ Scan passed

Agy Safe

dsh plugin: use a logged-in Antigravity CLI (agy) headless session as the chat and subagent model provider

Updated 11/4/2026✓ Scan passed

@wingsky-1/dsh-opencode-usage

Opencode Usage

OpenCode Go plan usage overlay: persistent three-window usage percentages in the top-right corner, expanding into three independent mini charts for rolling/weekly/monthly (each window has an independently adaptive axis, a 100% quota reference line, reset marker line, and background sampling to prese

Updated 11/4/2026

@y2zyyr/dsh-token-usage-sidebar

Token Usage Sidebar

Persistent Token Usage insights for DeepSeek Harness, backed by a scalable durable SQLite ledger.

Updated 11/4/2026

dsh-model-tidy

Model Tidy

DeepSeek Harness plugin: keep the model selector tidy. Choose which models appear and what they are called, without touching any provider configuration or running session.

Updated 11/4/2026

dsh-mimo-connect

Mimo Connect

将 MiMo 桌面 App 包含的模型自动接入 DeepSeek Harness，在 DSH 对话窗口里零配置使用。复用客户端已登录的额度，无需单独申请 API Key，也无需常驻程序。Bring the models included in the MiMo desktop App into DeepSeek Harness automatically, with zero configuration.

Updated 11/4/2026✓ Scan passed

dsh-peak-cost-mode

Peak Cost Mode

DeepSeek peak-pricing cost guard for DSH: during peak hours (Beijing 09:00–12:00 / 14:00–18:00, ×2) the agent automatically switches to ultra-compressed caveman-style output to save tokens, and a header badge + toast keep you posted on every peak/valley t

Updated 11/4/2026✓ Scan passed

dsh-keys-manager

Keys Manager

Multi-key management for DSH providers: sticky per-session round-robin, retry failover, cooldown recovery, and searchable extra providers.

Updated 11/4/2026

dsh-context-truth

Context Truth

DeepSeek Harness plugin: tells the model its real, host-measured context occupancy every turn — and keeps compaction summaries from carrying false "context is nearly exhausted" claims.

Updated 11/4/2026✓ Scan passed

← Previous 1…5 6 7 8 9…82 Next →

DeepSeek Harness Plugin Hub

Profiles Plugins Categories News Docs Sign in Manage Profiles

Profiles Plugins Categories News Docs Sign in