DSH插件商店

dsh-deepseek-quota

cn-scuo-oo

DeepSeek Harness Web 侧边栏 DeepSeek API 额度卡片 + 充值面板插件 | Sidebar quota card & recharge panel for DeepSeek Harness: real-time official /user/balance (60s auto-refresh), recharge tiers/payment methods matching the official site, official top-up QR, API key stays in Host. One-command install: bash install.sh

dsh-model-thinking

cyberlieflife

DSH (DeepSeek Harness) web plugin: thinking intensity / reasoning effort settings for custom OpenAI-compatible (pi-ai) models

deepseek-harness-plugins

dshplugin-app

A maintained directory of DeepSeek Harness plugins with categories, GitHub sources, install details, security signals, and compatibility evidence.

dsh-rollback-withdraw

dyhyfjn

Trae-style withdraw for DeepSeek Harness Web — one-click rollback of workspace code + conversation (git commits or hard-link snapshots). 会话撤回插件

dsh-usage-lite

ericw0315

为 DeepSeek Harness Web 界面提供简洁、优雅的余额与 Token 用量面板。 Compact provider balances and local token-usage analytics for the DeepSeek Harness Web UI.

dsh-polymarket-knowhow

fashionmascherine-svg

DeepSeek Harness plugin (dsh-plugin): complete Polymarket superpowers — 31 verified tools across Gamma/CLOB/Data-API/Perps/RFQ/Bridge, embedded knowhow skill, live WebSocket stream. Read-only by default.

dsh-omni-workstation

huashenglian

dsh全模态工作站插件，让模型支持视频、图片、语音的输入与输出，支持comfyui图像生成工具调用。Any-to-Any.

dsh-openai-api

huyang2024

OpenAI-compatible HTTP surface for DeepSeek Harness (dsh): POST /v1/chat/completions, POST /v1/responses, GET /v1/models over the harness webServer + llm runtime

everything-codex

iamaanahmad

The complete collection of OpenAI Codex skills, automations, multi-agent workflows, and prompts. 50+ production-ready skills, 100+ reusable prompts, background automations, and battle-tested patterns for AI-powered development.

dsh-project-prompt

imroc

Private, per-project prompt rules for DeepSeek Harness — matched by git remote/repo/path, worktree-aware, never committed to the repo

dsh-im-gateway

jelech

An IM gateway for the DeepSeek Harness: bridge messengers into harness agent sessions and control them with slash commands.

dsh-model-sync

jiay98528-dev

Writes live provider model lists into DSH settings. Composer rings show 5h/7d plan windows or metered balance for the current session model. / 把线上模型列表写进设置，输入框圆环显示当前会话的 5 小时/7 天窗口或按量剩余余额。

dsh-ext-vision-proxy

jin123-alpha

External vision proxy extension for DeepSeek Harness, enabling text-only models to analyze and understand images via OpenAI-compatible vision APIs.

dsh-survey

jinhuang712

Questionnaire-style batch questioning plugin for DeepSeek Harness: 10+ questions at once (single/multi/yes-no toggle/compare/open), per-question skip, fullscreen overlay, two-column recap after submit

dsh-agent-compact

jonah791

Agent-driven compaction for DeepSeek Harness: the agent summarizes its own conversation (KV-cache friendly, no giant rep

awesome-dsh-plugins

jqueryscript

Verified, star-ranked community plugins for DeepSeek Harness (dsh).

dsh-opencode-zen

keman-ai

Bring OpenCode Zen's free models to DeepSeek Harness — zero config, no API key, catalog discovered live from upstream

dsh-plugins

kestiny18

Community plugins for DeepSeek Harness

fast-compaction-dsh

kolawong

Verdict-based context compaction for DeepSeek Harness — replaces lossy LLM summaries with fast keep/truncate/drop decisions from jev-latest; everything kept stays verbatim. Port of tamaratran/fast-jev-compaction.

dsh-context-compactor

kusesad-1122

DSH 上下文压缩/总结插件：80% 自动全局详细总结压缩（保留核心任务/决策/待解决问题/重要文件位置，删除调试细节与已解决错误），压缩后验保证 totalTokens 必须真实下降，context-overflow 自动恢复，/compact + /context-status，输入框上方一键按钮

dsh-file-uploads

l541402398

Upload arbitrary local files from the DeepSeek Harness Web composer and manage them in Settings.

dsh-composer-layout

lavapapa

A DSH Web plugin that keeps long answers and detailed prompts side by side with a dockable Composer.

dsh-vision-provider

libinyam

Config-only DeepSeek Harness bundle for OpenAI-compatible vision models.

deepseek-vl-support

limccn

Give DeepSeek (text-only) models **vision** in Claude Code and Codex by routing image files to any OpenAI-compatible vision endpoint (OpenRouter, SiliconFlow, DashScope, Ollama, llama.cpp, vLLM, LM Studio, …). Zero runtime dependencies, MIT licensed.