dsh-catgirl-plugin
Freakz2zA token-efficient persona runtime for DeepSeek Harness. 把人格留在界面,把智能留给模型。Measured: -67% input tokens, -66% cache reads, 0-token catgirl rendering.
DSH model and provider plugins connect DeepSeek Harness to additional model backends, or change how requests are routed between them. They matter when you want a local model, a second vendor, or cost-based routing.
Repositories with traceable evidence of a DeepSeek Harness relationship. They have not been reviewed, install tested, or security checked — the signal below each one is the whole of what the registry currently knows.
A token-efficient persona runtime for DeepSeek Harness. 把人格留在界面,把智能留给模型。Measured: -67% input tokens, -66% cache reads, 0-token catgirl rendering.
DeepSeek Harness 个人自研插件集:上下文罗盘 / 跨会话知识 / 子代理模型路由 / AI 生图(Personally developed plugins for DeepSeek Harness)
DSH agent-fleet hygiene audit plugin: credential-file permissions, embedded git-remote credentials (masked), provider token literals. Read-only, zero-dependency, deterministic.
DeepSeek Harness (dsh) plugin — tokensforce gateway integration: one-login onboarding, provider groups, and a usage dashboard tab
DeepSeek Harness LLM provider that runs your installed Claude Code CLI as the model backend — no API key.
⚡ DeepSeek Harness 自定义模型增强插件:在配置第三方提供商时,自动从权威模型库补齐上下文大小、Token 上限、视觉多模态输入与思考强度档位。
Connect your sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and a settings page.
DeepSeek Harness Web UI plugin: adds a 'Release GPU' button to free VRAM by unloading local Ollama models
DeepSeek Harness 第三方 API 与自定义模型设置插件:支持请求头、User-Agent、模型列表、图像输入和思考等级 | WebUI plugin for third-party APIs and custom models with request headers, image input, and reasoning levels
DSH 插件:让模型始终用中文进行内部推理与思考(think in Chinese)。
Computer Use 插件:虚拟鼠标真人操作 for DeepSeek Harness(screen_observe + computer_click 等 11 个模型友好工具,跨平台 cua-driver 引擎)
Vendor logo seat in the DSH web composer: shows which provider serves the current model, live from the official per-session ModelDirectory.
输入框文件引用插件:在 DeepSeek Harness Web GUI 输入框里像 Kimicode/Cursor 那样,输入 @ 弹出可搜索、可逐级下钻的文件选择面板,选中后把 @相对路径 回填进输入框(保留 @、末尾一空格),让模型按路径读取该文件。
DSH command plugin: adjust LLM provider retry count (maxRetries 0-20) via /retry-count
模型账户余额悬浮窗插件 for DeepSeek Harness Web GUI — floating model-account balance monitor with a settings master switch
Built-in translator plugin for DeepSeek Harness (DSH): multi-language, multi-model streaming translation, document import (PDF/DOCX/PPTX/XLSX/text), translation history, Markdown preview.