插件广场

输入框旁一键提示词增强：把半成品草稿原地改成可执行的提示词，只改不发送。

DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开，请查看署名要求部分

dsh-purge 社区适配版：上游已停更，这里让它继续跑在 DeepSeek Harness 0.2.1-rc.2 上（基于 1.1.72）

DSH稳定高效的破甲插件： 常驻1,597token +零宿主补丁（可与dsh-purge共存）+ 三层技能路由+ 分级 prefill + 拒答自我强化阶梯+ finish_reason 四路分流 状态查询: /flash light

将 Qoder（国内版/国际版）以 PAT 接入 DeepSeek Harness —— 侧栏额度展示、上下文窗口切换、模型自由开关、每日自动签到。Qoder CN & Global models for DeepSeek Harness via PAT. 支持 DSH 0.2.1-rc.1+。

"🐳 Dsh-Quant: The Everything-Plugin Ai native Quant OS "

DSH 插件：在对话里调用本机 ComfyUI，用千问 Qwen-Image 2.1 出图。纯本地、不出网、不需要 API Key。

DSH适用的大肥鱼跑步思考强度滑块。Codex-style model and reasoning-effort slider for DeepSeek Harness

dsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).

DSH插件「DSH-Think-zh」 ：为利于中文使用者阅读推理过程、复核结论；在设置添加切换模型思考语言档位[简体中文/默认英文]；回复语言跟随提问语言，代码与标识符保持原文。

A DeepSeek Harness plugin for reasoning-effort defaults and protocol-aware gateway compatibility settings for llm-pi-ai models.

DeepSeek Harness 提示词破限插件：通过系统提示词解除模型回答限制，深度适配 Web 与桌面端多模式及工具调用

Scene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.

Near-native image understanding for DeepSeek Harness

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

DSH voice input plugin: tap or hold Alt to talk, text lands in the composer. Local SenseVoice ASR by default — offline, zero config, zero key. Auto-fallback to browser Web Speech, optional OpenAI-compatible ASR chain, polish via DSH models.

将 WorkBuddy 桌面 App 包含的模型自动接入 DeepSeek Harness，零配置使用。Bring the models in the WorkBuddy desktop app into DeepSeek Harness with zero configuration.