Plugins

Collapsible in-conversation interactive terminal with multi-tab live shells, auto-reconnect, one-click quick commands, and a bilingual UI that follows the theme.

Sidebar conversation anchor navigation: one anchor per chat node (user / assistant / tool / command) with role badges and summaries, click to smooth-scroll to that message; live-refreshes with the session.

Codex-style token usage dashboard: five stat cards, GitHub-style activity heatmap (daily/weekly views), insights & model ranking; persisted snapshot with incremental sync, survives session deletion.

Installed-plugins README summary panel: floating 📖 button, zh-preferring titles, default-all-expanded READMEs, blue circular index badges, per-plugin one-click update (`dsh plugin update`) via a loopback endpoint.

8 curated color schemes plus custom palette import (name + scheme + seed colors derive a full token map), a Palette row in General settings, hot-plug install.

System parameter adjustment UI: grouped settings page for timeouts, parallelism, LLM retry policy, model params, web search, permissions and presets; safe profile-config editing with line-level YAML matching and post-write validation.

Chinese localization for tool results: intercepts tool execution output and translates English markers (`[exit code]`, `[timed out]`, `[sandbox: ...]`, etc.) into Chinese, with a settings toggle.

Splits the composer model selector into a searchable, favorite-marking dropdown and a reasoning-effort slider, with Ctrl+P / Ctrl+T quick-switch shortcuts.

Rewrite the current composer draft through an auxiliary LLM call without sending a message.

A super-simplified LLM-wiki memory plugin: one index document (auto-loaded) + one markdown file per topic (read only when needed) — no dumping everything into the context and burning tokens. Simple and lightweight, painless to install/uninstall, and freely editable however you like.

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.

DeepSeek Harness 会话删除插件：设置页管理归档会话，真正删除磁盘日志（回收站可还原）+ 批量清理——官方归档只隐藏不删盘，这里补上。

dsh-netease-music-plugin

DSH 网页版网易云音乐播放器插件：顶部条迷你播放器 + 展开面板，扫码登录，支持 AI 对话控制

Standalone configurable MSYS2/UCRT64 and Git Bash executor for DeepSeek Harness, with global or per-preset activation

用于DSH的对话框任务音效，以及个性化聊天背景||Dialog box sound effects for DSH, as well as personalized chat backgrounds.

DeepSeek Harness 侧边栏用量仪表盘插件：跨会话 token / 模型 / 活动统计、按会话明细与可选时间尺度的用量趋势图。 Usage dashboard plugin for DeepSeek Harness web: cross-session token, model, and activity stats with a per-session table and a windowed trend chart.

DSH plugin-manager-ui: MCP/Skills management + plugin stop/enable/delete. Derived from liqichen/dsh-plugin-manager (MIT).

DeepSeek Harness 皮肤扩展插件 Skin plugin

Claude Science-style AIDD research workbench for DeepSeek Harness — ReAct research loop, versioned artifacts with provenance, and 17 skills for virtual screening, molecular generation, ADMET prediction, DTI modeling and model reproduction.

专为 DeepSeek Harness 打造的一键发布工具：一条命令即可把本地插件发布到 GitHub，自动添加 dsh-plugin 话题并生成中英双语 README。| One-command publishing for DeepSeek Harness: publish local plugins to GitHub with a single command, including the dsh-plugin topic and a bilingual README.

帮助寻找DSH插件，引导安装，并持续在DeepSeek Harness内收集插件评分、FAQ、踩坑记录并分享到社区