Plugins

Smart session titles for DSH: after each conversation turn an independent auxiliary LLM call summarizes the full user+assistant transcript into a title that follows the session's real topic instead of echoing the first message; the first message is titled instantly, failed built-in titles auto-retry on later turns, manual renames are never overwritten, and subagent/fork sessions are skipped.

WSL (Windows Subsystem for Linux) bridge for DeepSeek Harness: run Linux commands, manage distros, convert paths, and copy across the Windows/Linux boundary.

One-click update for the self-built Linux dsh-desktop: check fork releases, download the deb, swap the app and restart.

Durable, reversible installer that patches DSH Desktop session-reference UX — workspace-prioritized @ candidates, title-first display, two-line menu layout, and sidebar drag-to-composer session references.

A xiuxian (Chinese cultivation-fantasy) world where agents create a cultivator and play through 16 tools - cultivate, roam 22 areas, delve 8 dungeons, chat with 4 builtin NPC cultivators - and on exit export a self-contained HTML replay plus a Markdown journey diary, fully offline with zero servers.

Computer use through an external USB HID device: name a target in plain language, a vision model locates it in a cropped window screenshot, and a Raspberry Pi Pico 2 moves the real mouse and types on the real keyboard. 7 tools. Windows has window listing, per-window cropping and automatic window raising; macOS needs pyobjc and has neither; Linux is unsupported.

Linux X11 computer use for DeepSeek Harness: 9 tools (screenshot, move/click/drag/scroll mouse, type, key combos) driven by a zero-dependency Python XTest helper — native-pixel coordinates, per-action verification, optional auto-observation screenshot.

跨平台 AI Skills 统一管理器：以 ~/.agents/skills 为中心技能库，通过系统符号链接把同一份技能一键安装/卸载到 Claude Code、Cursor、Codex、Gemini CLI、Trae、Windsurf 等多个 Agent 工具，仅展示本机已安装的平台，统一管理本地技能目录与只读平台展示。支持 Windows / macOS / Linux。DeepSeek Harness plugin.

DSH plugin: an unattended AI software team. Feed it a bare Linux server, a set of secrets (env-var references only) and a git remote, and the plugin-driven AI team drives the whole project lifecycle — environment bootstrap, scaffolding, task decomposition

Persistent tmux control-mode cockpit for DSH Web that mirrors native panes in a dock.

DeepSeek Harness mobile: CSS-only UI plugin, password-protected Cloudflare tunnel and a tiny Android WebView app - use DSH on your phone.

Web UX kit for DeepSeek Harness: hover session actions and a large model picker, with more surface polish to come.

Daily cost card for your local LLM gateway: /usage reads gateway_usage.jsonl and itemizes spend per model and per hour, covering official direct, OpenRouter relay, and in-plan metered pools.

Linux crontab-style scheduled tasks for DeepSeek Harness: the LLM can schedule recurring workflow runs and prompt-driven tasks with cron expressions, plus proactive task suggestions inferred from the chat.

DeepSeek Harness SSH plugin for AI remote development: run commands and read, write, or browse files on Linux and Windows servers.

Writes text to the system clipboard, cross-platform (macOS/Windows/Linux).

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

FAL image generation for DeepSeek Harness: a generate_image tool backed by the FAL queue API (default model fal-ai/flux-2/klein/9b). Images render directly in the conversation, are saved to the workspace, and all settings are editable from the Web GUI.

System-level desktop notifications: turn-completion and workflow-end banners, plus a modal alert when an approval is needed (macOS osascript / Linux notify-send).

Desktop notifications and tones when a task finishes, waits for approval, or errors — native on macOS, Windows and Linux with zero runtime dependencies.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Free-interval session reports with AI-narrated daily/weekly digests over any date range, plus every-N-days scheduled reminders with system notifications (macOS / Linux).

Conversation-style UI/UX visual review plugin for DeepSeek Harness: vision_review / vision_ask tools backed by any OpenAI-compatible multimodal endpoint (e.g. agnes-2.5-flash)

Take control of your tmux panes: list/send-keys/capture, run long jobs in a pane with watch mode, and approval-gated destructive commands.