Plugins

Loads Claude-style plugins into DeepSeek Harness (dsh): discovers skills, commands and optional SessionStart hooks from Claude plugin directories, with hot command reload and uninstall cleanup.

Always-on ADHD-friendly output shaping: one system-prompt section makes replies action-first with numbered steps and concrete time estimates; adhd_on / adhd_off / adhd_status tools persist the mode across restarts.

Configurable VS Code style keyboard shortcuts for the DSH web GUI, with a settings-page keybinding editor, conflict detection and JSON import/export.

Antigravity-style run_command for DSH: short commands return inline within a configurable wait window (default 10s) while longer ones auto-promote into ctx.jobs for later collection and completion notices — executed via ctx.shell under the session sandbox and approval pipeline.

User message jump bar for the DSH web GUI: a minimap-style dash strip on the right edge of the conversation, with hover preview, click-to-jump, drag-to-scrub and a viewport marker.

Drag-and-drop file attachments as Codex-style cards, with in-app PDF/text/video/audio previews and system-default opening for other formats.

Codex-style /side side conversations for DeepSeek Harness: a temporary fork of the current chat in a floating panel, inheriting context without interrupting the main task.

Adds a Codex-style message navigation rail for quickly locating earlier prompts in long DeepSeek Harness Web UI conversations.

Codex-style message timeline navigation for DSH web clients: hover to preview a message, click to jump to it, and the currently-read turn stays highlighted.

Youdao-style word-selection translation for the DSH web GUI. Select text anywhere, click the floating button, get a translation from the harness's own LLM — no API keys, no third-party endpoints. 有道风格划词翻译：DSH Web GUI 里划选文本即现悬浮「译」按钮，点击由 harness 自带大模型翻译，无需

LLM debug console for DeepSeek Harness: captures the full content of every model call at the llm/stream waterfall (options, stream chunks, usage, wire protocol) and shows it in a DevTools-style docked panel, with shared-prefix context diffing, wire-JSON reconstruction, JSON export and a runtime-tunable capture policy.

macOS desktop shell for the DSH web UI: a plugin plus a small Tauri/WKWebView window over the loopback web surface — real macOS fullscreen, single instance, external links delegated to the system browser, and browser-style zoom.

Independent Codex Guardian-style approval reviewer for DSH.

DeepSeek Harness compatibility plugin for third-party OpenAI-style gateways: tolerates SSE streams that close without the [DONE] sentinel after a complete reply.

Codex-style Git workbench: workspace-scoped changes, diff, stage, commit, guarded branch operations, graph history, fetch, fast-forward pull, and upstream push through official plugin APIs.

Codex-style session archiving: hovering a sidebar conversation row reveals an Archive icon at the far right; one click archives the session via the official workspace archive API.

Desktop-style UI enhancements for the DSH Web client: adaptive wallpapers, a desktop pet companion with an activity feed and feeding economy, @file workspace references, and the resizable file/preview right panel.

Session repair button in the conversation header: detects & fixes session-log corruption — tool-call id swaps, empty call ids (`message must have tool source`), unknown event types from disabled plugins (marks `ignorable`), torn zstd tails, missing final-frame newlines; ghost-style UI, auto-backup before writes.

Codex-style token usage panel: whole-instance cumulative/per-session peak tokens, longest chat & streak, daily/weekly/cumulative activity heatmap, and plugin/skill Top5.

A dsh desktop bundle: an Electron shell over the dsh Web UI with a system tray and a dsh-styled custom title bar.

Codex-style context visibility for DeepSeek Harness: live context-window occupancy, composition breakdown, KV-cache hit rate, and a GitHub-style 53-week usage heatmap

Codex-style approval autopilot for DeepSeek Harness: ordered glob rules (allow/ask/deny) plus an AI risk judge (low/medium/high) mapped through a risk tolerance, as an approval answerer.

A desktop-style project and AI workbench for DeepSeek Harness

Aseprite-style pixel art studio: the AI draws sprites stroke by stroke with selections, layers, animation frames, gradients, symmetry and reference layers, each step rendered live as ANSI terminal frames.