Plugins

Model quality testing for DeepSeek Harness Desktop with a question bank, manual and scheduled checks, saved responses, human reviews, and model attribution. Install it into the desktop profile: the shared Go backend is started only by the desktop app, and a web profile can only view an already-running desktop backend.

EVA cel-shade skin for the Harness Web UI. Overrides the --dsw-* design tokens to give panels square corners, ink outlines, hard offset shadows and CRT scanlines, adds a three-state session rail (running, done, waiting on you), recolours the turn-navigator ticks, and can embed an optional dark backdrop image.

Realtime ocean skin for DeepSeek Harness, rebuilt from d-dev0101/open-sea-skin 1.2.7 under MIT. Wave height follows the live session load, the sky comes from a local NOAA ephemeris, the star field is a real 2851-star HYG subset with 88 constellations, one boat per running subagent, plus a searchable 11-group settings panel and three quality tiers. It reuses the upstream package name "open-sea-skin" and the same bundle id, so uninstall d-dev0101/open-sea-skin first — the two cannot be installed side by side.

Adds the real CNY cost of each assistant turn, plus today's running total, after the timestamp in DeepSeek Harness's completed-turn footer. Amounts are folded from the session log's usage with a local price table - no billing API, no network call, no extra tokens.

Floating photo companion for the DSH Web UI with a 15/25/45/60-minute focus timer, water and stretch reminders, Open-Meteo weather, and a session radar listing running, ended, input-waiting and permission-requesting conversations for one-click navigation.

One Windows desktop shortcut for DeepSeek Harness: it opens the authenticated UI when the harness is running and starts it with no console window when it is not, with the same open, restart and close actions in a sidebar panel.

Two columns for the dsh Plugins page, Minecraft resource-pack style: the left column holds the packs running together, the right holds packs that are installed but switched off, with arrow or drag moves between them, custom tags, search, scope filters, batch toggling and undo. Tags and display names live in a hand-editable packs.json under DSH_HOME instead of browser storage, so they survive a new browser or cleared site data.

The mobile client for DeepSeek Harness: use the DSH running on your computer from your phone. The Android app signs in with the same account, picks this computer from the device list and opens its DeepSeek Harness UI on mobile. The desktop plugin handles registration and the connection, and nothing on the computer needs an inbound port. The UI adapts on its own: on a phone it becomes a touch-friendly layout, and returns to the desktop layout when a foldable opens or the window gets bigger. A PC-side panel shows login state, device quota, device list and the app download QR code.

Clears four kinds of idle-only system notices (approval policy, working directory, plan mode, plugin changes) that DeepSeek Harness counts as active work, so quitting with no running tasks no longer warns about interrupted work.

Tells the parent agent when a subagent died from an upstream failure instead of finishing: it listens to agent/error on every agent, waits a short settle delay, and if the child is still not running delivers a followup turn to the parent carrying the child id, the failure and the options the parent has, with a cooldown and a per-child cap so a flapping provider cannot flood the parent.

Skill management panel inside DeepSeek Harness settings: lists global and per-project skills, marks whether the running DSH actually loads each one, offers one switch that controls both model and slash-command invocation, previews and edits SKILL.md with the chat UI markdown renderer, and creates, imports (folder or zip) or deletes skills into a recovery folder. It only reads and writes the local skill roots (~/.dsh/skills and <project>/.dsh/skills) through its own Host routes behind the DSH Connection trust fence; no telemetry, no outbound requests, no credentials.

MCP hub for 1C development: keeps 1C:EDT connected through EDT-MCP, starts BSL Language Server with workspace roots on demand, and adds per-project settings, a read-only documentation wiki, model rules and SonarQube/GitLab skills. Requires 1C:EDT 2026.1/2026.2 with EDT-MCP running (default 127.0.0.1:8765).

Per-session fast-delivery mode from the composer. New conversations start enabled; switching is refused while that conversation is running, and a read-only session-header badge shows on/off during a run. One switch drives three subsystems: a circuit breaker that short-circuits test and build commands instead of running them, an apply_patch tool that writes SEARCH/REPLACE hunks atomically (all anchors must match or nothing is written), and a dehydrator that trims terminal output to a pass line or the last 15 error lines.

Pauses running DeepSeek tasks when peak billing starts and automatically resumes them after the off-peak window begins, with model-aware guards, an off-peak planning queue, and a sidebar countdown clock.

A password lock screen for DeepSeek Harness so passers-by cannot see a running session while you step away.

Adds a per-session notebook with autosave, a draggable key-information panel with collapsible items and queue injection, notebook and key-information inheritance for native and /fork forks, workspace-scoped session groups, session highlighting, running-workspace prioritization with a blue spinner, and close-current/left/right/all actions on every right-sidebar tab.

General-purpose chat agent on a parent agent + worker sub-agent split, for DSH Desktop only: a sidebar row opens each assistant's long-running conversation, where the parent chats, records schedule, lists, memos, logs, profile, persona and projects as plain files in that assistant's workspace folder, and hands other work to background workers through the bundled complete-subagent, picking each worker's model from the ones you enable and approving their write access. A heartbeat wakes it for reminders, a daily brief and wake-ups it sets itself, and holds back during quiet hours. Through the bundled im-robot it chats over WeChat: the model decides per reply with im_route whether the reply also goes to WeChat, and images and files sent from WeChat appear in the conversation and stay in the workspace's IM/WeChat folder for a set number of days. Its tools never appear in normal sessions.

Drive the installed ego lite app from DeepSeek Harness: 20 structured ego_app_* tools over the official ego-browser CLI, running inside real ego TaskSpaces.

Map a remote server directory over SSH and SFTP into a controlled local cache workspace, so the model, agent, session and memory keep running on the local machine.

A settings-tab workshop plus the cordis-plugin-development skill it hands to the agent, for writing DSH plugins against the running host API.

Streams a running Godot game into a DSH sidebar panel as MJPEG by driving a native Godot process, so Forward+ projects and GDExtensions keep working. The panel can start, stop, capture and fullscreen the view and inject clicks, and the agent gets tools to read status, drive input and take screenshots.

File-based task pool and dispatcher for DeepSeek Harness: keeps a P0-P3 backlog as Markdown, hands one task at a time to a background subagent, gates delivery by rerunning the project test command, and accepts the result against a git commit or a file snapshot; git and non-git directories both work.

External one-shot subagent provider using the local CodeBuddy CLI over ACP, with background result delivery and steering of running children.

Injects the non-obvious operating rules of Agent Teams into the Lead session through one ordered system-prompt section: plan the roster before spawning, roster slots are never released, write scopes are advisory, and wait_agent short-circuits when no peer is running.