Плагины

Read-only session dashboard for DeepSeek Harness over the local ~/.dsh data: a sidebar overview of every session (tokens, estimated cost, turns, tool calls, model mix, daily activity, searchable and sortable session table) and an in-conversation Dashboard view that shows the current conversation turn by turn with per-turn tokens, cost, timing and tools. Zero dependencies, no network.

Adds a system-prompt section that asks the model to drop stock AI writing habits: subheadings, bold and emoji overload, quoted aphorisms and grand-finale endings.

Switches which assistant persona answers, based on how the message addresses it (alias matching, with names inside quotes and copula phrases such as "is/was" excluded); each persona is a folder holding its own prompt, aliases, colour, avatar and optional lore, several personas can answer one turn, and a settings panel plus a per-turn routing log make each switch checkable. Personas live under ~/.dsh/personas (deleting one in the panel removes its folder) and the routing log in ~/.dsh/persona-router keeps the first 60 characters of each message; its HTTP routes (/persona-router/…) have no DSH access check.

Runs sessions on your own Claude Code and Codex CLIs from the model picker, and lets a DSH agent hand background tasks to them and follow up. Permission prompts cannot be answered from DSH: Claude Code runs in acceptEdits mode by default, Codex in its workspace-write sandbox, and ACP permission requests are approved automatically by default.

Exposes the chat models of a locally signed-in QwenWork desktop app as a Harness provider, with a multi-account pool, session affinity and failover, pre-expiry credential renewal, a health watchdog, per-model enable/context-window/input-type settings, and account status with credit balance. Unofficial local integration that reuses your own signed-in client credential; your own account only. Windows only: needs the QwenWork desktop app signed in, and keeps its account pool in a DPAPI-protected file under %LOCALAPPDATA%. The author warns that reusing the client credential may conflict with the vendor's terms.

Connects the models of the SCNet (超算互联网) Computing Service desktop client to DSH, adding a per-model switches tab on the plugin page and adapting the transcript to whichever pi-ai generation the profile resolves. Reuses the API key the SCNet client cached under ~/.sclaw (or SCNET_API_KEY, or a key set in the plugin config) and sends chats to api.scnet.cn through a loopback proxy; it depends on SCNet's unofficial client interface, which may change, and use is subject to SCNet's terms.

Qwen mode for DSH: manages local GenieX and Alibaba Cloud QwenCloud providers, normalizes thinking and sampling, detects model capabilities, and shows per-turn latency and decode speed. Its bundle patch replaces the permission plugin's preset table with reply-only, read-only, workspace-write and danger-full-access (the last two as in stock), so any custom presets are overridden.

Connect a locally installed agy CLI to DeepSeek Harness 0.2.2-rc.1, with separate thinking levels, quota display, and Harness-owned tools. Community fork of dannndouglas/dsh-antigravity-acp, beta, verified on Windows x64 only. Needs the agy CLI signed in with your own Google account; installing makes new chats default to Agy models (messages go through agy to Google), switches web search to the agy provider and replaces the built-in compaction. Do not enable it alongside other forks that register the agy-local-acp provider.

A Desktop 0.2.2-rc.1 adaptation of DSH WebTokens that registers a signed-in Chrome DeepSeek web session as the deepseek-web model in DeepSeek Harness, with tool-call transport, reply validation, a Chrome bridge extension, plus install and rollback scripts. It cannot be installed with the one-line plugin add shown on this page: it needs its own installer (node scripts/install-desktop.mjs, which backs up the whole profile first). Prompts, project content and tool results are sent to the DeepSeek website through your Chrome session; the author has tested it on macOS only.

Runs a four-task, 150-point model intelligence benchmark inside DeepSeek Harness (Qin 60, Pompeii 45, Pelican 22.5, Candy 22.5): each selected model × reasoning-effort pair executes every task in its own isolated subagent session, Qin and Pelican are graded by the selected judge model against rubrics, Pompeii and Candy programmatically, and batches keep scores, artifacts and cost. Adds a 0–1000 real-world performance score per model × effort computed from local session logs across seven dimensions (output speed, first-token latency, reasoning speed, tool cadence, tool latency, tool success rate, cache hit), with baseline deltas and controlled speed runs, plus a sidebar page with ranking, performance, history and settings views. Each batch spends real tokens of the candidate and judge models, and candidate subagents get file and bash tools inside an isolated run directory.

Dark mecha wallpaper theme with graphite glass panels, drifting particles and a pointer-following spring mesh, with 16 adjustable settings and a one-switch return to the native look. The bundled Gundam wallpaper is not covered by the MIT license.

Windows 11 Mica, Acrylic and Tabbed backdrop materials for the DSH desktop window, with adjustable page opacity; a bundled app.asar patch makes the window transparent so the wallpaper shows through. Windows only. The transparency patch is a separate step you run yourself (node tools/window-bridge.mjs apply, with DSH closed): it edits the installed app.asar, keeps a backup next to it, and restore undoes it.

iOS-style appearance plugin: light, dark and auto modes, iOS system accent colours, night eye-care, OpenCode palettes and typography, and local background images with blur, transparency and rotation.

Ten Markdown-reader colour schemes for DeepSeek Harness that repaint the window background and the rendered Markdown typography, with a dedicated settings page to switch between them.

Arknights-style procedural opening film and silent looping chat backdrop for the DeepSeek Harness Web UI: Canvas-drawn visuals, synthesized WebAudio sound, click-anywhere skip, cross-dissolve into the interface, live-adjustable opacity; zero dependencies and no media files. By default the film (about 12 seconds, with sound) plays on every page load; a setting turns it off.

Shows the remaining MiniMax coding-plan quota (5-hour window and weekly window) below the chat composer, and keeps the profile's MiniMax model list current by appending newly released models.

Adds a recap card under the composer for the current session: turns, steps, tool calls grouped by name, the uncached / cache-read / cache-write / output token split, the cache-hit rate, and a cost range computed from the official Flash off-peak and peak list prices. Exports the same card as Markdown or a standalone HTML page.

Shows whether the DeepSeek API is currently billing at the peak or off-peak (half-price) rate in the conversation title bar, with a live countdown once the next switch is under 30 minutes away and the Chinese statutory-holiday calendar built in.

OpenDesign (AMR) quota readout: the Design Plan 5-hour and 7-day windows, wallet balance and days-to-exhaust in a composer pill, read over a local controlKey or a browser session. The local source reads the controlKey from ~/.amr/config.json; the browser source opens a temporary Chrome window, and after you log in collects the session cookie over CDP into DSH's credential store.

Rewrites a draft prompt against the current project: a composer button, slash command and agent tool ground the rewrite in the workspace stack, structure and conventions.

Per-session token, cost and wall-clock budgets that stop the model session at the limit, plus a DeepSeek peak and off-peak schedule.

OpenCode Go allowance bar under the DSH input box: the rolling, weekly and monthly percentages still left, plus a popover pace budget that turns each window into a per-day and per-week spend target and marks whether the current burn is ahead of that target or behind.

Gives the agent its own context usage through a context_usage tool plus one reading line per turn, with an editable template.

Records how long DSH is open each time and the running total in a left-sidebar page; a restart within 3 minutes continues the same use.