Plugins

Watches installed DSH bundles for load failures and dependency drift, brakes repeatedly failing tools, and attributes token cost per message source.

Shows and loads Qwen (qianwen*) skills only when the session runs on the Qwen Token Plan CN provider, and hides and blocks them on any other provider.

Back up and restore a whole DSH environment (installed plugins, DSH and plugin settings, skills, sessions and explicitly registered workspace files) into one private GitHub repository. Multiple machines share a single repo through per-device namespaces that never overwrite each other, and a pull can restore from this device, the latest backup or a chosen device. Push previews a read-only plan before writing, pull backs up local data first, secret-looking settings are redacted and key files are never uploaded. It calls api.github.com with the GitHub token you save in the panel (kept host-side only); its HTTP routes (/one-pack/api/...) require DSH browser auth.

Connects all seven Qwen Token Plan Harness-entitlement MCP services (enhanced search, web fetch, code interpreter, vertical search, image, TTS, ASR) plus the decision-model-preview model (qwen_decide) as native tools, with a per-service on/off and live-status panel.

Multi-chain wallet tracker: keep a named book of Solana, EVM and Bitcoin addresses, see balances, prices and estimated FIFO PnL per wallet or combined, and open any token for its chart, latest trades and top holders. Wallet addresses are sent to public data services (DexScreener, Jupiter, GeckoTerminal, Solscan and similar) to fetch balances, prices and trades.

Confluence and Jira over Atlassian remote MCP as a configuration-only bundle: one MCP client row, OAuth handled by mcp-remote with the token cached in ~/.mcp-auth, no login command and no in-app UI. Exposes mcp__atlassian__* tools (CQL search, pages, comments, JQL issues, transitions).

Auto-continue a stalled turn: re-prompt after an empty turn, a max-tokens cutoff or a listed model error, and switch to a healthy backup route before retrying.

Session rotation for long conversations: when a session reaches its step budget, at the end of the turn the plugin opens a new session in the same workspace, posts a handoff summary it assembles itself from local session events, and archives the old one immediately or after a retention window. Per-workspace step limits, a minimum-steps floor, a cooldown, a rotation cap and a dry-run switch are configurable in the settings page, and the summary is built with no model call.

Unofficial Qwen Token Plan provider: registers a `qwen-token-plan-full` route with a model catalog fetched from the gateway, Responses and Chat Completions protocols, server-side built-in tools, image and video generation tools, and per-entitlement budget tracking that disables a benefit once its quota is exhausted.

Standalone usage statistics panel for DSH, derived from HaoyueQin/dsh-usage-statistics-panel by HaoyueQin (MIT): per-session breakdowns with model drill-down, per-row cache hit rates, an all-time range and CSV export.

Device-wide token usage on the Settings Usage page: Chat and Code cards with input, output and cache rows, a daily token chart that groups by scene or by model, and a per-model table that merges providers, all folded read-only from the local session logs.

Predict a task's steps, tokens, duration and cost from this machine's local session history, with a local price table for cost estimates. Read-only, local-only.

Shows each conversation turn's cost and the running session cost in CNY or USD, with a session budget pill in the composer, balance reminders, an all-session billing dashboard and Excel export.

A balance and usage card at the bottom of the sidebar: DeepSeek account balance, today token count with input, cache and output breakdown, this session tokens, and the last error when a fetch fails.

Disk, CPU/memory/GPU, listening-port and token-usage cards with a full-page zoom; runs as a workbench module or standalone. The port card works on Windows only and the GPU card needs nvidia-smi.

Homework helper for the AI Passport device: turns homework screenshots into a checklist with per-task countdown timers and push-to-talk, plus a parent dashboard. It runs its own HTTP server on 0.0.0.0:8787 by default so the device on the same Wi-Fi can reach it: the parent dashboard only accepts connections from this computer, and a device needs a token issued after you approve its pairing code.

Test configured DSH models with connectivity, behavioral fingerprint and a local 18-item weighted intelligence battery scoring 0-100 with a tier and per-question evidence, plus animated or custom SVG probes, quick SVG limits, concurrency controls, and latency and token metrics.

Recolours and re-lays-out the DSH Web GUI as Tencent WorkBuddy desktop does: mint brand #00c29a, gray sidebar, 24px composer with a single hairline border, 848px column. Values are read from WorkBuddy v5.0.2 asar tokens, not eyeballed; light mode only, pure CSS, restores by removal.

Shows the current conversation's cache hit rate and per-request token details in a fixed DSH sidebar entry.

Monochrome MiniMax Token Plan radar: a sidebar readout with the 5-hour and weekly window remaining and both reset countdowns, plus a dashboard with tokens spent on this machine by day and by model and the pay-as-you-go cost estimate.

Shows a Kobe iced-tea side popup and reports per-turn costs or token counts with bundled offline audio. Uses dsh-cost-meter first, or estimates each request from native usage and public prices. Includes twenty cost phrases, four token phrases, CNY/USD, three-decimal rounding and custom previews; no runtime TTS service or API key. The bundled voice clips are pre-synthesized offline and the portrait is a fan-made image; the package declares UNLICENSED. When it has to estimate a cost itself it fetches a public price table from raw.githubusercontent.com (Han-1413141/dsh-cost-meter) and the USD/CNY rate from open.er-api.com, at most once a day, and sends no session data.

A fork of dougen/dsh-deepseek-usage (the upstream repository has no license file; its manifest declares MIT) that adds IKunCode account balance queries alongside the upstream provider readers, subscription usage windows and model price snapshots. For IKunCode, your key is sent as a Bearer token to api.ikuncode.cc. It installs as @elsebit/dsh-deepseek-usage-extended from GitHub Releases with its own routes and settings, so disable the original usage plugin if you want a single card; the OAuth credential references it inherits are shared with the original.

Account balance chip beside the Harness mark, per-session spend beside each Session row, and a sidebar-foot list of what running sessions are spending — all priced from each session log's token usage, with a live ≈ estimate while a call is streaming.

A floating whale-girl pet for DeepSeek Harness that shows the live account balance and per-minute token spend.