Plugin

Cross-agent token usage dashboard: aggregates local conversation logs from Claude Code, OpenCode, Cursor IDE, DSH, OpenClaw, CodeWhale, Hermes and more into a persistent ledger that survives log deletion, with cache-hit rate, cost estimation, period comparison and day drill-down analytics in a sidebar panel.

Shows the active model's usage and remaining balance in the session header: OpenCode Go plan usage (rolling, weekly, monthly) with the selected model's monthly cap, Command Code 5-hour and weekly window usage with remaining credits, and DeepSeek account balance.

Extra LLM provider routes for DeepSeek Harness: OpenCode Go with per-session x-opencode-session routing, and OpenAI Codex over ChatGPT-subscription OAuth.

DeepSeek Harness plugin for querying LLM service provider usage: reads DeepSeek and Moonshot balances plus Kimi For Coding and OpenCode Go quota windows on the host and shows them in an always-visible card with three view modes, edge docking and a collapsed letter bubble.

DSH 插件（用量中心）：常驻用量卡片 · 多提供方用量/余额查询（OpenCode Go 订阅 + DeepSeek 余额 + Command Code 订阅/余额，对齐 cc-switch 查询语义）

Unified real-time quota dashboard: one collapsible glass panel for OpenCodeGo windows, DeepSeek balance, OpenRouter credits, SiliconFlow and Moonshot balances — auto-detects DSH credentials, host-side fetching (keys never reach the browser), custom providers via ~/.dsh/dsh-quota-hub.json.

Bring OpenCode Zen free models to DSH: 8 live-discovered providers with zero config, no API key; includes persistent quota tracker with rate-limit detection and reset countdown.

Free anonymous OpenCode Zen models inside DeepSeek Harness (DSH): native LlmAdapter, no API key, no child process; optional Go sidecar included

OpenCode GO quota and plan status panel for DeepSeek Harness: sidebar health light, quota bars, countdown timers, and in-app key management

AI Quota & Usage Monitor for DSH: real-time balance and reset countdown tracking for Codex, Cursor, Google Antigravity, and OpenCode-Go.

dsh plugin: bounded retry for gateway network_error failures the stock retry policy cannot classify (e.g. OpenCode Zen finish_reason: network_error)

Specialist subagent delegation preset (orchestrator + 5 roles: oracle/designer/fixer/explorer/librarian) that seeds itself into your DSH home — background-first delegation, JSON-driven models/effort/tool permissions, scoped MCP for research.

多智能体总指挥插件（DeepSeek Harness 原生版） ——让 DeepSeek 高效打开并指挥一个 claude / opencode / codex 智能体团队，实时看到每个智能体在做什么，通过共享记忆与任务看板编排多人协作。

Pools several OpenCode Go API keys and hot-switches each request to the least-used one, with official usage and balance lookup plus a graphical settings page.

Use OpenCode models inside DeepSeek Harness without a separate provider API key.

DeepSeek Harness plugin that shows the DeepSeek API account balance and OpenCode Go plan usage (consumption ring, hover details) in the sidebar footer, with adaptive polling and zh/en locale support.

Import chat history and memory from other AI agents (Claude Code, Codex CLI, Gemini CLI, Aider, Cline, OpenCode, Hermes Agent, OpenClaw) into DeepSeek Harness

DeepSeek Harness community Bundle for local, evidence-backed Agent Memory

Monitor delle quote per la GUI web di DeepSeek Harness: utilizzo del piano OpenCode Go + saldo/utilizzo dell'API DeepSeek, come finestra di monitoraggio trascinabile in basso a sinistra (il lato host fa da proxy per le API, le chiavi restano su disco)

Plugin di interrogazione dell'utilizzo del piano OpenCode Go: lo strumento opencode_usage interroga in tempo reale l'API ufficiale di utilizzo di opencode.ai (percentuale di utilizzo e orario di reset per le tre finestre rolling 5h / settimanale / mensile), con la API key risolta automaticamente dal file di autenticazione di opencode / dalle variabili d'ambiente / dalla configurazione del plugin, senza bisogno di login aggiuntivo

Badge di utilizzo del piano: mostra nell'angolo in basso a destra della finestra di dialogo web tre finestre di utilizzo — 5 ore / limite settimanale / limite mensile (supporta OpenCode Go e i due canali del GLM Coding Plan: versione internazionale Z.AI / Zhipu, oltre alla quota dell'abbonamento Kimi Code, con la quota mensile potenziabile tramite cookie kimi-auth), e offre in "Impostazioni → Plugin" interruttori di attivazione e configurazione della API Key indipendenti per ciascun canale