Plugins

Centro global de skills para dsh: agrega skills de Claude Code, del proyecto y de .skill-package en ~/.dsh/skills, con importación por referencia o copia y uso mediante el menú de barra

Plugin de DeepSeek Harness: consulta el saldo/uso de AI Monitor desde SQLite local; un agente consciente de los costes, con contabilidad automática mediante el proxy de AI Monitor.

Monitor de uso de DeepSeek para DeepSeek Harness: consulta de saldo de cuenta y resumen de uso de tokens como herramientas invocables por el modelo.

Saldo y uso de sesión en vivo para la interfaz web de DSH: botón de saldo en la cabecera (a la izquierda de Session log), desplegable con el saldo de la cuenta, desglose de tokens en tiempo real (fallo/acierto de caché, escritura de caché, salida), tasa de aciertos de caché y estimaciones de coste con tarifas oficiales y cambio automático punta/valle.

Saldo de la API de DeepSeek, tendencia del saldo y gráficos de uso diario en los ajustes de DSH Web.

Un panel flotante de comandos que muestra todos los comandos de barra de DeepSeek Harness como botones ejecutables, ordenados por uso.

Per-session LLM cost meter for the DeepSeek Harness Web UI: folds provider usage into uncached input / cache read / cache write / output per model and prices it against DeepSeek and Xiaomi MiMo pay-as-you-go rates (DeepSeek peak-idle tiering included).

Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.

Realtime model usage panel: tokens, cost, requests, trend and composition, with editable pricing.

DSH 用量与余额：会话用量、按每笔实际发生时刻与模型计价的费用（峰谷/档位）、账户余额；账号登录无需 API Key。

Fireworks celebration engine: floats fireworks above the chat window while the agent codes — welcome show, per-turn salutes, tool sparks, milestone celebrations, a finish finale and a dud on failure; each event type has its own fireworks card group with random variants, and token usage decides firework size, height and splendour.

精准 Token 洞察，实时追踪，智能优化提示和用量归因 Sharp token insights, real‑time tracking, smart optimization signals & attribution

OpenCode Go provider for DeepSeek Harness: live gateway catalog, per-conversation session header, usage

Track token spend and enforce budgets for every model call your dsh agent makes.

Adds a whole-corpus usage statistics page to DSH with daily and cumulative tokens, cache hit rate, per-model breakdown and a year-long activity heatmap, all read from the provider-reported usage.

Shows the remaining OpenCode Go quota (5-hour, weekly, monthly) in the DeepSeek Harness Web composer dock.

OpenCode GO quota widget pinned to the sidebar, with rolling/weekly/monthly usage bars, an elapsed-versus-remaining time bar under each, a same-origin usage proxy, an /opencode-go command, and the runtime x-opencode-session fix for GO gateway chat requests. Fork of yumusb/dsh-opencode-go-usage.

OpenRouter provider that reads the live /models list, so new models appear without a harness release: models sorted by name with input/output prices, per-model reasoning levels, image input, reasoning_details replay, Anthropic prompt caching, and actual spend per session including subagents from OpenRouter usage.cost, shown under the Web UI composer and by /cost.

DeepSeek Harness 的用量徽标插件：侧边栏底部一行显示当天的 token 总量与估算费用，点开可看 24 小时 / 近 7 日 / 近 30 日 / 近 12 个月 / 按年用量，按 provider 筛选，并按 DeepSeek 官方定价与中国法定节假日计价。A usage badge plugin for DeepSeek Harness: today's tokens and estimated spend in the sidebar, with 24h / 7d / 30d / 1

OAuth sign-in for 9 subscription LLM providers (Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE) with zero-config login and usage dashboards.

Maintained fork of feibi-mochi/deepseek-harness-control-center, which has not been updated since 2026-09-09. Pricing follows the official model pool instead of a hardcoded model prefix, so DeepSeek V4.1 Flash (`deepseek-flash`) is billed and shows its peak/off-peak clock, and the official price page is parsed structurally so a renamed or retired model no longer stops price sync. Adds an English interface beside the original Chinese. Otherwise the same plugin: balance, per-session cost and token breakdown, a 24-hour peak/off-peak clock, Z.ai plan quota, and a local usage ledger, following the host light/dark theme.

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.

Tracks API token usage and estimated costs with per-route model pricing, optional billing groups, synchronized CNY/USD display, session reports, composer totals and a clickable daily sidebar total.

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.