AI Agent Hub
Back to plugins
dsh-shanhai-stats preview

dsh-shanhai-stats

Web Tools Updated 2026.08.25

Run the following command in DeepSeek Harness:

dsh plugin install cn-zhangpeng/dsh-shanhai-stats

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install cn-zhangpeng/dsh-shanhai-stats in DeepSeek Harness to install this plugin, source: https://github.com/cn-zhangpeng/dsh-shanhai-stats

About this plugin

When you call multiple models through DSH every day, token spend is scattered across individual session logs. Figuring out monthly totals, cache hit rates, or which model burns the most tokens usually means digging through JSON and doing the math yourself. dsh-shanhai-stats turns that manual work into a ready-to-use usage dashboard inside DSH Settings, so your numbers are at a glance instead of buried in logs.

The dashboard delivers four panels: a summary badge row covering total tokens, cache hit rate, request count, and consecutive-use days; a daily four-segment token line chart (input / cache-read / cache-write / output) with toggles for today, 1-day, 7-day, and 30-day windows; a GitHub-style heatmap spanning the past 52 weeks with hover-to-reveal daily details; and a usage detail table switchable between per-provider and per-model views. All figures are aggregated directly from DSH session-log usage events, so the plugin never recalculates tokens and stays aligned with DSH's native accounting. Sub-agent sessions are included automatically, and the UI adapts to both light and dark themes out of the box.

It is built for developers who call multiple providers daily, want to track spend trends over time, gauge how well their prompt cache is working, or need a defensible basis for cost allocation across a team. Install the plugin, open Settings, and a continuously updating usage dashboard is there with zero extra configuration.

Screenshots

Use Cases

  • Monitoring overall token spend trends when calling multiple LLM providers daily
  • Evaluating cache hit-rate trends to refine prompting and caching strategy
  • Breaking down costs by model or provider for team-level monthly reports

Best For

  • Solo developers calling multiple LLM APIs at high frequency
  • Tech leads who track token spend and cache efficiency over time
  • Platform engineers handling LLM cost allocation and auditing for a team