AI Agent Hub
Back to plugins
🖥️

dsh-token-usage

Client Updated 2026.08.17

Run the following command in DeepSeek Harness:

dsh plugin install az7627/dsh-token-usage

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

In DeepSeek Harness, please run the command dsh plugin install az7627/dsh-token-usage to install this plugin. Source: https://github.com/az7627/dsh-token-usage

About this plugin

In the DeepSeek Harness Web conversation view, tracking long-term token consumption can be obscure and difficult to grasp intuitively. The dsh-token-usage plugin is designed to solve this pain point by visualizing dispersed usage data, allowing you to clearly insight into resource consumption for each conversation turn.

This plugin offers powerful analytical capabilities, featuring stacked bar charts that segment tokens into Cache Read, Input (including Cache Write), and Output. You can flexibly adjust time granularity and range, from the fine-grained 15-minute level to full-day spans, viewing trends over the last 7 or 30 days. Powered by the ECharts visualization engine, with local timezone alignment and precise tooltips, it ensures a professional and intuitive data presentation.

Whether you are a developer, researcher, or a user sensitive to AI costs, this plugin is an essential tool for enhancing session management efficiency. It generates data directly from session log replay without extra API calls, enabling you to easily review conversations after the fact, optimize prompt strategies, and achieve more efficient resource utilization.

Use Cases

  • View daily token consumption trends
  • Analyze cache hit rates and optimization strategies
  • Compare input/output ratios across sessions

Best For

  • Users who need precise management of AI costs
  • Developers dedicated to optimizing Prompts
  • Researchers studying model efficiency and data consumption