dsh-token-monitor
Run the following command in DeepSeek Harness:
dsh plugin install zhangzheng25/dsh-token-monitor
Paste the following prompt into your AI chat to install this plugin:
Install the plugin in DeepSeek Harness using the command `dsh plugin install zhangzheng25/dsh-token-monitor` with full source at https://github.com/zhangzheng25/dsh-token-monitor.
About this plugin
When using DeepSeek Harness for AI interactions, users often struggle to track token consumption in real time, which can lead to unexpected overages or wasted resources. The dsh-token-monitor plugin addresses this by adding a 'today's usage' card at the bottom of the sidebar, allowing users to monitor daily token totals at a glance without navigating away from their workflow.
Its core capabilities include a clickable statistics window that displays today's, 7-day, and 30-day token totals, along with a 30-day stacked usage chart by model and a model usage ranking. Additionally, it offers session statistics, showing conversation counts and request frequencies over different periods. All data is automatically persisted and refreshed every 30 seconds, ensuring accuracy and timeliness, with history backfill to cover usage before installation.
This plugin is ideal for developers, AI researchers, and team managers who regularly use DeepSeek Harness. It helps them monitor resource usage, optimize interaction strategies, and manage costs effectively. Whether in personal or collaborative settings, users can benefit from intuitive usage visualization to make informed decisions and enhance productivity.
Screenshots
Use Cases
- Monitor daily token usage in real time to prevent overages
- Analyze 30-day per-model usage to optimize model selection
- Track session statistics to understand interaction patterns and resource allocation
Best For
- Developers who frequently use DeepSeek Harness
- Team managers who need to manage AI resource costs
- AI researchers focused on token consumption and efficiency
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.