dsh-token-stats
Run the following command in DeepSeek Harness:
dsh plugin install MoonlitDropOfBlood/dsh-token-stats
Paste the following prompt into your AI chat to install this plugin:
To install the dsh-token-stats plugin in DeepSeek Harness, run the command `dsh plugin install MoonlitDropOfBlood/dsh-token-stats`. The full source code is available at https://github.com/MoonlitDropOfBlood/dsh-token-stats.
About this plugin
When using DeepSeek Harness (DSH) for model inference, users often find it challenging to visualize token consumption, especially when working with multiple models simultaneously. The dsh-token-stats plugin is designed to address this issue by seamlessly integrating into the DSH web UI and providing a dedicated 'Token Statistics' page that offers clear insights into usage details for each model.
The core strength of this plugin lies in its comprehensive visualization capabilities. With stacked bar charts, you can view daily token consumption per model over the last 7 or 30 days; pie charts clearly display the proportion of total consumption for each model; and a GitHub-style heatmap extends the timeline up to a year, visually showing daily activity. Additionally, the plugin supports local data persistence for quick startup and historical retention, along with real-time auto-refresh to keep statistics up-to-date.
Whether you are a regular DSH user or a developer, this plugin helps you monitor and analyze token usage effectively. It's particularly useful for those looking to control costs or optimize model selection, offering valuable insights into consumption patterns. After a simple installation, all statistics are easily accessible from the settings panel, making your DSH experience more efficient and transparent.
Use Cases
- Monitor daily token usage to optimize resource allocation
- Analyze multi-model consumption data to control inference costs
- Track historical usage trends to improve decision-making
Best For
- Regular users of DeepSeek Harness
- Developers and researchers in model inference
- Teams needing cost monitoring and resource management
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.