dsh-token-stats
Run the following command in DeepSeek Harness:
dsh plugin install qiushui0901/dsh-token-stats
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install qiushui0901/dsh-token-stats in your DeepSeek Harness terminal to install the plugin; the source is available at https://github.com/qiushui0901/dsh-token-stats .
About this plugin
Token consumption in DeepSeek Harness tends to scatter across hundreds of sessions, providers, and models. Figuring out how much you actually spent this month and where used to mean digging through raw logs. dsh-token-stats puts the answer right in your Settings panel: a monthly stacked cost chart, one bar per day, each bar segmented by model in USD, with a color-coded legend on top. Month navigation and provider/model filters let you zoom in on exactly which model or provider drove a cost spike.
The overview panel rolls up the session count carrying usage, the four provider-reported token buckets (uncached input, cache read, cache write, output), and the grand total, then splits the estimated cost by model using exact provider/model price-table matches, falling back to a default table when no specific row applies.
Built for developers and small teams who work with DeepSeek Harness daily and need a cross-week, cross-month view of their token spend. The bundle installs standalone with no core-repository changes required, and the dashboard is one click away in Settings.
Use Cases
- Reviewing monthly token spend and pinpointing cost-spike models
- Comparing per-model cost across providers
- Presenting budget consumption trends to the team
Best For
- Developers using DeepSeek Harness daily
- Small teams tracking multi-model invocation costs
- Tech leads focused on API budget and billing transparency
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.