dsh-token-usage
Local-first token observability, budgeting, and session trajectory auditing dashboard for DeepSeek Harness.
Install
$ dsh plugin --profile web add github:LeemanCheung/dsh-token-usagePlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Tracks 4-bucket token usage (uncached input, output, cache read/write) across models and sessions
- Provides a 30-week activity heatmap, period trends (7/30/90 days), and near-real-time output token rate monitoring
- Maintains local rolling 30-day token budgets with 80% warning and 100% overrun forecasting
- Generates opt-in AI-powered token usage reports and deterministic session trajectory audit reports with privacy allowlists
- Calculates agent efficiency metrics including compaction ratios, retry costs, and cache hit efficiency
- Exports aggregated usage data to JSON v3 and CSV formats with formula injection prevention
Useful For
- Auditing and tracking DeepSeek Harness token consumption across sessions and providers
- Setting up local rolling 30-day token budgets to prevent unexpected model usage spikes
- Analyzing multi-step agent execution trajectories and context compaction overhead
- Estimating API expenses based on static public pricing benchmarks without sending sensitive prompts to external services
Who It Fits
- Developers building and debugging agent workflows in DeepSeek Harness
- Teams managing local LLM usage budgets and token efficiency
- DeepSeek Harness users seeking privacy-preserving, local-first token telemetry
Documented Limitations
- Requires DeepSeek Harness Web profile with client UI services; dashboard is not available in CLI-only mode
- Cost calculations rely on static local public pricing tables (OpenAI baseline) rather than live billing data
- AI trajectory analysis and token projections rely on opt-in triggers and local browser storage (up to 24 reports globally)
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 25 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- LeemanCheung/dsh-token-usage
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 8200ee9 · 2026-09-27
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 12GitHub stars
- Forks
- 0
- Open issues
- 1
- Last commit
- 2026-09-12
- Last release
- 2026-09-02
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Token balance monitor and whale-girl animated companion plugin with peak-valley pricing tracking for DeepSeek Harness.
View plugin →A bilingual DeepSeek Harness cost-tracking plugin with session and daily costs, budgets, pricing management, balance lookup, and coding-plan quota displays.
View plugin →Generative UI plugin for DeepSeek Harness that renders interactive components and charts inline from assistant responses.
View plugin →In-app skill audit and management panel for DeepSeek Harness with turn-by-turn invocation tracking and background customizations.
View plugin →