tokscale

🥈Silver

Tokscale is a CLI tool for tracking token usage and costs across AI coding assistants like OpenCode, Claude Code, and Gemini CLI. It helps developers and operations teams monitor usage, optimize costs, and integrate with IDEs like Cursor and AmpCode.

1,770380Updated Today

Intermediate30min to implementautomation

Saves ~30 min per use

Quick InstallView Source

git clone https://github.com/junhoyeo/tokscale.git

Works with:

Claude

Overview

About This Skill

https://github.com/junhoyeo/tokscale

How to Use

["Install tokscale: `pip install tokscale` or use the pre-built binary for your OS.","Configure your AI tools: Add API keys for OpenCode, Claude Code, and Gemini CLI in `~/.tokscalerc`.","Run analysis: Execute `tokscale --project [PROJECT_NAME] --timeframe [TIME_PERIOD]` to generate a report.","Export data: Use `tokscale --export-csv` to share results with your team or integrate with tools like Grafana.","Optimize: Apply the tool’s suggestions (e.g., truncate comments, enable caching) and re-run the analysis to validate savings."]

Use Cases

Monitor token usage across multiple AI platforms to optimize costs.

Analyze daily token consumption trends to identify peak usage times.

Visualize contributions and performance over time with interactive graphs.

Submit usage data to leaderboards for competitive analysis and community engagement.

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/junhoyeo/tokscale

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Use tokscale to analyze the token usage and costs for [PROJECT_NAME] over the past [TIME_PERIOD]. Compare the usage across [TOOLS_OR_MODELS] and identify the top 3 most expensive operations. Suggest optimizations to reduce costs by at least [PERCENTAGE]%.

Example Output

Here’s the token usage and cost analysis for the 'E-Commerce API' project over the past 30 days using tokscale:

**Total Token Usage:** 1,245,678 tokens
- OpenCode: 678,901 tokens ($135.78)
- Claude Code: 456,789 tokens ($91.36)
- Gemini CLI: 110,988 tokens ($22.20)

**Top 3 Most Expensive Operations:**
1. **Database Schema Migration** (Claude Code): 234,567 tokens ($46.91) – Generated 50+ SQL files with verbose comments.
2. **API Documentation Update** (OpenCode): 189,012 tokens ($37.80) – Used multi-turn prompts to refine Swagger docs.
3. **Test Suite Refactor** (Gemini CLI): 98,765 tokens ($19.75) – Overly detailed test case explanations.

**Cost Optimization Recommendations:**
- **Truncate verbose comments** in generated SQL files to reduce tokens by ~30%.
- **Use summarization tools** (e.g., `summarize` CLI) for API docs to cut input/output tokens by 40%.
- **Enable caching** in test suites to avoid re-generating identical test cases (saves ~25% tokens).

**Projected Savings:** ~$75/month with these changes.

Run `tokscale --export-csv` to generate a detailed breakdown for your team.