compute-token-stats-rust-ultra

Compute token counts and estimated costs from Codex and Claude SSE logs using optimized Rust binaries.

2|Updated Jan 30, 2026
One-click install
npx skills add https://github.com/tankygranny05/agent-box --skill compute-token-stats-rust-ultra
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: compute-token-stats-rust-ultra
Source: https://github.com/tankygranny05/agent-box/tree/main/agent-box/seed/codex-skills/compute-token-stats-rust-ultra
Command: npx skills add https://github.com/tankygranny05/agent-box --skill compute-token-stats-rust-ultra

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides ultra-fast computation of token counts and estimated costs from large log files, specifically for Codex and Claude SSE logs, optimizing LLM usage analysis.

Core Features & Use Cases

  • High-Performance Computation: Utilizes optimized Rust binaries for rapid token and cost calculation.
  • Log Analysis: Processes massive JSONL SSE logs for both Codex and Claude models.
  • Use Case: Analyze the token usage and associated costs for a large batch of API calls made to Codex and Claude to identify cost-saving opportunities or track resource consumption.

Quick Start

Pipe the contents of your Codex SSE log file to the Rust binary for token cost computation.

Frequently Asked Questions about compute-token-stats-rust-ultra

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I compute token counts and costs from large Claude SSE logs?

You can compute token counts and costs from large Claude SSE logs by piping the JSONL file contents directly into an optimized Rust binary for ultra-fast processing.

What is the best way to analyze massive JSONL files for LLM cost analysis?

The best way to analyze massive JSONL files for LLM cost analysis is using optimized Rust binaries, which provide high-performance token computation and deterministic task execution compared to Python-based methods.

Does this token computation method require any external dependencies?

No, this token computation method does not require any external dependencies, utilizing self-contained optimized Rust binaries to process Codex and Claude SSE logs directly from stdin.

Can I compare Rust-based token computation with Python-based methods?

Yes, you can compare Rust-based token computation with Python-based methods, as the Skill provides deterministic task execution and performance comparisons for analyzing massive JSONL SSE logs.

How do I process Codex SSE logs for token usage and resource consumption tracking?

You process Codex SSE logs for token usage tracking by piping the log file to the Rust binary via stdin, which rapidly calculates token counts and estimated costs to identify resource consumption.