Show HN: Toktrack – Track your Claude Code token spending in under a second

My session files were ~3GB (2,000+ files). I first tried a Node.js approach but it took 40+ seconds – sequential JSON.parse, GC overhead, and libuv thread pool limits made it hard to optimize further.

Rewrote it in Rust with simd-json (SIMD-accelerated parsing) + rayon (parallel file processing). Cold start: ~1s, warm: ~0.04s.

Also supports Codex CLI and Gemini CLI.

Install: npx toktrack