Claude Code and Codex are logging your token usage locally. Here is how to read it.

Your AI coding agent's token data is already on your machine. You just haven't looked at it yet.

Claude Code and Codex both write local logs after every session. Those logs include detailed token breakdowns: uncached input, cache hits, cache writes, output. No API call needed, no provider dashboard, no guessing. The number that matters most, your prompt cache hit rate, has been sitting on your disk every time you wondered why you were burning through your weekly limit so fast.

The logs you already have

Claude Code writes a JSONL transcript for every session under ~/.claude/projects/. Each assistant message carries a usage block:

{

Claude Code and Codex are logging your token usage locally. Here is how to read it.

Related reading

I Analyzed 4,788 AI Coding Sessions — Here's Where Your Tokens Actually Go

Where Claude Code Tokens Actually Go (and How to Cut the Waste)

7 Ways to Cut Your Claude Code Token Usage

I built TokenBoard to track AI coding token usage without uploading prompts or…

Where Claude Code's Tokens Actually Go (and How I Cut My Bill in Half)

Your AI-tool usage is invisible. Here are 4 tiny local tools to see it.