Everyone is talking about token spend, but not what we actually spend tokens on. I’ve always found it interesting to track my time across different tasks to challenge whether I was working on the right things.

Nowadays, I spend around 95% of my day in the Claude desktop app, so “where did my time/tokens go?” basically means “what did I do in Claude?”*

Turns out it’s all already on your disk. Every Claude Code / Cowork session is a JSONL transcript with per-message usage blocks: input, output, cache creation, cache read, and timestamps.

Run it from the terminal:

  curl -fsSL 'https://gist.githubusercontent.com/danmeier2/064f7db8c0867dd6331007ba43f0e6fe/raw/claude-token-analyzer.py' | python3 -

Run the snipped to get an overview of what you did and when based on your Cowork and Claude Code history. Example output:

Claude Token Analyzer · 2026-06-15 · 5 threads

  Claude Token Analyzer  ·  2026-06-15  ·  5 threads

  ╭────────────────┬────────────────┬────────────────┬────────────────╮
  │ Spend          │ Tokens         │ Active         │ Cache-read     │
  │ $39            │ 27.5M          │ 1.8h           │ 91%            │
  ╰────────────────┴────────────────┴────────────────┴────────────────╯

   when active   08:00               09:00                10:00                11:00               12:00
     Claude Code                                                         
   Claude Cowork                                             

  Claude Code  —  $36.56  ·  3 threads
       $22.07  17.9M  Claude usage report for 2026-06-14
                $9.29   7.6M  LinkedIn data export analysis
                  $5.19   1.0M  Productization plan

  Claude Cowork  —  $1.99  ·  2 threads
                     $1.15   791K  YouTube video summary
                     $0.84   156K  Picture location identification

*ccusage doesn’t see my Claude Code sessions because they’re stored in ~/Library/Application Support/Claude/local-agent-mode-sessions/.

投稿

Show HN: Claude Token Analyzer: a token "screen-time" report

コメント