Usage

What I'm using Claude Code for, and how much. Generated from local transcripts on 10 Jun 2026.
31.59Btokens through Claude Code since Mar 2026
164,886messages
23.3Kshell commands run
291subagents dispatched
56active days
55day streak
1.15Bnet new tokens

~96% of the headline is cache reads (free replay of context the model already saw). The honest "did real work" number is 1.15B in input + output + cache writes. Both numbers are accurate, the second is the one I think about. Claude Code rotates raw transcripts after about a month, so each refresh merges the live window into a day-level archive; headline numbers are all-time. Model, tool, and category splits cover the recent window only.

What all this actually built

Tokens are the cost, not the point. The point:

  • This site: ~4,600 lines of server.js, every post, every feature.
  • The personal agent fleet: seven agents and 48 crons on a Mac Mini in my living room.
  • Voltade work: customer demos, eval harnesses, ops tooling. The Voltade and AI products slices below.
  • The automation that lets The Bon Pet run mostly without me.

Where it goes

Token share by project category, recent window. A few private folders count towards the totals but are not broken out.

  • 🤖 AI products1.9%
  • 🌐 Personal site6.2%
  • ⚡ Voltade47.8%
  • 🐾 BonPet20.6%
  • 🧪 Side projects23.6%

Daily activity

Last 60 days. Each cell is one day, intensity is messages sent.

2026-04-12: no activity2026-04-13: no activity2026-04-14: no activity2026-04-15: no activity2026-04-16: no activity2026-04-17: 1,658 messages2026-04-18: 4 messages2026-04-19: 3,804 messages2026-04-20: 3,733 messages2026-04-21: 2,065 messages2026-04-22: 2,115 messages2026-04-23: 6,013 messages2026-04-24: 2,465 messages2026-04-25: 6,560 messages2026-04-26: 173 messages2026-04-27: 2,704 messages2026-04-28: 1,906 messages2026-04-29: 1,627 messages2026-04-30: 2,826 messages2026-05-01: 6,091 messages2026-05-02: 2,303 messages2026-05-03: 2,155 messages2026-05-04: 2,324 messages2026-05-05: 3,060 messages2026-05-06: 2,243 messages2026-05-07: 3,562 messages2026-05-08: 2,215 messages2026-05-09: 1,934 messages2026-05-10: 2,684 messages2026-05-11: 6,530 messages2026-05-12: 2,946 messages2026-05-13: 3,923 messages2026-05-14: 1,019 messages2026-05-15: 2,140 messages2026-05-16: 1,968 messages2026-05-17: 3,772 messages2026-05-18: 2,560 messages2026-05-19: 1,638 messages2026-05-20: 7,023 messages2026-05-21: 2,724 messages2026-05-22: 4,079 messages2026-05-23: 1,632 messages2026-05-24: 1,956 messages2026-05-25: 770 messages2026-05-26: 1,271 messages2026-05-27: 1,061 messages2026-05-28: 3,232 messages2026-05-29: 3,501 messages2026-05-30: 7,038 messages2026-05-31: 1,137 messages2026-06-01: 4,096 messages2026-06-02: 3,066 messages2026-06-03: 606 messages2026-06-04: 4,031 messages2026-06-05: 656 messages2026-06-06: 466 messages2026-06-07: 1,927 messages2026-06-08: 6,546 messages2026-06-09: 1,612 messages2026-06-10: 2,520 messages
LessMore

Models

Share of input + output + cache writes by model, recent window.

  • Claude opus 4.742.7%
  • Claude opus 4.840.2%
  • Claude haiku 4.514.2%
  • Claude fable-52.4%
  • Claude sonnet 4.60.5%

Tools

How Claude actually spends its turns. 46,823 tool calls across 73 distinct tools. More reads than edits usually means I'm in exploration mode.

  • Bash49.7%
  • Read16.7%
  • Edit12.0%
  • Write3.8%
  • WebSearch3.5%
  • TaskUpdate3.2%
  • TaskCreate1.8%
  • mcp__plugin_playwright_playwright__browser_navigate1.3%
  • WebFetch1.2%
  • mcp__plugin_playwright_playwright__browser_evaluate0.9%
  • other (63)5.8%

Meta

  • First entry2026-03-06
  • Last entry2026-06-10
  • Peak week4.44B tokens · w/o 2026-04-27
  • Projects scanned70
  • Files scanned1,217

Aggregated locally by scripts/aggregate-claude-usage.mjs from ~/.claude/projects/**/*.jsonl. No prompt content is read or shipped. Categories are curated in content/claude-categories.json.