Your Claude Code cost tracker is probably wrong.
Most read session logs. Logs don't carry billing-grade cost — so the number drifts from your actual bill.
WTClaude reads the statusline instead: the same source behind your bill.
It's free + open source. Here's what it does 🧵
A dozen ways to track Claude Code spend — here are the 7 criteria that actually separate them: accuracy, attribution, limits, multi-machine, privacy, and price.
The buyer's guide: https://t.co/c8V1byoL0g
How do you actually track what you're spending on Claude Code? From the built-in command to billing-grade, per-project, and multi-machine totals — a practical 2026 guide.
https://t.co/Cg2NhLHdhJ
Heads up: Claude Code's +50% weekly limits are set to expire July 13 (unless extended). Prices aren't changing — your weekly headroom is.
wtclaude limit shows how close you are to your plan limit, reading Anthropic's own rate-limit data — so a tighter ceiling shows up as a number you can see, not a wall you hit.
What changes + how to check: https://t.co/wbK5OBrlkW
The most complete view of your Claude Code spend: billing-grade cost in the terminal, the compare reveal, one true total across machines, and a full dashboard.
See it: https://t.co/djXVJnI0Vd
A few days left on Peerlist Launchpad — voting closes Sunday.
WTClaude: free, open-source, billing-grade Claude Code cost tracking. A look + a vote helps a lot: https://t.co/iLA4keiGqC
Run one command — wtclaude compare — and see your real, billing-grade Claude Code cost next to what a log-based tracker reports.
The gap is usually bigger than people expect. Free + open source: https://t.co/wn2GdxJHIB
Most Claude Code trackers read the session logs, which were never the billing source — so their totals drift. WTClaude reads the statusline instead.
Run wtclaude compare and see your own gap: https://t.co/wn2GdxJHIB
Two Claude billing changes in two weeks. Neither took effect.
The honest takeaway isn't chaos — you can't control the announcements, only your own visibility. New post on building on shifting ground, and why an honest tracker matters more, not less: https://t.co/PTterp8Yn9
Update: Anthropic paused the June 15 Agent-SDK billing split — it didn't take effect.
Agent SDK / claude -p / third-party apps still draw from your subscription as before. No separate credit to claim. Anthropic will give notice before any future change.
Nothing to do right now. We're watching for if/when it returns.
WTClaude is live on Peerlist Launchpad this week 🌿
Billing-grade cost tracking for Claude Code — free & open source. If it looks useful, a look and honest feedback over there means a lot: https://t.co/iLA4keiGqC
One command shows what your Claude Code spend really is:
wtclaude compare — your billing-grade cost next to the number a log-based tracker reports, and the gap between them. Now per-pool after the June 15 split.
Free + open source: https://t.co/wn2GdxJHIB
WTClaude is live on Peerlist Launchpad this week and climbing 🚀
Billing-grade Claude Code cost tracking, built in public. If you've got a sec tonight, a look + honest feedback genuinely helps: https://t.co/u9cg0CxGGn
Two Claude billing changes, 8 days apart: the June 15 Code split and the June 23 Fable cliff. Easy to confuse — here's a clear map of what changes, and when.
Wrote up the thing behind WTClaude: why your Claude Code cost tracker probably disagrees with your bill.
It reads the session logs — which were never the billing source — so the number drifts. The fix: read the statusline, the actual source behind your bill.
Full writeup in the reply 👇
Posted my zero-to-launch story on @IndieHackers today: I shipped a free, billing-grade Claude Code cost tracker — built because my own tracker never matched my bill.