Peter Bean

Creator of | Agentic AI founder | DeFi native builder | Nerd | Proud 🇨🇦 | Live Long and Prosper 🖖🏽

[Peter Bean @Beannation]

I built this because my own Claude Code spend didn't match what my tracker said. Turns out it reads session logs, which don't carry real cost. So I made one that reads the statusline — the source behind the bill. Run wtclaude compare and tell me your gap. Mine was not small.

[WTClaude @getwtclaude]

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 🧵

[Peter Bean @Beannation]

how to track your real Claude Code spend in 2026 — built-in command → billing-grade, per-project, multi-machine: https://t.co/4eoWgsU1Vx

[Peter Bean @Beannation]

Confused by Claude Code billing — pools, credits, limits, what you actually pay? I wrote the plain-English version: https://t.co/leYW5SylSr

[Peter Bean @Beannation]

Heavy Claude Code user? The +50% weekly-limit boost expires July 13 (unless extended). Where do you stand? https://t.co/HdLCgIuIL0

[Peter Bean @Beannation]

most Claude Code trackers read the session logs, which were never the bill. wtclaude reads the statusline. see your gap: https://t.co/llDcTQIAsU

[Peter Bean @Beannation]

a week into building WTClaude in public — the honest Claude Code cost tracker. see your real spend vs the log estimate: https://t.co/llDcTQIAsU

[Peter Bean @Beannation]

Two Claude billing changes in two weeks. Neither happened. What stays steady? Your real numbers: https://t.co/zGw9zInD6p

[Peter Bean @Beannation]

Bracing for the June 15 Claude billing change? It was paused — didn't take effect. Agent SDK, claude -p & third-party still draw from your subscription as before. No credit to claim. You can exhale.

[Peter Bean @Beannation]

Building WTClaude in public — the honest Claude Code cost tracker. See your real gap vs the log-based number: https://t.co/llDcTQIAsU

[WTClaude @getwtclaude]

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

[Peter Bean @Beannation]

WTClaude is live on Peerlist Launchpad this week. If you build with Claude Code, a look + feedback means a lot: https://t.co/QUrJqZofa8

[Peter Bean @Beannation]

Your other Claude costs are unaffected, and the June 15 Code billing split still stands. I'll track Fable again if it returns.

[Peter Bean @Beannation]

Update: Claude Fable 5 was suspended June 12 and is unavailable for now. So the Fable cost-cliff I flagged is moot — nothing to forecast there.

[Peter Bean @Beannation]

https://t.co/la7OOtkF2a

[Peter Bean @Beannation]

Two Claude billing changes, 8 days apart: the June 15 Code split, then the June 23 Fable cliff. People keep mixing them up — so I mapped what changes, and when. No drama.

[Peter Bean @Beannation]

That gap is the whole pitch. Onward.

[Peter Bean @Beannation]

Day 1 of launching WTClaude in public.
Yesterday: shipped it, dropped the writeup, posted across the dev communities, and lived in the replies.

[Peter Bean @Beannation]

The most common reply wasn't "cool tool" — it was people running wtclaude compare and going "wait, THAT'S my real number?"

[WTClaude @getwtclaude]

Claude Fable 5 is free until June 22 — then it starts drawing usage credits at $10/$50 per million.

[Peter Bean @Beannation]

@IndieHackers https://t.co/mgtetMht5z

[Peter Bean @Beannation]

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.