What does ccwhy do for Claude Code?

Parses local ~/.claude/ data offline, breaks down token usage by cache, input, output—shows why your bill's high.

How to reduce Claude Code token costs?

Use /compact after 20 turns, grep instead of Agent searches, avoid peak hours, summarize tool outputs.

Is 97% cache reads normal in Claude Code?

Common for long sessions, but optimize or it'll eat your budget—Anthropic profits most.

Burned $6,744 on Claude Code Sessions—97% Went to Cache Reads, Not Code

Staring at my terminal last night, parsing 187 Claude Code sessions that torched $6,744 in tokens. Turns out, almost everything's just Claude re-reading its own homework.

DevTools Feed Apr 03, 2026 3 min read 26 views

Read in: Deutsch English Español Français Italiano 日本語 한국어 Português (BR) Русский Türkçe

Bar chart breaking down 3.3 billion Claude Code tokens: 97% cache reads dominating

⚡ Key Takeaways

97% of Claude Code tokens are cache reads, making real control tiny at 2.8%. 𝕏
Fixes like /compact and grep over Agent slashed anomalies instantly. 𝕏
Tool like ccwhy reveals why—open source, offline, game-changer for AI bills. 𝕏

Published by

DevTools Feed

Ship faster. Build smarter.

#AI costs #claude-code #dev tools optimization #token usage

Worth sharing?

Get the best Developer Tools stories of the week in your inbox — no noise, no spam.

Originally reported by dev.to

⚡ Key Takeaways

The 60-Second TL;DR

DevTools Feed

Share this article

Worth sharing?

Related Stories

187 Claude Code Sessions Burned $6,744 in Tokens – 97% Was Pointless Cache Reads

512,000 Lines Leaked: Claude Code's Permission-Gated Agent Loop Exposed

Claude Code Token Crunch: The Local Agent Saving Devs from Defection

Claude Code's Dirty Secret: .claudeignore Stops the Node_Modules Madness

Stay in the loop