---
title: "Where did all my Claude Code tokens go?"
url: https://daily.dev/posts/where-did-all-my-claude-code-tokens-go--6pq3unlpu
source_url: https://coralogix.com/blog/where-did-all-my-claude-code-tokens-go
type: article
source: "Coralogix"
published: 2026-06-25T16:53:07.635Z
updated: 2026-06-27T10:03:12.774Z
tags: ["ai-agents", "observability", "claude-code", "opentelemetry"]
reading_time: 11
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Where did all my Claude Code tokens go?

**[Coralogix](https://daily.dev/sources/coralogix)** · 11 min read · 0 upvotes · 0 comments

## Summary

Most teams evaluate AI coding agents by their monthly bill and gut feeling, but neither reveals what the agent actually did. An experiment using Claude Code across three coding approaches (open/default, TDD, and skip-permissions) with OpenTelemetry telemetry piped to an observability backend reveals that total cost is a misleading metric. Per-turn cost and cache hit rate are far more informative signals. Cache invalidation events — where the agent rewrites its own plan mid-session — are the primary cost driver, not code generation itself. About 63% of spend is context re-read, ~25% is cache writes, and only ~11% is generated output. The key cost levers are: keeping context lean, scoping sessions tightly, matching model size to task complexity, and generating in proportion to need. These findings were validated across 20,000+ real Claude Code sessions over 90 days.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://coralogix.com/blog/where-did-all-my-claude-code-tokens-go>

## Similar posts on daily.dev

- [Your Team is Using Claude Code. Do You Know What It’s Costing You?](https://daily.dev/posts/your-team-is-using-claude-code-do-you-know-what-it-s-costing-you--83sobkexk) · Coralogix · 2 upvotes · 0 comments
- [Claude Code Sends 4.7x More Tokens Than OpenCode Before Reading Your Prompt](https://daily.dev/posts/claude-code-sends-4-7x-more-tokens-than-opencode-before-reading-your-prompt-9m02iom1z) · Hacker News · 6 upvotes · 0 comments
- [What I Learned From My Claude Code Dashboard](https://daily.dev/posts/what-i-learned-from-my-claude-code-dashboard-3batpkklt) · Atomic Spin · 0 upvotes · 0 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#observability](https://daily.dev/tags/observability), [#claude-code](https://daily.dev/tags/claude-code), [#opentelemetry](https://daily.dev/tags/opentelemetry)

[View this post on daily.dev](https://daily.dev/posts/where-did-all-my-claude-code-tokens-go--6pq3unlpu)