Show HN: CodeBurn – Analyze Claude Code token usage by task

github.com - 37 poäng - 11 kommentarer - 251227 sekunder sedan

Built this after realizing I was spending ~$1400/week on Claude Code with almost no visibility into what was actually consuming tokens.

Tools like ccusage give a cost breakdown per model and per day, but I wanted to understand usage at the task level.

CodeBurn reads the JSONL session transcripts that Claude Code stores locally (~/.claude/projects/) and classifies each turn into 13 categories based on tool usage patterns (no LLM calls involved).

One surprising result: about 56% of my spend was on conversation turns with no tool usage. Actual coding (edits/writes) was only ~21%.

The interface is an interactive terminal UI built with Ink (React for terminals), with gradient bar charts, responsive panels, and keyboard navigation. There’s also a SwiftBar menu bar integration for macOS.

Happy to hear feedback or ideas.

Kommentarer (8)

Isolated_Routes - 6848 sekunder sedan
I like this a lot An interesting next iteration would be to add a functionality that evaluates a user's work for inefficiencies and suggests where they can improve cut cost. Might be outside the scope of your project, but it could be interesting.
coatol5 - 7738 sekunder sedan
Made something similar a while back: https://www.clauderank.com/ Completely open source
giancarlostoro - 12233 sekunder sedan
> The interface is an interactive terminal UI built with Ink (React for terminals)
Just like Claude Code btw.
I'm working on a custom harness because I don't like or trust some of the ones out there, so I'm going to build one purely for myself and my own needs to see just how they work, and figure out some of what you've learned by looking at how Claude works, so I might add your project to my list of tooling to look at.
hmokiguess - 10892 sekunder sedan
Very cool! I saw a similar product recently that I liked but I much prefer your approach to theirs[1]
[1] https://github.com/cordwainersmith/Claudoscope
halostatue - 11465 sekunder sedan
Doesn't seem to work with Cursor Agent (which may store its data in ~/.cursor).
ieie3366 - 7656 sekunder sedan
"Built this after realizing I was spending ~$1400/week on Claude Code with almost no visibility into what was actually consuming tokens."
holy slop. the $200/month plan has NEVER hit rate limits for me and I often run 5+ tabs of concurrent agents in a large 300k LoC codebase
KaiShips - 6117 sekunder sedan
[dead]
maroondlabs - 13402 sekunder sedan
[dead]