SaaS Metrics
Show HN: CodeBurn – Analyze Claude Code token usage by task
A specialized tool for Claude Code users to gain granular visibility into token consumption at the task level, addressing the lack of detailed cost breakdown beyond model and daily usage, and revealing inefficiencies in agent interaction patterns.
View Origin LinkProduct Positioning & Context
AI Executive Synthesis
A specialized tool for Claude Code users to gain granular visibility into token consumption at the task level, addressing the lack of detailed cost breakdown beyond model and daily usage, and revealing inefficiencies in agent interaction patterns.
CodeBurn addresses a critical, emerging pain point for businesses adopting AI coding agents: cost visibility and optimization. The lack of granular token usage breakdown from providers like Claude Code leads to significant, unmanaged expenses. CodeBurn's ability to classify usage by task, rather than just model or day, provides actionable insights into where costs are incurred, highlighting inefficiencies like high spend on non-tool-using conversation turns. This tool is essential for organizations seeking to control and optimize their AI development budgets. It underscores a broader market need for robust cost management and observability solutions as AI agent usage scales, positioning itself as a necessary utility for responsible AI expenditure.
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.
Related Ecosystem & Alternatives
Discover adjacent products, open-source repositories, and developer tools sharing similar technical architecture.
Deep-Dive FAQs
What is CodeBurn – Analyze Claude Code token usage by task?
CodeBurn – Analyze Claude Code token usage by task is analyzed by our AI as: A specialized tool for Claude Code users to gain granular visibility into token consumption at the task level, addressing the lack of detailed cost breakdown beyond model and daily usage, and revealing inefficiencies in agent interaction patterns.. It focuses on CodeBurn addresses a critical, emerging pain point for businesses adopting AI coding agents: cost visibility and optimization. The lack of granular...
Where did CodeBurn – Analyze Claude Code token usage by task originate?
Data for CodeBurn – Analyze Claude Code token usage by task was aggregated directly from the Hacker News community ecosystem, representing raw developer and early-adopter sentiment.
When was CodeBurn – Analyze Claude Code token usage by task publicly launched?
The initial public indexing or launch date for CodeBurn – Analyze Claude Code token usage by task within our tracked developer communities was recorded on April 17, 2026.
How popular is CodeBurn – Analyze Claude Code token usage by task?
CodeBurn – Analyze Claude Code token usage by task has achieved measurable traction, logging over 78 traction score and facilitating 17 recorded discussions or engagements.
Which technical categories define CodeBurn – Analyze Claude Code token usage by task?
Based on metadata extraction, CodeBurn – Analyze Claude Code token usage by task is categorized under topics such as: Claude Code, token usage, JSONL session transcripts, tool usage patterns.
Are there open-source alternatives related to CodeBurn – Analyze Claude Code token usage by task?
Yes, the GitHub ecosystem contains correlated projects. For example, a repository named AgentSeal/codeburn shares highly similar architectural descriptions and topics.
How does the creator describe CodeBurn – Analyze Claude Code token usage by task?
The original author or development team describes the product as follows: "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..."
Community Voice & Feedback
So how much did the tokens to build this cost?
[dead]
This is cool.I do find the activities a little suspect - it has 1 turn of planning for me in the last 30 days. I have claude write plans first before every coding session, often using one agent session to plan and then output a plan file, and then others to execute on it. I also have several repos dedicated to 'planning' in the sense of what should I do next based on what emails/tickets/bugs etc. I have. In other words - I do all kinds of planning!
[flagged]
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.
"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
Made something similar a while back: https://www.clauderank.com/
Completely open source
Completely open source
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
Doesn't seem to work with Cursor Agent (which may store its data in ~/.cursor).
> 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.
Discovery Source
Hacker News Aggregated via automated community intelligence tracking.
Tech Stack Dependencies
No direct open-source NPM package mentions detected in the product documentation.
Media Tractions & Mentions
No mainstream media stories specifically mentioning this product name have been intercepted yet.
Deep Research & Science
No direct peer-reviewed scientific literature matched with this product's architecture.