CodeBurn
Analyze Claude Code token usage by task
Details
- External ID
- 47759035
- Source
- HN
- Company
- —
- Product
- CodeBurn
- Website domain
- github.com
- Launched
- April 13, 2026
- Cohort
- —
- Upvotes
- 112
- Upvotes percentile
- 0.9010282776349614
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
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.
Enrichment
- Theme
- utilities for Claude and Claude Code
- Vertical
- Horizontal
- Function
- Analytics & BI
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- token usage analyzer for claude code
- Manually corrected
- False
Could you build this?
Yes This is a local CLI utility that parses existing local JSONL log files generated by Claude Code and aggregates token metrics by task. Parsing JSONL files and displaying summary tables or terminal charts is a very simple task completely suited for vibe coding.
Discussion
20 comments analyzed.
Competitors mentioned: Anthropic's Claude (comparison/context), React (mentioned as alternative), PatchPilot (referenced for agent optimization)
Concerns raised: Windows support not available, Activity classification may not capture all planning work accurately, No cost breakdown by parallel sessions, Throttling/queueing on $200/month plan vs unthrottled API, Missing data limits efficiency analysis capabilities
Feature requests: Cost breakdown by session for parallel runs, Separate exploration turns from pure thinking turns by activity type, Cost scaling metrics for different project sizes/monorepos, Inefficiency detection and cost optimization suggestions, Windows platform support
Competitors
Other products that read as similar to this one — 252 launches clear the similarity bar, closest 8 shown.
Attention rank: #24 of 253 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 152 days after the earliest competitor.
- Claude Code usage tracking by LangWatch · ph · 2026-07-30 · 351 upvotes · similarity 0.63
- Claude Usage Tracker · ph · 2026-03-23 · 235 upvotes · similarity 0.59
- claudebill · ph · 2026-09-18 · 63 upvotes · similarity 0.54
- I built a tool to un-dumb Claude Code's CLI output (Local Log Viewer) · hn · 2026-02-13 · 69 upvotes · similarity 0.53
- How well do you use Claude Code? · hn · 2026-07-24 · 21 upvotes · similarity 0.52
- Claude's Code · hn · 2026-03-24 · 23 upvotes · similarity 0.52
- Claude Meter · hn · 2026-02-10 · 9 upvotes · similarity 0.52
- Latitude for Claude Code · ph · 2026-05-13 · 368 upvotes · similarity 0.51
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a analytics & bi tool for Legal yet.