codeburn
AI coding tools consume tokens at scale; codeburn provides visibility into per-project costs and model efficiency, enabling teams to optimize spend and preve…
Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
- Track Claude API token spending across multiple projects to identify cost overruns.
- Monitor token usage by model type to optimize which AI tools your team uses.
- Generate monthly cost reports for each development project to allocate expenses correctly.
AI coding tools consume tokens at scale; codeburn provides visibility into per-project costs and model efficiency, enabling teams to optimize spend and prevent bill shock across distributed agent usage.
Engineering leaders and DevOps teams managing multi-tool AI coding environments seeking cost tracking and token accountability.
https://github.com/getagentseal/codeburn
By getagentseal
How to Get It
claude plugins install getagentseal/codeburn
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Help me track Claude API token spending across multiple projects to identify cost overruns
Trust Signals Auto-scanned
Community Pulse New
- Show HN: CodeBurn – Analyze Claude Code token usage by task — Hacker News · 112 pts
- Show HN: Stop letting Claude Code burn your tokens and leak API keys — Hacker News · 3 pts
- Codeburner (by Groupon) – Security-Focused Static Code Analysis for Everyone — Hacker News · 2 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 9,433 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 9,433 GitHub stars; contributors unknown; last commit 0d ago; license MIT.