Audit coding-agent token spend with CodeBurn

Audit coding-agent token spend with CodeBurn

Run CodeBurn locally or as an MCP server so agents can inspect token usage, cost, model mix, project spend, and budget waste across coding tools.

Prerequisites

Node.js 22.13+; local session data from supported AI coding tools; optional Claude Code, Cursor, or another MCP client for codeburn mcp

Installation

Use the upstream install or setup path that matches your environment:

• npx codeburn
• npm install -g codeburn
• git clone https://github.com/getagentseal/codeburn && cd codeburn/gnome

Requirements and caveats from upstream:

• Requires Node.js 22.13+ and at least one supported tool with session data on disk. For Cursor and OpenCode, better-sqlite3 installs automatically.
• Requires a git repository. Run from your project directory.

Basic usage or getting-started notes:

• CodeBurn is a free, open-source, local-first tool that tracks AI coding token usage and cost across 36 tools and agents (Claude Code, Cursor, Codex, Gemini, Grok and more), broken down by model, project, and task.

• Quick start ·

• Run it instantly, no install needed:

• Source: https://github.com/getagentseal/codeburn

• Extracted from upstream docs: https://raw.githubusercontent.com/getagentseal/codeburn/HEAD/README.md

Documentation

• https://codeburn.app/

Source

• Agent Skill Exchange