getagentseal/codeburn: README-based editorial guide

getagentseal/codeburn describes itself in the README as "Free, local tool to track AI coding token usage and cost across 31 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn". This article keeps to facts that can be checked in the repository. Stars, forks, and promotional badges are signals of attention, not proof of quality. Under "README", the README says: 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.. That establishes the project's stated boundary, not a production test.

The README's "Find and fix waste" section gives a useful starting point for deciding whether the project fits: Low Read:Edit ratio (editing without reading leads to retries and wasted tokens). If that problem is not yours, popularity is a poor reason to adopt it. Project names, commands, and component names are kept as written so a reader can return to the primary source without guessing at terminology. Another checkable README item is: Files Claude re-reads across sessions (same content, same context, over and over). It can shape a first test, but it does not replace testing in the intended environment.

The operating model is spread across sections such as "README". The source evidence includes: CodeBurn does. It reads the session files your tools already write to disk and breaks down every token and dollar by task, model, tool, and project, across 36 AI tools.. This article does not turn missing architecture, performance, or security details into claims. A real deployment still needs a look at the repository layout, configuration files, and release history.

Start installation from the README's documented entry point. A command that can be checked in the source is: npm install -g codeburn When the README contains no runnable command, this article does not invent one. Open its "Your month at a glance" section and confirm system dependencies, default ports, and first-run initialization before using a public server.