Context Evaluator – Detect and fix issues in your AGENTS.md, CLAUDE.md, and more

Summary: Context Evaluator is an open-source tool that scans AI coding agent context files like AGENTS.md and CLAUDE.md to identify content quality issues, missing setup steps, and mismatches between documentation and code. It supports agents such as Claude Code, Cursor, and GitHub Copilot to help keep context files accurate and up to date.

What it does

It analyzes context files in Git repositories using coding agent CLIs and evaluation prompts to detect errors, outdated instructions, and gaps in documentation. The tool suggests improvements and remediations to ensure context files reflect the current codebase.

Who it's for

Developers and teams using AI coding agents like Claude Code, GitHub Copilot, and Cursor who need to maintain accurate and comprehensive context files for their projects.

Why it matters

It addresses the challenge of keeping AI coding agent context documentation current amid rapid code changes, improving the agents’ effectiveness by ensuring their context is accurate and complete.