What problem does it solve?
AI agents struggle when a repo lacks accurate, project-specific guidance, so builds, tests, and conventions get misapplied; this workflow fixes that by generating or updating AGENTS.md based on what actually exists in your codebase.
Core Features & Use Cases
- Creates or updates AGENTS.md at the project root with concrete build commands, test procedures, code style, architecture, and conventions.
- Audits tool-specific AI convention files (such as .cursorrules, CLAUDE.md, and .github/copilot-instructions.md) and consolidates redundant generic instructions into AGENTS.md while keeping tool-auto-loaded files as needed.
- Detects monorepos and recommends adding nested AGENTS.md files for subprojects when the structure supports it.
Quick Start
Run the ai-ready command that executes /ai-ready:update to scan the repository and update the root AGENTS.md using the project’s current files and conventions.