Scar helps AI coding agents avoid repeating old mistakes
Scar is a Git-based tool that helps avoid touching code that should stay the way it is. It records inside the codebase, such as failed approaches, intentionally unusual code, risky areas, and libraries that were removed before. When an AI agent like Claude Code is about to work on related files, can show a warning at that exact moment.
This can stop the agent from “fixing” code that looks strange but is important, bringing back old dependencies, or trying an approach that already failed. The main idea is to give the AI not only the current code, but also the history of why some choices were made.
Key points
- Scar is meant to stop AI agents from repeating known mistakes in a codebase.
- includes failed attempts, intentional code choices, risky areas, and removed libraries.
- Claude Code can receive warnings through before it works on relevant code.
- The workflow aims to add project history to , not just current file contents.
- For solo projects, it can reduce regressions and repeated explanation when using .