A repo map experiment aims to cut AI token use
An tool scans a and turns the whole app into an . The map also marks areas where the code looks tangled or likely to break.
The goal is to reduce token use and save time by giving AI the map instead of making it re-read the full codebase on every prompt. It is aimed at , where AI often creates or edits code and may break fragile parts of an app.
The tool is still rough and being tested on real apps. People can send a repo to have it mapped and give feedback.
Key points
- The tool scans a and creates an .
- It highlights tangled areas and parts that may break easily.
- The aim is to reduce token use by giving AI a map instead of the full codebase each time.
- It targets where AI edits apps frequently.
- The approach is early and needs real-world .