What 49 Vibe-Coded GitHub Projects Revealed About AI Code Duplication

This story was originally published on HackerNoon at: https://hackernoon.com/what-49-vibe-coded-github-projects-revealed-about-ai-code-duplication. Scanned 49 vibe-coded GitHub projects for code duplication. Found that AI skill libraries - not AI apps - have the highest duplication rates, up to 37%. Check more stories related to machine-learning at: https://hackernoon.com/c/machine-learning. You can also check exclusive content about #vibe-coding, #code-quality, #ai-coding, #open-source, #developer-tools, #programming, #github, #copilot, and more. This story was written by: @akucherenko. Learn more about this writer by checking @akucherenko's about page, and for more stories, please visit hackernoon.com. I ran jscpd against 49 vibe-coded GitHub projects looking for code duplication patterns. Average duplication: 7.98% (above the 3-5% industry benchmark). But the unexpected finding wasn't in the apps — it was in the skill libraries built to teach AI agents how to code. Those have 30-40% duplication rates, mostly in markdown instructions and CSS templates duplicated for different agent platforms. The infrastructure designed to enforce AI discipline embodies the same pattern it's trying to prevent.