Each repository has a scorecard. - its dependencies (too much - potential bloat) - issue progression over time (number of issues, time to close issues) - by maintainer count and reputation (changes hands often - bad). - by funding
Allows users to set their own rating, giving a more nuanced distribution than just github stars. It also allows users to blacklist repositories, and exposes an MCP server that allows one's own agents to know what to avoid.
What do you think?
If majority of people like to generate code it doesn't mean writing code is automated, it means a lot of people like to generate code. If you want to build on top of slop go ahead, but do not expect it to "improve" the slop experience, (and please forgive me to assume) with even more slop.