awesome-claude-code-subagents: Production-ready Claude subagents collection
github.com
github.com
Amazing there’s been time for battles and best practices and industry standards in the like weeks since Anthropic added this feature.
I really had not anticipated that LLMs would claim rational use of adjectives and superlatives before they took my job.
In contrast, I find the scope of the ones in this repository a little weird. The claude main agent does great with CLAUDE.md context, so does it really make sense for it to delegate different tasks to a frontend and backend agent and coordinate between the two? Especially when the additional context in the frontend agent definition is a listing of what libraries and patterns are used in the repo?
It truly feels futile to stay on top of all the new stuff coming out.