Comment by weird-eye-issue

3 days ago

Subagents are literally built into Claude Code via a built-in tool where it can recursively call itself

9 comments

weird-eye-issue

Reply
faangguyindia  3 days ago

Yes I know, but subagent suffer from context amnesia during context handouts which is why this subagent use is flawed for purpose of coding product features. I've been using these tools a lot and installed every ai agent out there i could find.

  • CuriouslyC  3 days ago

    Yup, this is the killer. Subagents SEEM good when you use them on greenfield projects, you can grind out a whole first pass without burning through much of your main context, it seems magical. But when you have a complex project that handoff is the kiss of death.

    • jpollock  3 days ago

      I'm wondering if in large projects, you want subagents to avoid having tasks flush out the main context?

      If you're working with large source files, you might want to do each piece of work in an independent context with the information discarded afterwards?

      Is the context a sliding window, or are there tiers of importance?

      2 replies →

    • catlifeonmars  3 days ago

      So maybe the solution is to make all subproblems greenfield products?

      By this I mean treat features as isolated plugins. I get that there are cross-cutting features that touch multiple pieces of functionality, and those probably need special treatment, but a large class of functionality can be developed in an isolated way with a common set of design tokens and APIs to tie them all together.

      This might play better to coding agent strengths.

      Full disclosure: this is very much an armchair view. I have all of 2 weeks of experience coding via agents (vs manually), but this thread is nerd sniping me into trying it myself.

      3 replies →