‹ BackHN Continuity

Thread

Claude Code now reads AGENTS.md if there is no Claude.md

741 points · 285 comments · datadrivenangel

  1. bryanhogan · · focus · HN ↗
    What worked well previously was to have the Claude.md file contain just "@AGENTS.md".

    But this is a good change.

    The world of managing skills between providers still feels messy though.

    1. bengt · · focus · HN ↗
      I’d argue this is still the better way. We used to simlink too, but @AGENTS.md with any Claude specific additional steering below it is the best way.

      <a href="https:&#x2F;&#x2F;code.claude.com&#x2F;docs&#x2F;en&#x2F;memory#import-additional-files" rel="nofollow">https:&#x2F;&#x2F;code.claude.com&#x2F;docs&#x2F;en&#x2F;memory#import-additional-fil...

      1. albert_e · · focus · HN ↗
        If this continues to be a thing ...one might actually imagine a good system where we have AGENTS.md with all generic agent instructions and a bunch of harness specific files like CLAUDE.md, GEMINI.md, and CODEX.md that all add whatever nuance and nudging each harness seems to individually require
        1. OliverGuy · · focus · HN ↗
          I like this, but can we not have any of this in the root of the repo cluttering it up with the harness specific instructions for a half dozen plus different harnesses. Something like a dot agents dir
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.