Feature Request: Support AGENTS.md
11–20 of 236 posts
Re: Feature Request: Support AGENTS.md
#12Re: Feature Request: Support AGENTS.md
#13Deeply unserious at every level; this cannot be what all the 100x AI-enabled developers are spending their time on.
Re: Feature Request: Support AGENTS.md
#14how does agents.md work for subagents and swarms? is it actually that useful?
yes, they are useful, mainly in that they shorten the context gathering phase and can call out gotchyas, keep it minimal
Re: Feature Request: Support AGENTS.md
#15Re: Feature Request: Support AGENTS.md
#16- " Generated with Claude Code"
God I hate this world. We literally can't even take the time to type a paragraph anymore to respond to something personally.
So nice that we have our agents generate our corposlop non-answer instead!
Re: Feature Request: Support AGENTS.md
#17The obvious reason is that they would prefer to have CLAUDE.md files in every repo (even if it's just a symlink to AGENTS.md). It serves as a free advertisement for them. Same reason as for auto-adding attribution text in commit messages, etc. It's the "Sent from my iPhone" of our time.
Re: Feature Request: Support AGENTS.md
#18My Claude.md has one line that says to read agents.md, this is a bit of a nothingburger
Re: Feature Request: Support AGENTS.md
#19The obvious reason is that they would prefer to have CLAUDE.md files in every repo (even if it's just a symlink to AGENTS.md). It serves as a free advertisement for them. Same reason as for auto-adding attribution text in commit messages, etc. It's the "Sent from my iPhone" of our time.
[flagged]
Re: Feature Request: Support AGENTS.md
#20I wonder if you could use this to make the harness recognize AGENTS.md.