My claude.md:

# CLAUDE.md

This project uses `AGENTS.md` as its agent instruction file (kept provider-agnostic). Treat any `AGENTS.md` file exactly as you would a `CLAUDE.md` file — at the root level and in any subdirectory you are working in.

@AGENTS.md

I don't think this will work reliably. Pretty sure it's not the LLM deciding to read the files, it's the harness in Claude Code itself injecting the instructions files based on the paths the model accesses.

Edit: sometimes if Claude lists files in a directory or does a search that shows it an AGENTS.md exists it will decide to read it. But it's not a reliable behavior.

If only there was a technology that existed to link files together… /s

You mean symbolically?

Good one

The idea was to have it automatically detect nested AGENTS.md

Does your tech do that?

Anyway, the joke is on me I guess, because it might not work reliably.

On many filesystems, a lot of data about a file is not attached to the content of the file, but stored in a master filename and metadata table graph tree of some sort, and the address offset within that metadata used to retrieve the contents on disk can be a duplicate of another entry, without that situation instantly leading to a filesystem driver crash. Some filesystems officially support such duplicates as well as equivalents of HTTP 3xx, some you can just do as a matter of fact and fsck would have some words about it.

Default filesystems for all Unix, Linux, WinNT, all do.

Yes. The thing is that creating a link will not do it recursively for all subdirectories. Even worse, in the subdirectories I didn't want to place a claude.md in the first place but just have agents.md.

That was the idea.... For the toplevel it works because of the @AGENTS.md and this is also the part the link would solve.

Thanks for all the great advice and explanations.

CLAUDE.md is handled by the harness, not the agent.

I phrased it wrong. It was not about "automatically detect nested AGENTS.md". The idea was that when AGENTS.md files should be treated just like CLAUDE.md files in all subdirectories, when encountered.

Anyway, with the change they announced, I can now simply delete my CLAUDE.md and everything will just work the way I wanted.

Thanks for your clarification.

What I meant is that the LLM isn’t the one that loads the agent file. It’s not trained to look for CLAUDE.md. It’s only training is to edit that file, and the harness does the magic of injecting it. So I would predict that with those instructions it rarely or only intermittently loaded AGENTS.md, but if you asked it to add a rule it would probably have put it on the right file.

Moving the goalposts a bit here, aren’t you?

Clearly the author knows what he is doing, even if you think it isn’t a sensible approach.

It might still be true that LLMs make it too easy to create a broken design and don’t warn you if you ask for something already exists.

The thing is, the example you decided to pick on does not work.

You accused the author of having fallen into the ‘vibe-coding trap’. He clearly did not.

Post author just wanted quick clicks based on kneejerk heuristics based attacks on Bend. Now he’s doing gymnastics all over this thread to mitigate what he said. Sad and disappointing.

Yes, I used Bend as an example because it is recent and high profile, and I also wanted to present my issues with it. I did not mean to conflate it with the main idea I was trying to present to the degree that I obviously did after reading my own writing as a third party would (at least to the degree that it is possible to do so).

Your only issue was that the author was unaware of a subject and that the code is long. You didn’t even google the guy! Respectfully, I think you made a bad point and probably harmed your own stance with this post.

This comment aged very quickly

I skimmed through it. Looks fine. Had a bit of trouble following step 5 of theroem 10.5 (page 89), but after a second look it became all too obvious.

I was more confused by the application of Nakayama’s lemma in the following paragraph, but then it suddenly became clear to me.

basically trivial.

uff.. HN is degrading rapidly. (Yes, also all your comments about "AI SLOP SPOTTED, AI;DR". Regurgitating the same crap over and over again.... pff...)

Indeed. But also some things that were harder at the small company were easier at the large one. You have processes in place, were things in the small company are all done ‘by hand’.

So I think it is hard to compare small and big. For one company things are easy that are hard for the other and vice-versa.

boring af. what a waste of time.

Yes, I've also donated to NVDA... I use interactive-brokers to donate. Which apps do you use?

:)) the two neurons required to get this took several mins to connect.

My neurons are still searching for one another

This is literally Hacker News :)