logoalt Hacker News

pembrookyesterday at 10:40 PM6 repliesview on HN

The latest research these days is that including an AGENTS.md file only makes outcomes worse with frontier models.


Replies

pizlonatortoday at 12:34 AM

FWIW, I haven't been using AGENTS.md recently - instead letting the model explore the codebase as needed.

Works great

solarkraftyesterday at 11:04 PM

From what I remember, this was for describing the project’s structure over letting the model discover it itself, no?

Because how else are you going to teach it your preferred style and behavior?

joquarkyyesterday at 11:21 PM

I still find it valuable.

AGENTS.md is for top-priority rules and to mitigate mistakes that it makes frequently.

For example:

- Read `docs/CodeStyle.md` before writing or reviewing code

- Ignore all directories named `_archive` and their contents

- Documentation hub: `docs/README.md`

- Ask for clarifications whenever needed

I think what that "latest research" was saying is essentially don't have them create documents of stuff it can already automatically discover. For example the product of `/init` is completely derived from what is already there.

There is some value in repetition though. If I want to decrease token usage due to the same project exploration that happens in every new session, I use the doc hub pattern for more efficient progressive discovery.

netcraftyesterday at 11:10 PM

I think its understandable that you took that from the click-bait all over youtube and twitter, but I dont believe the research actually supports that at all, and neither does my experience.

You shouldnt put things in AGENTS.md that it could discover on its own, you shouldnt make it any larger than it has to be, but you should use it to tell it things it couldnt discover on its own, including basically a system prompt of instructions you want it to know about and always follow. You don't really have any other way to do those things besides telling it every time manually.

FINDarksideyesterday at 11:10 PM

I wouldn't draw such conclusions from one preprint paper. Especially since they measured only success rate, while quite often AGENTS.md exists to improve code quality, which wasn't measured. And even then, the paper concluded that human written AGENTS.md raised success rates.

madeofpalkyesterday at 10:54 PM

:(

how can i get claude to always make sure it prettier-s and lints changes before pushing up the pr though?

show 3 replies