mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: Antheas Kapenekakis <lkml@antheas.dev>
Cc: corbet@lwn.net, workflows@vger.kernel.org,
	linux-doc@vger.kernel.org, skhan@linuxfoundation.org,
	rdunlap@infradead.org, linux-kernel@vger.kernel.org,
	"kees@kernel.org" <kees@kernel.org>
Subject: Re: [PATCH] docs: add AGENTS.md as a symlink to README
Date: Sun, 27 Sep 2026 10:06:00 -0400	[thread overview]
Message-ID: <arkiyMt2NIydrPhE@laps> (raw)
In-Reply-To: <CAGwozwE5pJaW14ePjeUQ_w=i1W-Kg=QQOzLY_33qV0W-Urmgjw@mail.gmail.com>

On Sun, Sep 27, 2026 at 04:42:06AM +0200, Antheas Kapenekakis wrote:
>I do not have a problem with coding-assistants.rst staying as it is
>now. But it does not make for a good agents.md file. And neither does
>the readme.

What makes one good? In my tests this one did its job: both agents
followed the kernel's rules, for about 1.3k to 2.4k tokens. If you have
a case where it makes an agent do worse, I'd like to see it.

>I think there might be a misunderstanding with what an agents.md file
>is meant to do. It is meant to be a small file that lists a few
>notable things agents should know about a project.

The spec at agents.md doesn't say that. It has no required fields or
length, and says anything you'd tell a new teammate belongs there.
OpenAI's own AGENTS.md in the Codex repo is 320 lines, about four times
the size of README.

>Why should the kernel make an exception here and say no, this is the
>agents.md file you get

It's a default for people who haven't written their own, the same as
.clang-format, .cocciconfig, or .pylintrc. Anyone with their own file can still
use that instead, and the spec says "explicit user chat prompts override
everything".

>what is the point of creating a
>shared agents.md file? Is it to help experienced kernel developers?

Yes, and everyone else too. README is an index, so it helps the agent
figure out where to find things, whether that's an experienced
developer working in a subsystem or someone asking how some part of the
kernel works.

It also covers the patches maintainers get from people who never write
their own. In my tests, two current agents without AGENTS.md got the
basics wrong: one added my Signed-off-by itself, the other added no
attribution. With it, both got it right.

>Because omitting sign-offs is not helpful, they will need to add one
>even if they do not understand what it is

If someone adds their sign-off without understanding what it certifies,
that's on them. We can't have agents add it for them just because some
people would ignore its meaning anyway.

If you think a hand-written AGENTS.md would do better, feel free to
write one and propose it. For now, this one seems to be working just
fine.

-- 
Thanks,
Sasha

  reply	other threads:[~2026-09-27 14:06 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-24 13:49 Sasha Levin
2026-09-24 14:31 ` Theodore Tso
2026-09-24 15:18   ` Sasha Levin
2026-09-24 15:08 ` Bradley Morgan
2026-09-24 15:20   ` Sasha Levin
2026-09-24 15:44     ` Bradley Morgan
2026-09-24 16:57       ` Sasha Levin
2026-09-25  0:12 ` Kees Cook
2026-09-25  7:18   ` Laurent Pinchart
2026-09-26 11:12 ` Antheas Kapenekakis
2026-09-26 15:48   ` Sasha Levin
2026-09-26 17:54     ` Antheas Kapenekakis
2026-09-27  1:13       ` Sasha Levin
2026-09-27  2:42         ` Antheas Kapenekakis
2026-09-27 14:06           ` Sasha Levin [this message]
2026-09-27 15:24             ` Antheas Kapenekakis

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=arkiyMt2NIydrPhE@laps \
    --to=sashal@kernel.org \
    --cc=corbet@lwn.net \
    --cc=kees@kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lkml@antheas.dev \
    --cc=rdunlap@infradead.org \
    --cc=skhan@linuxfoundation.org \
    --cc=workflows@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®