From: Steven Rostedt <rostedt@goodmis.org>
To: Sasha Levin <sashal@kernel.org>
Cc: Greg KH <gregkh@linuxfoundation.org>,
corbet@lwn.net, josh@joshtriplett.org, kees@kernel.org,
konstantin@linuxfoundation.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, workflows@vger.kernel.org
Subject: Re: [PATCH v2 2/2] agents: add unified agent coding assistant configuration
Date: Wed, 13 Aug 2025 20:36:47 -0400 [thread overview]
Message-ID: <20250813203647.06e49600@gandalf.local.home> (raw)
In-Reply-To: <aJirFxwuzxyau1j-@lappy>
On Sun, 10 Aug 2025 10:22:15 -0400
Sasha Levin <sashal@kernel.org> wrote:
> We don't strictly need this patch. Here are the options I came up with:
>
> 1. Multiple agent files: agents automatically read our rules, higher
> chance of comlpiance, doesn't require user to do anything manually.
>
> 2. No agents files at all: this means that the user will need to
> explicitly trigger an action, otherwise all the tools I've tested it
> with will happily ignore the README file even when prompted to do other
> actions on the codebase (analyze code/write a patch/etc).
>
> 3. Only "AGENTS.md" which seems like a few of the tools are trying to
> standardize on. We could also use it in the future to add prompt cues
> that might not be relevant within the README.
2 or 3 are the only options that seems reasonable. I agree with Greg. I
wouldn't want these files adding noise to the main directory for every
agent.
>
> We could also start with most of these files, along with a statement
> that they will be removed within 12 months to give the various tools
> time to standardize around something.
Ideally, in 12 months they will all standardize on AGENTS.md and that's all
we will need. Let's not enable them to do their own thing in the mean time.
If we add this file, I would suspect it would help encourage the agents to
use it.
The best "standards" are the ones that are done in collaboration before
they are added to a specification ;-)
-- Steve
next prev parent reply other threads:[~2025-08-14 0:36 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-09 23:40 [PATCH v2 0/2] Add unified configuration for coding agents Sasha Levin
2025-08-09 23:40 ` [PATCH v2 1/2] README: restructure with role-based documentation and guidelines Sasha Levin
2025-08-10 15:44 ` Joe Perches
2025-08-10 16:46 ` Sasha Levin
2025-08-11 0:10 ` Joe Perches
2025-08-11 0:06 ` Randy Dunlap
2025-08-11 8:22 ` Geert Uytterhoeven
2025-08-11 15:48 ` Sasha Levin
2025-08-15 6:19 ` Kees Cook
2025-08-09 23:40 ` [PATCH v2 2/2] agents: add unified agent coding assistant configuration Sasha Levin
2025-08-10 7:01 ` Greg KH
2025-08-10 14:22 ` Sasha Levin
2025-08-14 0:36 ` Steven Rostedt [this message]
2025-08-15 6:23 ` Kees Cook
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=20250813203647.06e49600@gandalf.local.home \
--to=rostedt@goodmis.org \
--cc=corbet@lwn.net \
--cc=gregkh@linuxfoundation.org \
--cc=josh@joshtriplett.org \
--cc=kees@kernel.org \
--cc=konstantin@linuxfoundation.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=sashal@kernel.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