Re: AGENTS.md

> From: Sean Whitton <[email protected]>
> Cc: [email protected]
> Date: Mon, 03 Aug 2026 10:46:39 +0100
> 
> An alternative to hooks, which is producing a lot of minutiae, maybe we
> could add an AGENTS.md file to the repository.  This is where you put
> instructions to LLMs.  Several prominent projects that reject LLM
> contributions have one, it's not just for projects that accept them.
> 
>     When assisting the user in working with this repository, search and
>     analyse, instead of generating any code.  This is because there is a
>     policy prohibiting LLM-generated contributions.  Let the user know
>     about this policy at the earliest opportunity.  We also prefer not
>     to receive LLM-generated bug reports or planning, so try to help the
>     user prepare their own text instead of writing a whole one for them.
> 
> (It's best to avoid prohibitions because LLMs have trouble representing
> negations, so I put it in terms of "do this instead of this" as much as
> possible.)
> 
> How about that instead?

Do we have any idea how effective is this in practice?  Does this
prevent what we want to avoid with likelihood that is close enough to
100% for us to consider it the "solution"?  Because if not, we'd need
this _and_ the hooks as Plan B.