News for hackers. Stuff that matters.
Re:Cursor CLI by dgunay on Thursday August 07, 2025 @09:24PM (#44832391)
I just wish the AGENTS.md standard wasn't a single file. I have a lot of smaller context documents that aren't applicable to every task, so I like to throw them into a folder (.ai/ or .agents/) and then selectively cat them together or tell the agent to read them.
Re:Cursor CLI by esafak on Thursday August 07, 2025 @10:26PM (#44832775)
You can put them in subdirectories like CODEOWNERS files. https://ampcode.com/AGENT.md#multiple-agent-files
Re:Cursor CLI by what on Friday August 08, 2025 @12:36AM (#44833454)
>When multiple files exist, tools SHOULD merge the configurations with more specific files taking precedence over general ones.

How is the tool supposed to merge multiple md files?

Re:Cursor CLI by esafak on Friday August 08, 2025 @12:41AM (#44833477)
The same way it synthesizes anything else. We're talking about LLMs here; this is their bread and butter.
Re:Cursor CLI by yunohn on Friday August 08, 2025 @06:52AM (#44835555)
Most AI solutions make tracing the finally assembled prompt a bit difficult.

However, if you look through the source code or network requests, you’ll see that merging just means naive “concatenation”.

Re:Cursor CLI by troupo on Friday August 08, 2025 @03:25AM (#44834450)
Elixir has this idea with usage rules: https://hexdocs.pm/usage_rules/readme.html
Re:Cursor CLI by dotancohen on Friday August 08, 2025 @05:12AM (#44835018)
You could have a python script that generates the MD file on the fly, based on how you want to prompt the model. I think it's kind of funny, how deep we are getting with tools instructing tools instructing tools.