News for hackers. Stuff that matters.
Re:Evaluating AGENTS.md: are they helpful for coding agents? by giancarlostoro on Tuesday February 17, 2026 @07:36AM (#47046819)
> The biggest usecase for AGENTS.md files is domain knowledge that the model is not aware of and cannot instantly infer from the project. That is gained slowly over time from seeing the agents struggle due to this deficiency.

This. I have Claude write about the codebase because I get tired of it grepping files constantly. I rather it just know “these files are for x, these files have y methods” and I even have it breakdown larger files so it fits the entire context window several times over.

Funnily enough this makes it easier for humans to parse.

Re:Evaluating AGENTS.md: are they helpful for coding agents? by belval on Tuesday February 17, 2026 @07:51AM (#47046959)
My pet peeve with AI is that it tends to work better in codebase where humans do well and for the same reason.

Large orchestration package without any tests that relies on a bunch of microservices to work? Claude Code will be as confused as our SDEs.

This in turns lead to broader effort to refactor our antiquated packages in the name of "making it compatible with AI" which actually means compatible with humans.

Re:Evaluating AGENTS.md: are they helpful for coding agents? by anamexis on Tuesday February 17, 2026 @10:51AM (#47048839)
Why is that a pet peeve, though? Seems like a win/win.
Re:Evaluating AGENTS.md: are they helpful for coding agents? by giancarlostoro on Tuesday February 17, 2026 @11:56AM (#47049674)
In my opinion it’s not just compatible with AI its code that now fits in your head. Lots of famous “we can rewrite it later” remarks throughout my career… Well the AI can rewrite it, and now you can understand it.
Re:Evaluating AGENTS.md: are they helpful for coding agents? by dsjoerg on Wednesday February 25, 2026 @11:58AM (#47154197)
AI is teaching some people that best practices actually matter.