News for hackers. Stuff that matters.
Re:Ask HN: Do you still spend time maintaining Claude.md / A... by bisonbear on Saturday May 16, 2026 @12:20PM (#48161536)
My advice, from doing this myself and reading best practices, would be:

- Keep it concise, use progressive disclosure / nested AGENTS.md for information expansion - Give agent the high level repo structure if necessary - Have a "why" section to align the agent, high level, what your code is doing - Keep behavior instructions positive where possible, eg Always clarify intent before acting

Re:Ask HN: Do you still spend time maintaining Claude.md / A... by david_d8912 on Saturday May 16, 2026 @12:24PM (#48161568)
cool. I agree with all the front points. The last part ```Keep behavior instructions positive where possible```, do you have good experience on it. I'm only asking since my own experience is they're constantly not followed.
Re:Ask HN: Do you still spend time maintaining Claude.md / A... by bisonbear on Saturday May 16, 2026 @01:26PM (#48162108)
Yeah, I've found that to be more effective. Going with the example "Always clarify intent before acting" > "Never act without getting intent first", seemingly because telling the agent NOT to do something sometimes primes it to do that exact thing