(blog.google)

1362 points sync | 1 comments | 25 Jun 25 13:10 UTC | HN request time: 0.212s | source

GitHub: https://github.com/google-gemini/gemini-cli

Show context

eisbaw ◴[25 Jun 25 19:42 UTC] No.44381169[source]▶

>>44376919 (OP) #

Can't we standardize on AGENTS.md instead of all these specific CLAUDE.md and now GEMINI.md.

I just symlink now to AGENTS.md

replies(4): >>44384292 #>>44384792 #>>44388004 #>>44388340 #

22c ◴[26 Jun 25 04:55 UTC] No.44384292[source]▶

>>44381169 #

Hmm kinda makes sense to keep them separate because the agents perform differently, right?

You might want to tell Claude not to write so many comments but you might want to tell Gemini not to reach for Kotlin so much, or something.

A unified approach might be nice, but using the same prompt for all of the LLM "coding tools" is probably not going to be as nice as having prompts tailored for each specific tool.

replies(1): >>44386857 #

seunosewa ◴[26 Jun 25 12:41 UTC] No.44386857[source]▶

>>44384292 #

Put in the file:

Instructions for Claude:

- ...

Instructions for Gemini:

- ...

replies(2): >>44388102 #>>44388171 #

1. breakingcups ◴[26 Jun 25 14:59 UTC] No.44388102[source]▶

>>44386857 #

But then the irrelevant instructions are just cluttering the context.

↑

Gemini CLI