Cursor CLI • Hacker News Board

Re: Cursor CLI

#91

Post by bikeshaving » Fri, Aug 08, 2025, 1:28 AM UTC

thehamkercat wrote: post #21

I wonder when all of them will adopt AGENT.md and stop using gemini.md/claude.md/crush.md/summary.md/qwen.md https://agent.md [redirect -> https://ampcode.com/AGENT.md ] https://agent-rules.org

Every time I’ve ever read a {CLAUDE|GEMINI|QWEN}.md I’ve thought all this information could just be in CONTRIBUTING.md instead.

Re: Cursor CLI

#92

Post by hahajk » Fri, Aug 08, 2025, 1:38 AM UTC

bikeshaving wrote: post #91

thehamkercat wrote: post #21

I wonder when all of them will adopt AGENT.md and stop using gemini.md/claude.md/crush.md/summary.md/qwen.md https://agent.md [redirect -> https://ampcode.com/AGENT.md ] https://agent-rules.org

Every time I’ve ever read a {CLAUDE|GEMINI|QWEN}.md I’ve thought all this information could just be in CONTRIBUTING.md instead.

Yes! I want an option to always add README.md to the context; It would force me to have a useful, up to date document about how to build, run, and edit my projects.

Re: Cursor CLI

#93

Post by stonecharioteer » Fri, Aug 08, 2025, 1:38 AM UTC

thehamkercat wrote: post #21

I wonder when all of them will adopt AGENT.md and stop using gemini.md/claude.md/crush.md/summary.md/qwen.md https://agent.md [redirect -> https://ampcode.com/AGENT.md ] https://agent-rules.org

Symlinks $AGENT.md to AGENT.md in your repo.

Re: Cursor CLI

#94

Post by extr » Fri, Aug 08, 2025, 1:45 AM UTC

byronic wrote: post #85

I'm having trouble finding a use for this outside of virtualized unused environments. Why not instead give me a virtual machine that runs this in a confined storage space? I would _never_ give an LLM access to any disk I own or control if it had anything more than read permissions

Why not? Have you ever actually used these things? The risk is incredibly low. I run claude code with zero permissions every day for hours. Never a problem.

Re: Cursor CLI

#95

Post by anp » Fri, Aug 08, 2025, 1:46 AM UTC

thehamkercat wrote: post #21

I wonder when all of them will adopt AGENT.md and stop using gemini.md/claude.md/crush.md/summary.md/qwen.md https://agent.md [redirect -> https://ampcode.com/AGENT.md ] https://agent-rules.org

FWIW at least with Claude and Jules on a project I have a decent setup where I put all of the real content in an agents.md and then use “@agents.md” in CLAUDE.md. If all of the tools supported these kinds of context references in markdown it wouldn’t be that hard to have a single source of truth for memory files.

Re: Cursor CLI

#96

Post by blurbleblurble » Fri, Aug 08, 2025, 1:59 AM UTC

lvl155 wrote: post #78

blurbleblurble wrote: post #26

Hopefully this one is as good as Claude code. None of them that I've tried have come close yet.

Have you tried opencode?

Yeah, opencode and crush. I'm gonna give Claude code router a good try soon.

Re: Cursor CLI

#97

Post by daviding » Fri, Aug 08, 2025, 2:01 AM UTC

Can you pick thinking models with this or is that implied?

GPT-5 seems a bit slow so far (in terms of deciding and awareness). I’ve gone from waiting for a compiler, to waiting for assets to build to now waiting for an agent to decide what to do - progress I guess :)

Re: Cursor CLI

#98

Post by mrcwinn » Fri, Aug 08, 2025, 2:04 AM UTC

I went from years of vscode to "Cursor is the future" to never using Cursor at all. Claude Code, even with new limits, is just too good. If I were to switch to gpt-5, why wouldn't I just use Codex? I'm struggling to understand the value of what they're presenting.

Re: Cursor CLI

#99

Post by fastball » Fri, Aug 08, 2025, 2:04 AM UTC

thehamkercat wrote: post #21

I wonder when all of them will adopt AGENT.md and stop using gemini.md/claude.md/crush.md/summary.md/qwen.md https://agent.md [redirect -> https://ampcode.com/AGENT.md ] https://agent-rules.org

That sounds nice and I have the same pain, but not sure AGENT.md is the right abstraction either. After all, these models are indeed different and will respond differently even given the same prompting. Not to mention that different wrappers around those models have different capabilities.

e.g. maybe for CURSOR.md you just want to provide context and best practices without any tool-calling context (because you've found it doesn't do a great job of tool-calling), while for CLAUDE.md (for use with Claude Code) you might want to specify tools that are available to it (because it does a great job with tool calling).

Probably best if you have an AGENT.md that applies to all, and then the tools can also ingest their particular flavor in addition, which (if anything is in conflict) would trump the baseline AGENT file.

Re: Cursor CLI

#100

Post by teaearlgraycold » Fri, Aug 08, 2025, 2:05 AM UTC

mrcwinn wrote: post #98

I went from years of vscode to "Cursor is the future" to never using Cursor at all. Claude Code, even with new limits, is just too good. If I were to switch to gpt-5, why wouldn't I just use Codex? I'm struggling to understand the value of what they're presenting.

Why is Claude Code better than Cursor?