Cursor CLI • Hacker News Board

Re: Cursor CLI

#201

Post by yunohn » Fri, Aug 08, 2025, 10:52 AM UTC

what wrote: post #128

esafak wrote: post #105

Earlier quoted context omitted.

You can put them in subdirectories like CODEOWNERS files. https://ampcode.com/AGENT.md#multiple-agent-files

>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?

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

#202

Post by ascorbic » Fri, Aug 08, 2025, 10:59 AM UTC

ako wrote: post #137

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

I asked claude code for a guidelines file so it would collaborate with windsurf. This is what it proposed: --- This project uses shared planning documents for collaboration with Claude Code. Please: 1. First read and understand these files: - PLAN.md - current project roadmap and objectives - ARCHITECTURE.md - technical decisions and system design - TODO.md - current tasks and their status - DECISIONS.md - decision h…

You could create a CLAUDE.md that just contains:

  @AGENTS.md

Still messy, but at least it means it's using the same content

Re: Cursor CLI

#203

Post by eru » Fri, Aug 08, 2025, 11:05 AM UTC

dotancohen wrote: post #185

eru wrote: post #134

Earlier quoted context omitted.

> It would force me to have a useful, up to date document about how to build, run, and edit my projects. Not really: our AI agents are probably smart enough to even make sense of somewhat bad instructions.

Not the case at all. AI agents will happily turn your bad ideas into code.

Non sequitur?

I am talking about LLMs figuring out how to build your project with some bad and incomplete instructions plus educated guessing.

Re: Cursor CLI

#204

Post by calmoo » Fri, Aug 08, 2025, 11:11 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

The font on that RFC is aggressively squashed and aliased, why?

Re: Cursor CLI

#205

Post by epolanski » Fri, Aug 08, 2025, 11:20 AM UTC

meowtimemania wrote: post #127

teaearlgraycold wrote: post #100

Earlier quoted context omitted.

Why is Claude Code better than Cursor?

My company has a huge codebase, for me cursor would freeze up / not find relevant files. Claude code seems able to find the right files by itself. I seem to always have better outcomes with Claude code.

Cursor and these tools evolve quite fast.

The Cursor you used a month ago is not the one you get now.

Just saying that because in this space you should always compare latest X with latest Y.

I too switched weeks ago to Claude Code. Then between the times I am out of tokens I launch Cursor and actually find it...better than I remember if not on par with Claude Code (the model and quality of prompts/context matters more than the IDE/CLI tool used too).

Re: Cursor CLI

#206

Post by epolanski » Fri, Aug 08, 2025, 11:22 AM UTC

plantain wrote: post #142

teaearlgraycold wrote: post #100

Earlier quoted context omitted.

Why is Claude Code better than Cursor?

CC just feeds the whole codebase and entire files into the model, no RAG, nothing in the way. It works substantially better because of that, but it's $expensive$.

The more stuff you put in the context the worse models perform. All of them.

Larger context is a bonus sometimes, but in general you're degrading the quality of the output by a lot.

Precise prompting and context management is still very important.

Re: Cursor CLI

#207

Post by ksynwa » Fri, Aug 08, 2025, 11:25 AM UTC

Why are all these coding agents being created as terminal applications? Feels like the kind of thing that the tech industry would publish as an electron app.

Re: Cursor CLI

#208

Post by andai » Fri, Aug 08, 2025, 11:28 AM UTC

ksynwa wrote: post #207

Why are all these coding agents being created as terminal applications? Feels like the kind of thing that the tech industry would publish as an electron app.

Cursor minus CLI is already that.

Re: Cursor CLI

#209

Post by daliusd » Fri, Aug 08, 2025, 11:29 AM UTC

ksynwa wrote: post #207

Why are all these coding agents being created as terminal applications? Feels like the kind of thing that the tech industry would publish as an electron app.

Because you can script terminal app (ideally, at least you can do that with opencode.ai) and that opens some amazing opportunities.

Re: Cursor CLI

#210

Post by epolanski » Fri, Aug 08, 2025, 11:33 AM UTC

lvl155 wrote: post #76

didibus wrote: post #73

Earlier quoted context omitted.

I'm actually starting to think the opposite. If Cursor can build the better UX for all the use-cases, mobile/desktop chatbot, assistant, in IDE coding agent, CLI coding agent, web-based container coding agent, etc. In theory, they can spend all their resourcing on this, so you could assume they could have those be more polished. If they win the market-share here, than the models are just commodity, Cursor lets you pi…

No, model providers are not going to let Cursor eat their pie. The biggest cost in AI is in developing LLM models and inference. Players incurring those costs will basically control this market.

Unless a model provider utterly and completely dominates the scene (which won't happen, unless for brief periods of time) well thought tools with a consistent ux and switchable model providers have absolutely their place.

Models are commodities.