131–140 of 275 posts
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?
Earlier quoted context omitted.
You can spin up the Cursor CLI inside the terminal of your IDE of choice and not be tethered to Claude's models.
Is there a better agent than the anthropic one
But if you take speed/availability/cost into account, there might be "better" offers out there. I did some tests w/ windsurf when they announced their swe1 and swe1-lite models, and the -lite could handle easy tasks pretty well. I also tested 4.1-mini and 4.1-nano. There are tasks that I could see them handle reliably enough to make sense (and they're fast, cheap and don't throttle you).
Earlier quoted context omitted.
In my experience, it is much better at tool-calling, which is huge when we're talking about agentic coding. It also seems to do a better job of keeping things cleaning and not going off on tangents for anything that isn't accomplished in one shot.
I have had the exact opposite experience. Claude Code in any meaningful codebase for me gets stuck in loops of doing the wrong thing. Then when that doesn't work it deletes files and makes its own that don't have the problem it's encountering. Cursor on the other hand, especially with GPT-5 today but typically with Sonnet 4.1, has been a workhorse at my company for months. I have never had Claude Code complete a mean…
Earlier quoted context omitted.
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.
Not really: our AI agents are probably smart enough to even make sense of somewhat bad instructions.
I really like the IDE. It makes enough mistakes that I need to be constantly testing and catching little errors. I’ll interrupt the flow often when it’s going down a path I don’t want it to. When using Codex, for example, it’s doing too much in the background that is harder to correct afterwards. Am I doing this wrong?
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?
This may not work for everyone, but as a solo dev who wants to keep a real mental model of my work (and not let it get polluted with AI slop), the Claude Code approach just works really well for me. It's like having a coding partner who can iterate and change direction as you talk, not a junior dev who dumps a pile of code on your plate without discussion.
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
---
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 history with rationale
- COLLABORATION.md - handoff notes from other tools
2. Before making any significant changes, check these documents for:
- Existing architectural decisions
- Current sprint priorities
- Tasks already in progress
- Previous context from Claude Code
3. After completing work, update the relevant planning documents with:
- Task completion status
- New decisions made
- Any changes to architecture or approach
- Notes for future collaboration
Always treat these files as the single source of truth for project state.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…
opencode and Crush can use any model, so apart from a nicer visual experience, are there any aspects that actually make you more productive in one vs the other?
Earlier quoted context omitted.
In my experience, it is much better at tool-calling, which is huge when we're talking about agentic coding. It also seems to do a better job of keeping things cleaning and not going off on tangents for anything that isn't accomplished in one shot.
I have had the exact opposite experience. Claude Code in any meaningful codebase for me gets stuck in loops of doing the wrong thing. Then when that doesn't work it deletes files and makes its own that don't have the problem it's encountering. Cursor on the other hand, especially with GPT-5 today but typically with Sonnet 4.1, has been a workhorse at my company for months. I have never had Claude Code complete a mean…
You probably mean Opus 4.1; there's no Sonnet 4.1 yet.