10 Comments
User's avatar
Caleb Mellas's avatar

Thanks for sharing your experience, Daniel! I’ve been meaning to try out Claude Code for a while now and this pushed me over the edge to jump in and get going with it.

Nice straightforward tips, and demystified it a little for me. 👍

Expand full comment
Daniel Moka's avatar

Thanks brother, feel free to DM me if you have any question about it!

Expand full comment
arrlan's avatar

great post! I’ve also found that when working with UI, using Playwright mcp to capture screenshots for pixel-perfect checks or to grab console logs works really well

Expand full comment
Fejan Malek's avatar

Thanks nice post

Also currently I have using qwen cli free version I did used claude code in past

Expand full comment
Piotr Laskowski's avatar

> Give Claude screenshots

The real strength of agent mode is when agent can check the output (logs, screenshots) itself.

E.g. I added playwright MCP server so that agent itself can load the site and take screenshot or investigate the DOM tree to check it it achieved the result.

Expand full comment
Ameer Hamza's avatar

Cursor uses sonnet and gpt models at it's end

Expand full comment
Maximiliano Contieri's avatar

Amazing to have custom windsurf.md, claude.md etc

Expand full comment
Dan's avatar

I’ve seen several of these posts now about devs moving exclusively to Claude from Cursor… but my experience is that Claude is a massive token hog, it eats up a ton of money for small outputs compared to other tools. Do you have a workaround for this or a different experience?

Expand full comment
Marwane's avatar

really helpful thanks for sharing this Daniel.

Expand full comment
Victoria Cheng's avatar

Um, interesting, I didnt know you can put Claude markdown in each folder...🤔

Expand full comment