Yannick

Finally taking the time to use my faster.dev subscription and look at the video series. I almost skipped the "Claude Code from Scratch" one entirely, but decided to have a quick look anyway. Guess what – I didn't know you could customise the status line 🤦‍♂️

@andrewcairns Mostly PixelWatcher.io! Getting close to pushing it to production now, then an invite-only beta for those who registered interest. It’s been my playground for the past few weeks 🙂

@osteel Yeah indeed. I'm fortunate to be able to learn and experiment so much in my own time and company time. What are you working on atm?

I'm really grateful to be in an IC role at the moment. It's an important time to be hands-on, develop new skills, explore new ways of working and form new mental models.

I've now moved all my skills to a dedicated repository, with a small script to install them for Claude and Codex. I guess the upside of all this is that I can now switch from Claude Code to Codex CLI with little friction, and that's definitely a win github.com/osteel/agent-s…

Overall, Codex CLI feels much slower and clunkier than Claude Code. As I can't use Codex because of my Docker-based setup, currently, the overall experience is far better with Claude Code (when it works)

Giving Codex a go while Anthropic gets its shit together. Managed to import my Claude setup fairly easily and it's working well overall, but my project runs via Docker and it seems completely unable to interact with that. Is that a massive limitation or am I missing a trick?

First the reduced session limits, now an Opus 4.6 outage. Time to give Codex a shot I guess!

To manage growing demand for Claude we're adjusting our 5 hour session limits for free/Pro/Max subs during peak hours. Your weekly limits remain unchanged. During weekdays between 5am–11am PT / 1pm–7pm GMT, you'll move through your 5-hour session limits faster than before.

Floorboards are great until you have a kid

I just love refactoring with AI. It's like pair programming, really. I'm the navigator, keeping the big picture in mind, and implementation is so fast that I never lose my train of thoughts. No more "I know I should do this, but it would take too long to do it now"

@eMeRiKa Are you using skills at all?

@osteel Not sure what your exact use cases are, but on my end, I don't really notice any difference in: - Planning mode - Implementation - GitHub integration

Crazy how fast you hit the Claude message limit 😅 Meanwhile, I literally never run into this issue using ChatGPT + Codex. A ChatGPT Plus subscription is an absolute gold mine right now.

📢 Our next event is up! On Weds 8 April, Gina Banyard and Oliver Davies will join us for two great talks about backwards compatibility and Nix for PHP developers. 📅 Details and registration 👇 meetup.com/php-sussex/eve… Big thanks to @jumptwenty4 for sponsoring this event!

@peterfox Interesting! Talking to my computer is not something I’ve tried though. Makes me feel weird for some reason 😅

Really like this talk. Something every junior - mid developer should see. It explains perfectly why code and a lot of these features within PHP matter.

The recording of my talk Escaping the Code Maze at @PHPUKConference is available! Big thanks to the organisers. I just need to learn how to speak into a microphone on a stand 😬 youtube.com/watch?v=0emNLJ…

I sat down with Claude Code to build a test analyser. Our DX survey keeps flagging test efficiency, and I had a hunch our test pyramid was off. Wrote it up with some interactive bits. acairns.co.uk/posts/evaluati…

Just spent some time reviewing my agent skills using Anthropic's `skill-creator` skill (install via `/plugins` in Claude Code). Not just to improve the skills themselves, but also to tighten integration between them. Will do this regularly from now on

Do your coding agents often make mistakes that are not yet caught by PHPStan? What are they?