Build custom Skills to teach Claude specialized tasks. Create once, use everywhere—from spreadsheets to coding. Available across Claude.ai, API, and Code.

According to a report from the Austrian daily newspaper Kronen Zeitung, the EU plans to further restrict smoking and tobacco sales across the bloc.

Sponsorship is appreciated! ripgrep 15 is a new major version release of ripgrep that mostly has bug fixes, some minor performance improvements and minor new features. In case you haven't heard of...

Elixir v1.19 released: type checking of protocols and anonymous functions, broader type inference, improved compile times, and more

I'm two weeks behind on the newsletter (/newsletter/), so I was trying to be responsible by resisting the urge to document the success I've had with my current coding agent setup. My self-restraint has paid off, as Peter Steinberger essentially wrote the exact post I was planning (https://steipete.me/posts/just-talk-to-it) to write. There's lots of good nuggets in here, and it's uncanny how many I agree with: 1. I also use Codex CLI (https://developers.openai.com/codex/cli/) (well, this fork (https://github.com/just-every/code)) on a $200 ChatGPT Pro (https://openai.com/index/introducing-chatgpt-pro/) plan. Claude Code was an epiphany, but their models are overrated for the task, whereas GPT 5's variants are more adherent and diligent across the board. OpenAI's usage limits are virtually infinite by comparison, too 2. I run 3-6 agents in parallel (usually up to 3 per project and up to 2 projects at a time). Unlike Peter, it's rare I let two agents edit the same codebase simultaneously. GPT 5's codex-medium variant is so fast that the time-consuming activities are brainstorming, researching, unearthing technical debt, and planning refactors 3. While git worktrees (https://git-scm.com/docs/git-worktree) are a very cool feature, they dramatically slow down code integration with merge conflicts. Additionally, I've found it's hard to avoid API and port conflicts when running numerous development instances simultaneously. And when an environment stops working, agents will silently start coding based on speculation and conjecture. Fast feedback through observable execution of code is the single most important thing , so the risk isn't worth the (marginal) reward 4. Hooks, custom commands, and fancy hacks like coder's undocumented auto-drive mode (https://github.com/just-every/code/blob/main/code-rs/tui/src/chatwidget/auto_coordinator.rs#L158) are nice, but they're no replacement for thinking really hard about what you want But really, the reason I've had so much success with Codex in comparison to Claude is that if you get off your ass and do the hard thinking necessary to arrive at an extremely crisp and well-informed articulation of what you want, why you want it, and what obstacles it will face, today's agents will generally do a really good job.

I have been vibe coding like a madman for forty days and forty nights. It’s a long story, so I’ll summarize in these three pictures.

ast-grep playground is an online tool that lets you explore AST, debug custom lint rules, and inspect code rewriting with instant feedback.