For a subset of people the AWS version of localstack would be enough to run production loads. Which is bad for business =)

That doesn't make sense. You use AWS services because they are in the cloud, not because you want to do self-hosting. Similar to Cloudflare wrangler, localstack should be just a well-built local mocking service.

Try adding LSP support using the anthropic skills that should make it a bit more efficient.

You can allow specific commands, you do know that?

I run a generic Claude on my ~/projects/ directory and Claude logs every now and then and ask it what commands I commonly have to keep manually accepting in different projects and ask it to add them to the user-level settings.json.

Works like a charm (except when Opus 4.6 started being "efficient" and combined multiple commands to a single line, triggering a safety check in the harness).

Yes, they're even documented on the official site: https://code.claude.com/docs/en/memory#organize-rules-with-c...

...you test the interaction too? That's what Playwright does and LLMs are pretty capable of writing playwright tests for interaction.

What does this do that playwright-cli doesn't?

https://github.com/microsoft/playwright-cli

These aren't really comparable, OP's is something that records, captures and reproduces with steps.

playwright can do all of that too. I'm confused why this is necessary.

If coding agents are given the Playwright access they can do it better actually because using Chrome Developer Tools Protocol they can interact with the browser and experiment with things without having to wait for all of this to complete before making moves. For instance I've seen Claude Code captures console messages from a running Chrome instance and uses that to debug things...

Because LLM users are NIH factories?

I've also had Claude run javascript code on a page using playwright-cli to figure out why a button wasn't working as it should.

That's exactly what Playwright does, but also something you don't really need in order to debug a problem.

I think playwright doesnt capture video, right?

It does. I literally just watched a video of a Playwright test run a few minutes ago.

Yeah I’ve never seen it capture video before, but if you specify in your `AGENTS.md` that you want to test certain types of workflows, it will take progressive screenshots using a sleep interval or by interacting with the DOM.

I have zero hope, but he MIGHT have the ear of the people making the decisions and he might make a good point how if all of the "family tech support" people get pissed off about account requirements and move to Linux ... they'll start suggesting that to their families too which is kinda bad in the long run.

Even though it's been said many times that MS doesn't give a fuck about personal users, their money comes almost 100% from companies using Windows. Gaming computers etc. are a rounding error.

> Split your coding in two: The part that gets done quick, and the part where you personally care about every line of code. > This was always a problem with commercial programming for me: Employer only cares that it gets done, I care that it's good. The tension is necessary.

Use AI-assisted coding to MVP or vertical slice or however you want to call it. Prove that it works and is doable. Now you have baseline to start editing from, rewrite every single line, even the ones with just a single { if that's how you roll.

Or read it and ship it as is. Maybe adjust the agent's instructions and the project linters/formatters to match your specific style better.

They know how to cook and can if needed, but usually don't bother as they have 15 other restaurants to manage.

It's the difference between lovingly crafting heirloom tomatoes in small batches vs producing a consistent multi-ton quantity of tomatoes at an industrial scale.

There are uses for both, but job/compensation wise the heirloom grower isn't in the majority.