Kevin Wolf

Currently building Dobby, my very own coding agent on top of @badlogicgames's Pi. After spending hours trying to get Claude Code working the way I wanted, I decided to try Pi, and its extensibility is huge. Highly recommend giving it a try. Will continue posting updates about Dobby in case anyone wants to try it 🧦✨

I have been using Claude Code in the desktop app and I can say I missed being out of the terminal. It is way more ergonomic!

@fmontes Apenas pal cumple

Is here

In @tan_stack we trust.

@mattpocockuk @theo You should research pi and instead teach people how to build their own harnesses.

I don't know what the fuss is about. Anthropic's rules on using subscriptions are very simple: Claude Code = OK Claude's online platform = OK Agent SDK running in personal software = OK... ish? Agent SDK running in commercial software = NOT OK Claude Code running in CI = ?? Oh, maybe it's not so simple... Agent SDK running in CI = ?? claude -p running in CI = ?? claude -p running in personal software = OK claude -p running on open source software, but run on my personal computer = ?? claude -p running on distributed sandboxes, kicked off by me = ?? Distributing open source software which relies on claude -p, and documenting how to use your subscription with it = ?? A thousand other edge cases = ?? Let me be clear. I have never before experienced, from any developer tool, such a frustrating lack of clarity over the basic terms of usage. I personally asked, 3 weeks ago, and have received nothing but delays. The recent @bcherny announcement did absolutely nothing to clarify things. I say this as someone who just released a Claude Code course - my incentives all align with supporting Anthropic.

@tannerlinsley Or do it in Costa Rica, the TanStack logo is already on brand with the pura vida vibes. Just saying.

Instead of doing a TanStack Conf, I'm seriously considering inviting everyone to just meet up on a Caribbean-bound cruise ship. It'd be cheaper in every way, you could bring as many family/friends as you want, and instead of wasting time on talks/booths, we can just chat endlessly about JS/TS/Web over unlimited freestyle soda machines, soft-serve ice-cream and mini golf. TanStack Cruise 2028

@danestves El diseño se ve muy “claudy” échale un ojo a impeccable.style

Rediseñando el home de Vela llegue a este hermoso mockup, nada de cards, nada encerrado en ese "ai-slop" Before / After

@santtiagom_ No me gusta para nada tener que distribuir un marketplace + un plugin. Mucho mejor el sistema de open code o pi en donde se pueden instalar como NPM packages.

En Claude Code podés construir skills, hooks, subagents y MCP servers. Pero, ¿cómo compartís todo eso con tu equipo o con la comunidad? Con plugins. Un plugin es una forma de empaquetar esas capacidades para que otra persona las instale y las use directamente. ¿Cómo se arma? Es una carpeta con una estructura definida. Tiene un archivo obligatorio: .claude-plugin/plugin.json → define el plugin (nombre, versión y configuración) A eso le sumás lo que quieras compartir: - skills//SKILL.md - agents/ → agentes (.md) - hooks/hooks.json - .mcp.json → MCP servers Lo publicás en un marketplace (un lugar donde se distribuyen plugins). Hay uno oficial de Anthropic. Otra persona lo instala desde Claude Code: /plugin install Y Claude Code lee la estructura, registra las skills, activa los agentes y conecta los MCP. Así, quien instala tu plugin pasa a tener tus skills, agentes y automatizaciones listas para usar.

@fmontes @AnthropicAI Según entendí Capybara es el nombre interno y Mithos será el comercial.

Se filtra que se viene dos modelos nuevos de @AnthropicAI. Mythos: más poderoso que Opus 4.6 Y otro que internamente llaman Capybara enfocado en cybersecurity y vulnerabilidades.

@danazkari @jeudyx Que es la vara mae

@jeudyx Le diría que use neovim pero eso es para raros

Yo uso mucho el TextEdit en Linux, para mi poder integrarle un LLM sería una killer app por la que pagaría. Conocen alguna así? (sino para hacerla vibecodearla jaja)

@stefnox @dani_avila7 Why the hate?

@dani_avila7 So it’s just TeamViewer, but with extra steps and hype.. do you want a medal for rediscovering screen sharing, or what?

Yes, Claude is controlling my computer from my phone with Dispatch I don’t like posting about anything I haven’t actually tried myself Reposting a video is easy, quality content comes from actually experimenting with new features So I saw the announcement that Claude Dispatch now controls your computer and I simply asked it to open Twitter and like a Claude post Done ✅ Now we need SKILL.md files with instructions to use other apps on your computer… OMG! this is getting more interesting and more dangerous by the minute

@cnakazawa @dillon_mulroy Maybe a linter? It detects unused rules. But now that I think about it, maybe a linter rule could do the work right?

@kvnwolf @dillon_mulroy I would like to find a way, but I'm not 100% sure where it should sit below between Oxlint/Vite/Rolldown.

the clanker guardrail stack

@cnakazawa @dillon_mulroy Any plans to implement something like knip into vite+?

@dillon_mulroy Get rid of Husky, Oxlint and Vitest. Vite+ takes care of all of these. Enable typeCheck in the lint “options” in your Vite config and get rid of typescript, too. Just knip and Vite+, it’s cleaner.

@fmontes Que errores te da?

Hacer SDKs de react que funcionen en server y el browser es un dolor de colon. Hasta cuando está sufridera?

@official_taches Yes! I really want to support the project and use it since it seems really good. I can send you a report tomorrow evening when I’m back at the computer.

@official_taches Of all the almost five different times I’ve tried to use the tool (v1 and now v2), I find myself fighting it. Instead of getting shit done, I get a ton of crap and nothing works. :(

@brolag @fmontes En que te ha dado errores? yo llevo usándolo como una semana y no me ha fallado. Mas bien me encanta el contepto de poder agregar tabs dentro de un split.

@kvnwolf @fmontes Mae esta increíble esto es justo lo que necesito. Pero esta extremadamente buggy... Cuando lo mejoren esto definitivamente va a reemplazar Ghostty vanilla.

Necesito un TODO-List app donde cada item sea una terminal (ojo una terminal, no un chat...) ¿Alguien conoce o costruyó algo así? Pregunto antes de inventar el agua tibia.

Mae si pero eso es lo que se hace al analizar imágenes, analizar un conjunto de bytes para compararlo con la data de entrenamiento. Pero piense en convertir esos bytes a tokens, la cantidad de tokens que hay que analizar vs analizar un API que indica en dónde están los elementos interactivos. Al final eso es lo que hacen los render engines, parsear JSON o algún contrato similar y pintar el UI.

@kvnwolf Yo si creo que pronto lo vamos a ver. Al final lo que vemos en el monitor es solo un stream de bytes que una IA fácilmente podria analizar en tiempo real y enviar señales de teclado y mouse para interactuar como lo hace un humano. Ya deben estar trabajándolo.

Hay algo que siento que aún le hace bastante falta a las IAs para ser ya next level útiles y es poder ejecutar UIs (no solo web, por ej, también videojuegos) y probar cosas directamente sin tener uno que ser sus "ojos". Se que para web ya hay algunos tools, pero

@jamonholmgren Looks good, just a quick suggestion to be more token efficient; agents doesn't need a markdown link, you can just put the path and they'll follow when needed, that saves you tokens.

@kvnwolf I haven't yet found a place where skills work better than my current system, so I've kept it simpler with just markdown docs. Progressive disclosure is a good way to say it. AGENTS is the router, each doc may have references to deeper docs as needed. It's worked great so far.

My current agentic workflow is about 5x faster, better quality, I understand the system better, and I’m having fun again. My previous workflows have left me exhausted, overwhelmed, and feeling out of touch with the systems I was building. They also degraded quality too much. This is way better. I’m not ready to describe in detail. It’s still evolving a bit. But I’ll give you a high level here. I call this the Night Shift workflow.