Magimetal 👨‍💻🤖💊

Hot take: Vibe coding only works well if you already know how to code.

@lydiahallie Is this diversion from the spec or will the spec update for this? Skills are really meant to be universal and proprietary functionality makes it tough.

if your skill depends on dynamic content, you can embed !`command` in your SKILL.md to inject shell output directly into the prompt Claude Code runs it when the skill is invoked and swaps the placeholder inline, the model only sees the result!

@seerg__ I just want the fonts...

wake up honey, new leveling exploit just dropped

Hooks are coming to codex. That’s all I wanted to say.

@melvynx It says that's a credit you have that will be applied to your next invoice, not how much it cost you the last 4 days...

Just so people know: I used Cursor for 4 days with API credits enabled and spent $536 This is the REAL cost of coding with AI Claude Code and Codex are just hiding it If VC money stops, we'll all be paying $200 a day just to code with frontier models

@Gothalion This is actually so cool for you. Excited to see what y'all have been cooking!

This will be the last year I’m not at GDC

The only to-dos method that has worked for me: Every week I make a weekly note, and write my to-dos for the week. I may add more items to it during the week. If any items didn't get done I roll them over to the next weekly note or drop them. That's it.

@ashwinhegde19 @thdxr @opencode @steipete It used to work, does it not now?

Will OpenCode Go be supported as a provider in OpenClaw ? @thdxr @opencode @steipete

After todays @opencode release, I can't tell if Task is using my subagents or not anymore (or it's just not using them and that's why I can't tell) 😅

Now available: 𝚗𝚙𝚖 𝚒 𝚌𝚑𝚊𝚝 Write once, chat anywhere. 𝚌𝚑𝚊𝚝 makes it easy to build bots for Slack, Discord, Teams, Google Chat, GitHub & Linear, all with the same code.

this is huge. all agents have to do is send "Accept: text/markdown" and we’ll automatically convert the response to Markdown on-the-fly for any enabled site. way fewer tokens. no need to handle it on your own.

@maxbittker Super interesting, thanks for sharing. 4.6 using double the tokens!

racing Opus 4.6 against 4.5 to max out a Runescape account

Going to try and go cook for a few days since this site is just going to be a mess of "OMG I just one-shot xyz thing" for the next week 😂

@Gothalion Wonder how the gameplay loop will feel. Dauntless vibes.

Im more into this than any previous Horizon game.

This is a petition to get @AnthropicAI / @claudeai code to support the .agents/skills standard, just as these have: - amp - codex cli - factory/droid - gemini cli - gh copilot - kimi cli - opencode - vscode - etc Like this post if you want them to support .agents/skills ✊

GPT-5.2 and GPT-5.2-Codex are now 40% faster. We have optimized our inference stack for all API customers. Same model. Same weights. Lower latency.

@stefanofusai @iannuttall @AnthropicAI @claudeai @agents For sure there are ways around it but I still think it would be better to support it, even if additive

@MagiMetal @iannuttall @AnthropicAI @claudeai You can add @AGENTS.md to your CLAUDE.md to fix this :) It's also a nice way to separate Claude-specific instructions from generic agents instructions!

📣 Open call to agent builders: Let's read agent skills from `.agents/skills`, so people don't have to manage separate folders per agent. Today we pulled the trigger for Codex to read `.agents/skills`. Goal is to deprecate `.codex/skills`. Pls like/tag/RT for momentum.