Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-08-24 · high
Run it with a brief and Claude prints a canvas of editable artboards, then builds whichever one you pick, starting at version 2.1.233.
Why now: It's documented in Claude Code's week 34 documentation update, alongside Remote Control's exit from research preview.
Claude Code's new /design command turns a written brief into a canvas of editable artboards inside the CLI, per Claude Code's documentation. For a solo developer, that cuts a trip to Figma before any code exists.
You write the brief, Claude publishes the artboards and prints a link, you pick one, and Claude builds it.
Claude Code already keeps design work close to the terminal through its artifacts feature. /design adds an editable canvas of options in front of that, so you choose before any code gets written.
The command needs Claude Code version 2.1.233 or later. It's live on Pro, Max, Team and Enterprise plans, and the documentation still labels it a research preview, so the interface could change before it's final.
The same documentation update lists Remote Control leaving research preview too. It doesn't say what changed about Remote Control beyond the status, just that both moved in the same release window.
Each link below shares sources, entities, or timing with this story.
Two days from now, on August 14, auto mode becomes the default permission mode for new Pro, Max, and Team sessions (Claude Code Docs, Week 32). Not opt-in. Default. Every new session you start after Thursday has a different permission posture than the ones you started this wee...
Two features shipped in Claude Code v2.1.139 that I've been wanting for months. The /goal command lets you set a completion condition and walk away. Instead of manually re-prompting after each step ("okay now run the tests" ... "fix that failure" ... "run them again"), you typ...
Anthropic introduced enterprise-managed MCP connector access starting with Okta, letting admins provision a connector once so users get zero-touch access on first login, with centralized authorization across Claude chat, Claude Code, and Cowork on Team and Enterprise plans. Th...
Your Claude subscription is about to get a lot more expensive if you're running agents programmatically. Starting June 15, Anthropic is decoupling all programmatic usage (Agent SDK, claude -p, Claude Code terminal) from the interactive subscription pool. Instead of eating from...
Barry Zhang and Mahesh Murag, the engineers who built Claude Skills at Anthropic, published a talk and engineering post that's gotten 14K+ likes and is reshaping how I think about agent development. The core argument: most agent approaches fail because they lack domain experti...
Per the changelog, Anthropic shipped a Trusted Devices control letting Team/Enterprise admins require device verification before a member can view or steer local Claude Code sessions remotely. v2.1.195 adds CLAUDE_CODE_DISABLE_MOUSE_CLICKS, which kills fullscreen click/drag/ho...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.