Weekly digest
The item that matters most for Claude Code users: the Embrace The Red blog claims Opus 5's auto-mode protections against prompt injection can be bypassed. Auto mode has been the default in Claude Code since August 14. In earlier testing, the auto-mode classifier let Claude Code download and run code from an external server in 6 of 10 runs.
The other item that affects your budget is the temporary 50% bump to weekly limits, which ends September 13. A permanent 25% increase replaces it on September 14. Testing Catalog puts that at roughly a 17% net drop from what subscribers have now.
/Embrace The Red claims a break of Opus 5 auto mode
A new write-up on the Embrace The Red blog, "Breaking Claude Code Opus 5 Auto Mode", claims Opus 5's auto-mode protections against prompt injection can be bypassed. Earlier auto-mode testing had Claude Code downloading and running code from an external server in 6 of 10 runs, with the auto-mode classifier waving it through. Auto mode has been the default in Claude Code since August 14.
Per TestingCatalog, Anthropic is working on a way to open a Claude Code session in Claude Desktop without selecting a folder first. The same functionality showed up in today's iOS build, still hidden, and Anthropic hasn't announced a rollout. Requests for it ran through GitHub issues dating back to at least April 2026, closed as of July 2026.
Tobi Lutke says he's thinking about banning Claude Code at Shopify until it reads AGENTS.md and .agents/skills, in a post that hasn't been independently verified. Insisting on only reading CLAUDE.md "sometimes leads to split brain problems when different team members use different tools," he wrote.
The temporary 50% bump to weekly limits runs out September 13, replaced the next day by a permanent 25% increase over the standard cap. Testing Catalog puts the net drop at roughly 17% against what subscribers have right now.
Anthropic posted the change from its Bluesky account, covering Pro, Max, Team, and seat-based Enterprise plans. The 50% boost had been extended through August 31, with Anthropic saying at the time that it hoped to make an increase permanent.
Admins on Claude Team and Enterprise can centralize MCP connector authorization through their identity provider, and users get tools and data connected automatically without individual OAuth. Anthropic's ClaudeDevs account announced the general availability on X.
Support covers Asana, Atlassian, Canva, Datadog, Figma, Granola, Linear, Notion, Slack and Supabase. Developers can also add enterprise-managed auth to their own third-party MCP connectors in the Claude directory, with the setup written up in Anthropic's connectors docs.
, "promo": "..."}
Anthropic put a browser inside Claude's desktop app, so a task that involves a website gets finished without you switching apps. The browser opens in Cowork's side panel, where Claude navigates, fills forms, and completes the job. There's nothing to install, and it stays separate from your own browser and your logins.
The rollout runs over the next week on the desktop app for all paid plans. For anyone who'd rather work in a browser where they're already signed in, Claude in Chrome is generally available on all paid plans and stays the default for existing users.
TestingCatalog and AI News Live report that Anthropic has begun small-scale testing of a successor believed to be Fable 5.1, with some users routed to it while Fable 5 remains selected. Some users have also noticed updated knowledge cutoffs for Fable 5, pointing to a stealth rollout.
Per the author's write-up, an agent harness built with Strands took Claude Opus 5 to 99.95% on ARC-AGI-3, against 30% for the model on its own, and that Strands figure isn't corroborated in indexed sources. The 30% baseline holds up, and NVIDIA reports 100% for Claude Opus 5 wrapped in its own AVO harness.
