ClaudeDevs
@ClaudeDevs
Official updates for developers building with @ClaudeAI
2 Following 648K Followers
New in Claude Code: your sessions can now message each other.
Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.
Show more
Starting August 14, auto mode will be the default permission mode in Claude Code for Pro, Max, and Team users.
Auto mode reviews shell commands and actions with a separate classifier. In testing, it caught 89% of dangerous commands. Manual approval caught 14%.
Show more
We've made progress restoring capacity and things are stable right now, but we're not fully in the clear yet. If anything comes up, we'll post it on
Two incidents over the last 24 hours resulted in elevated errors or reduced availability on Claude for some users. Multiple separate network failures cut into our capacity to serve Claude, and some requests failed while we rerouted traffic.
Show more
MCP 2026-07-28 is live and it's the largest update to the protocol since launch.
MCP is now stateless, making it easier to deploy and scale remote servers.
We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them.
Try Opus 5 today. Use “claude-opus-5” on the Claude API, or run “/model claude-opus-5” in Claude Code.
To upgrade existing workloads to Opus 5, run `/claude-api migrate` in Claude Code.
The built-in claude-api skill updates your model strings and suggests prompt improvements that are tuned for Opus 5.
On the Chartography benchmark (100 questions over dense real-world charts), Fable 5's accuracy goes from 29% to 73% with a zoom tool, and Sonnet 5’s from 13% to 44%.
See the cookbook to learn more:
Show more
We've updated our "zoom tool" cookbook.
When large images get downscaled, important detail can be lost. A zoom tool lets Claude request a region and get that crop back from the full-res original.
Show more
Claude can see the app as it runs, interact with it, and iterate until finished. Tap through the simulator yourself at any time.
Available in Claude Code on desktop (macOS only, requires Xcode).
Claude Code on desktop now works with the iOS simulator.
Build and run your iOS app, and the simulator opens in a panel right next to your conversation. Available today in public beta.
Show more
Claude Code now has a screen reader mode.
Running `claude --ax-screen-reader` swaps the visual terminal UI for plain, linear text that screen readers (like VoiceOver and NVDA) can follow.
For the small teams with big plans: Claude Team plans now start at just 2 seats instead of 5.
Get shared projects, admin controls, centralized billing, SSO, and enterprise search across all your team's tools, all under one plan.
Show more
if you've run into this, please restart Claude Code, fix should be propogating
We're also keeping Claude Code weekly limits 50% higher, now through August 19, for all Pro, Max, Team, and seat-based Enterprise users.
Beginning July 20, Claude Fable 5 will be included in all Max and Team Premium plans, at 50% of limits.
Pro and Team Standard users will continue to have access to Fable via usage credits, and will receive a one-time $100 credit.
Demand for Fable has been challenging to predict, which is why we rolled it out to subscription plans in stages, extending access several times as we secured additional capacity.
Show more
We've resolved an issue where Fable was not selectable as a model within or Claude Code for a 30 minute period.
You may need to restart Claude Code. If Fable is not your default model afterwards, you should reselect it with /model.
Show more
We've reset 5-hour and weekly rate limits for all users.
Build an artifact once, then it pulls live data via MCP. Artifacts use the viewers’ own MCP connectors, so creators don’t need to re-run sessions to refresh, and viewers can only see the data they have access to.
Show more
