Claude Code Week 28: built-in browser, /doctor checkup, and safer worktree flows
Anthropic’s Claude Code adds a sandboxed built-in browser on desktop, upgrades /doctor into a fix-it checkup, and ships workflow/safety improvements.
Editorial Team
The Authority AI Tools editorial team maintains this directory using vendor documentation, dated source checks, product changelogs, and clearly identified hands-on observations where available.
Anthropic’s Claude Code “What’s new” for Week 28 (July 6–10, 2026) highlights a built-in desktop browser and several workflow improvements that matter for agentic coding sessions.
Anthropic's terminal-based AI coding agent with Claude Opus 4.7, /ultrareview, Routines, /ultraplan, and 80.9% SWE-bench
Built-in browser in Claude Code desktop
Claude Code on desktop now includes a built-in browser that can open and interact with external sites. Anthropic notes the browser is sandboxed/configurable, users can choose whether sessions persist, and actions are reviewed by safety classifiers.
/doctor becomes a setup checkup (and can fix issues)
Anthropic says /doctor is now a full setup checkup (with /checkup as an alias). The new flow can diagnose issues and propose fixes, including identifying unused skills/plugins/MCP servers, deduplicating local CLAUDE.md files, flagging slow hooks, and asking for confirmation before applying changes.
Other workflow improvements
Week 28 also includes several smaller but practical changes:
/cdnow suggests directory paths as you type/commit-push-prauto-allowsgit pushto the configured push remote (not justorigin)/loginsupports Anthropic-operated public gateway endpoints- Entering a git worktree outside
.claude/worktrees/now prompts for confirmation
Source
- Claude Code Docs — “Week 28 · July 6–10, 2026”: https://code.claude.com/docs/en/whats-new/2026-w28
Tools Mentioned in This Article
Free Resource
2026 AI Coding Tools Comparison Chart
Side-by-side comparison of features, pricing, and capabilities for every major AI coding tool.
No spam, unsubscribe anytime.
Workflow Resources
Cookbook
AI-Powered Code Review & Quality
Automate code review and enforce quality standards using AI-powered tools and agentic workflows.
Cookbook
Building AI-Powered Applications
Build applications powered by LLMs, RAG, and AI agents using Claude Code, Cursor, and modern AI frameworks.
Cookbook
Building APIs & Backends with AI Agents
Design and build robust APIs and backend services with AI coding agents, from REST to GraphQL.
Cookbook
Debugging with AI Agents
Systematically debug complex issues using AI coding agents with structured workflows and MCP integrations.
MCP Server
AWS MCP Server
Interact with AWS services including S3, Lambda, CloudWatch, and ECS from your AI coding assistant.
MCP Server
Context7 MCP Server
Fetch up-to-date library documentation and code examples directly into your AI coding assistant.
MCP Server
Docker MCP Server
Manage Docker containers, images, and builds directly from your AI coding assistant.
MCP Server
Figma MCP Server
Access Figma designs, extract design tokens, and generate code from your design files.
Frequently Asked Questions
What is Claude Code Week 28: built-in browser, /doctor checkup, and safer worktree flows?
Related Articles
Warp 2026.07.16 adds a cloud-agent connection indicator and more Agent Mode polish
Warp’s July 16, 2026 update adds a connection indicator for cloud agent sessions plus several Agent Mode and UI improvements.
Read more →Product UpdatesChatGPT (July 2026): global search across chats/projects/files + 5,000-character custom instructions
OpenAI’s mid-July 2026 release notes add global search across chats, projects, images, and documents, and expand custom instructions to 5,000 characters for paid plans.
Read more →Product UpdatesGoogle Antigravity CLI 1.1 adds code search, execution modes, and stronger diff review
Google’s Antigravity CLI changelog highlights new execution modes, line-level diff review, agent selection at launch, and a new /codesearch command, plus performance and reliability fixes.
Read more →