What do the links at the top mean?

A link takes you to another page. The links at the top give you these choices:

  • Start here — follow the four short lessons from the beginning.
  • Everyday uses — find small, practical jobs you could try with AI.
  • AI tools — meet examples of outside AI apps and learn how to choose one.
  • Explore more — find news, detailed activities, and the separate children’s area.
Anthropic

Claude Code adds write limits.

Three editing tools are covered.

Sources checked 2026-10-30. Access and availability can change.

Named tools first

Claude Code v2.1.314 was released at 01:06:26 UTC on October 30, equivalent to 20:06:26 CDT on October 29. This is an earlier-release catch-up. Its notes add permissions.blockWritesOutsideWorkingDirectories: Write, Edit, and NotebookEdit refuse paths outside working directories in every permission mode. They also report fixes for policy refresh after cache expiry and resumed-worktree sandbox protections. [1]

Anthropic’s permissions guide distinguishes built-in file rules and recognized Bash paths from arbitrary subprocess writes. It describes operating-system sandboxing as complementary protection and documents MCP permission rules separately. Editing-tool settings alone should not be treated as evidence of complete process isolation. [2]

Our take

Check Bash, external tools, and operating-system policies separately. A setting for named editing tools does not establish a complete sandbox. We reviewed documentation without installing or testing this release.

Sources & further reading

Open the source to check the original wording and current availability.

This is a source-linked briefing, not a hands-on product review. Provider claims and outside evaluations are identified in the text.

Hey, I’m Patch.

Your little guide to this website.

Ask about an AI word or find your next small adventure.

New here? Try “Help me get started.”

Prepared explanations + site search. No live model. Your question stays in this browser. How Patch works.