Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v1.0.70 Home All releases olderv1.0.69 v1.0.71newer
Claude Code v1.0.70

Enhanced Security Model

  • Explicit permission dialogs for MCP servers and hooks
  • Trust management for code execution permissions
  • API key validation with user confirmation for custom ANTHROPIC_API_KEY usage
  • Clear security notes displayed during onboarding about Claude's file system access

See this entry in the whole of v1.0.70 →