Skip to main content

Security, Permissions & Production Use

Permission System Deep Dive

0:00
LearnStep 1/3

The Capability Model

Security by Design

Claude Code operates on a capability-based security model. Unlike traditional CLI tools, Claude must be explicitly granted capabilities to interact with your environment.

Tool-Level Authorization

Every potentially dangerous action requires permission:

  • One-time: Approve a single specific call
  • Session: Approve all calls for that tool until exit
  • Persistent: Save to config for future sessions

Security Tip

Use --allow-read when starting Claude to limit its vision to only the current directory, preventing access to sensitive files in your home folder.