Claude Sdk Permissions

The Claude Agent SDK permission model — allowed_tools, disallowed_tools, the six permission_mode values, and the can_use_tool callback. Read when designing what an agent is allowed to do, when production deploys are surprising users with permission prompts, when you want dynamic per-call gating, or when locking down a deploy that runs unattended.

Folken2 Updated 2 repo stars
nuvel — production-ready agents, your way

File contents

Folken2/nuvel commit e18125ee75

Frequently asked questions

npx get-skill add folken2/claude-sdk-permissions