claude-sdk-permissions

SKILLWorkflowcommunity
v0.0.0Folken2MITUpdated 2mo agoSource →

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

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
2Repo stars
1Clients
1Formats
2mo agoLast update
Skill
AuthorFolken2
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

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.

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.