nonstop - Autonomous Work Mode for Continuous Execution
Enables continuous autonomous operation with pre-flight risk assessment, dangerous ops approval, and a blocker decision framework.
Tags
Updated: 2026-09-19Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Activate nonstop autonomous mode
- Perform pre-flight risk assessment
- Generate dangerous operations manifest
- Verify user permission mode
- Execute blocker decision framework
- Deactivate nonstop autonomous mode
Inputs
- Activation command
- Task instructions
- User confirmation and operation scope
- Permission mode status
Outputs
- Pre-flight risk assessment plan
- Dangerous operations manifest
- State file nonstop.activate
- State file nonstop.deactivate
- Execution summary report
Requirements
- Claude agent environment with hooks support
- File write access to ~/.claude/hooks/state/
- NONSTOP_MAX environment variable support