claude-allow-stop
Return to normal stop behavior. Use PROACTIVELY after completing all tasks in continuous work mode, when work is committed and tests pass, or when reaching natural stopping point. User can invoke with /claude-allow-stop.
When & Why to Use This Skill
The claude-allow-stop skill is a workflow management utility designed to transition Claude from continuous autonomous mode back to standard interaction behavior. It allows the agent to proactively signal task completion—such as after successful code commits or test passes—ensuring efficient execution cycles and preventing unnecessary resource consumption by stopping at natural breakpoints.
Use Cases
- Continuous Development Loops: Automatically halting the agent's autonomous work cycle once a coding task is completed, committed, and all unit tests have passed.
- Resource & Token Management: Preventing redundant execution and token usage by allowing the agent to exit 'continuous mode' immediately upon reaching a logical conclusion of its assigned task.
- Manual Session Control: Providing users with a specific command (/claude-allow-stop) to override persistent automation states and regain manual control over the agent's step-by-step behavior.
| name | claude-allow-stop |
|---|---|
| description | Return to normal stop behavior. Use PROACTIVELY after completing all tasks in continuous work mode, when work is committed and tests pass, or when reaching natural stopping point. User can invoke with /claude-allow-stop. |
| allowed-tools | Bash, Read |
Disable Stop Hook Automation
Allow normal completion and wait for user input.
.claude/skills/claude-allow-stop/scripts/allow-stop.sh
Or user invokes: /claude-allow-stop
Re-enable with /claude-do-not-stop [reason]