claude-do-not-stop
Enable continuous work mode. Use PROACTIVELY when user says "keep working", "don't stop", "finish everything", "complete all tasks". Automatically continues until work is complete. User can invoke with /claude-do-not-stop [reason].
When & Why to Use This Skill
This Claude skill enables a continuous work mode, allowing the agent to persist through complex, multi-step tasks without manual intervention. By automating the 'resume' process, it ensures that long-running operations in coding, research, or data processing are completed autonomously. This orchestration tool is essential for maximizing agent productivity and ensuring task completion in autonomous workflows.
Use Cases
- Case 1: Executing large-scale code refactoring where the agent needs to modify dozens of files sequentially without stopping for user confirmation between each step.
- Case 2: Performing deep-dive web research or data extraction tasks that require multiple iterations and navigation through various sources to reach a final conclusion.
- Case 3: Managing complex DevOps or CI/CD debugging sessions where the agent must monitor logs, apply fixes, and re-test until the environment is stable.
- Case 4: Handling 'set-and-forget' background tasks where the user provides a high-level goal and expects the agent to work through all sub-tasks independently.
| name | claude-do-not-stop |
|---|---|
| description | Enable continuous work mode. Use PROACTIVELY when user says "keep working", "don't stop", "finish everything", "complete all tasks". Automatically continues until work is complete. User can invoke with /claude-do-not-stop [reason]. |
| allowed-tools | Bash, Read |
Enable Stop Hook Automation
Enabled by default in BitBot.
.claude/skills/claude-do-not-stop/scripts/do-not-stop.sh [reason]
Or user invokes: /claude-do-not-stop [reason]
Default: "Resume work!"