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].

⭐5stars🔀1forks📁View on GitHub🕐Updated Jan 11, 2026⬇️1downloads

When & Why to Use This Skill

The 'claude-do-not-stop' skill enables a continuous execution mode for Claude agents, allowing them to autonomously complete complex, multi-step workflows without requiring constant user intervention. By automating the 'resume' process, it ensures that long-running tasks—such as large-scale coding projects or deep research—proceed uninterrupted until the final objective is achieved, significantly boosting productivity and agent autonomy.

Use Cases

  • Large-Scale Code Refactoring: Automatically navigate and modify multiple files in a repository without the user needing to manually prompt 'keep going' after every step.
  • Autonomous Multi-Step Research: Execute comprehensive web research or data synthesis tasks that require sequential tool use and long-duration processing.
  • Unattended Task Completion: Ideal for developers and power users who want to assign a complex goal and let the agent work through the entire execution loop until the task is verified as finished.
  • Workflow Automation: Streamline repetitive operations where the agent might otherwise pause for confirmation, ensuring a seamless 'hands-off' experience.
nameclaude-do-not-stop
descriptionEnable 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-toolsBash, 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!"