Claude Code adds /goal to run until tasks are complete

Claude Code 2.1.139 reportedly introduces /goal, a command that keeps working across turns until a stop condition is met. Early reactions praise the hands-off workflow, but raise concerns about reliability and usage caps.

•
Claude
Claude Code adds /goal to run until tasks are complete

TL;DR

  • Claude Code 2.1.139: Added /goal command, per Daniel San’s X post
  • /goal behavior: Keeps working across turns until a completion condition is met
  • Supported modes: Works in interactive, -p, and Remote Control
  • Stop/continue modes: /goal outcome-based; /loop clock-based; stop hooks script-based; normal chat manual follow-up
  • Template command: npx claude-code-templates@latest --setting statusline/vercel-deployment-monitor for Vercel deployment monitor status line
  • Community feedback: Interest in multi-step handoff; concerns about reliability, stale context, vague stop conditions, and usage/token caps

According to a post on X, Claude Code 2.1.139 has added /goal.

The command appears to let Claude keep working across turns until a completion condition is met, and the post claims it works in interactive mode, -p, and Remote Control.

The post also outlines how Claude Code determines when to continue and when to stop. These modes are now listed as:

  • /goal waiting for an outcome
  • /loop waiting for the clock
  • stop hooks waiting for a script

/goal was also added last week on Codex, where it drew positive feedback from the community, along with a practical path from repeated turn-by-turn prompting to a single declared exit condition. One reply described the appeal as finishing work without constant intervention, though the same thread repeatedly returned to the practical constraint of token and usage limits.

Source: X post

Continue the conversation on Slack

Did this article spark your interest? Join our community of experts and enthusiasts to dive deeper, ask questions, and share your ideas.

Join our community

Related Articles

claude cover

Anthropic boosts Claude Code weekly limits 50% through July 13

Anthropic has just rolled out a temporary 50% increase to Claude Code weekly limits for Pro, Max, Team, and seat-based Enterprise users. The bump applies across CLI, IDE extensions, desktop, and the web, stacking with last week’s 2x 5-hour limit boost.

1 shared tag
claude cover

Claude Opus 4.7 gets Fast Mode in API and Claude Code

Anthropic has just rolled out Fast Mode for Claude Opus 4.7 in research preview on its API and in Claude Code. It’s opt-in now for Claude Code users and becomes the default Thursday, with previews also live in tools like Cursor and Warp.

1 shared tag
claude cover

Claude Code adds agent view to manage parallel sessions

Claude has just rolled out agent view for Claude Code, a CLI dashboard for tracking all your sessions in one place. It shows what’s waiting on you, what’s still running in the background, and what’s finished. Available now as a Research Preview.

1 shared tag