DEV Community

gentic news
gentic news

Posted on • Originally published at gentic.news

Claude Code v2.1.139: Agent View and /goal Command Ship

Claude Code v2.1.139 adds agent view dashboard and /goal command for autonomous multi-turn work. Background sessions consume quota 10x faster, limiting parallel use.

Anthropic shipped Claude Code v2.1.139 with agent view and the /goal command. The release turns the single-session terminal tool into a multi-agent operations layer.

Key facts

  • v2.1.139 released with agent view and /goal command.
  • Agent view shows all sessions in a single dashboard.
  • 10 parallel sessions = 10x quota consumption.
  • /goal command enables autonomous multi-turn work.
  • Boris Cherny called it 'a shift to multi-agent workflows.'

Key Takeaways

  • Claude Code v2.1.139 adds agent view dashboard and /goal command for autonomous multi-turn work.
  • Background sessions consume quota 10x faster, limiting parallel use.

What agent view does

Agent view is a session roster. One screen. Every Claude Code session you have running, blocked, or finished, in a single list [According to Claude Code Agent View Just La]. Without it, running multiple sessions means multiple terminal tabs or tmux panes. Thariq from the Claude Code team at Anthropic described it as "like tmux built for CC."

To open it: claude agents. From inside any session, press the left arrow to jump to agent view. Each row shows the session name or task, current state (working, waiting, done, failed, stopped), and last activity timestamp. Keyboard shortcuts: Spacebar peeks at the latest turn without attaching, Enter or right arrow attaches, Esc exits while sessions keep running.

From agent view, type a prompt and press Enter to start a new background session. From inside a session, run /bg to send it to the background. From the shell: claude --bg "write tests for the auth module".

The rate limit caveat

Background sessions draw down your subscription quota the same as interactive sessions. If you open agent view and run 5 sessions in parallel, you are using your Claude Pro or Max quota 5 times faster than normal. Ten sessions in parallel means 10x quota consumption [According to Claude Code Agent View Just La]. For an indie hacker on Claude Pro ($20/month) or Max ($100/month), this limits how aggressively you can parallelize. Test with 2-3 concurrent sessions first.

Cover image for Claude Code Agent View Just Launched: What It Does and How to Use It

Sessions are local — they run on your machine. If your laptop goes to sleep, all background sessions stop. For overnight tasks, run Claude Code on a Hetzner or Railway VPS over SSH.

The /goal command

Set a completion condition and Claude keeps working autonomously across turns until that condition is met or it gets stuck. Usage: /goal deploy the staging environment with passing tests. A live overlay panel shows elapsed time, turn count, and current token usage while Claude works [According to Claude Code Agent View Just La].

This is separate from agent view. You can use /goal in a single session without opening agent view at all. The combination is where it gets interesting: start a session with /goal, send it to the background with /bg, then monitor progress from agent view while you work on something else.

Who benefits most

Multiple feature branches at once — run a separate session for each branch, monitor from agent view, peek when one needs input. Parallelising independent tasks works well; tasks that depend on each other do not. Agent view is a session manager, not an orchestrator. Claude Code does not yet automatically coordinate multiple sessions. For automated multi-agent coordination, that's in a separate product path (Claude Managed Agents, currently in beta).

What this release means

Boris Cherny from Anthropic called this "a shift to multi-agent workflows." That framing is right. Claude Code started as a single-session terminal tool. Agent view is the first step toward using it as a genuine agent operations layer where you run and monitor multiple parallel workstreams from one place [According to Claude Code Agent View Just La]. The research preview label means the interface will change — keyboard shortcuts, session display, and background session behaviour are all subject to revision based on feedback.

What to watch

Watch for the next Claude Code release that adds session orchestration — the gap between agent view (session manager) and Claude Managed Agents (multi-agent coordination) will narrow. Also watch for Anthropic's Q3 2026 pricing changes if parallel session usage strains infrastructure costs.


Originally published on gentic.news

Top comments (0)