Claude Code in Orca
Claude Code is Anthropic's agentic CLI. Orca runs it as a first-class terminal agent, with account-aware session start, usage tracking, and account hot-swapping.
Setup
- Install Claude Code (
npm i -g @anthropic-ai/claude-codeor follow Anthropic's docs). - Log in once from any terminal.
- Orca picks up
~/.claudeautomatically — no extra config needed.
Launching
In any worktree, open a terminal and pick Claude Code from the agent combobox. Orca launches it with the worktree as the working directory and a status-line hook that emits OSC title events Orca uses for state dots.
Usage & rate limits
Orca reads your local ~/.claude usage state and shows current usage plus rate-limit proximity in the status bar. See Usage & rate-limit tracking.
Account hot-swap
Orca supports multiple Claude accounts and can swap between them in one click, matching the Codex flow. Switching accounts works even with live Claude sessions running — Orca holds the in-progress switch behind a guard so you don't trigger overlapping auth refreshes. A swap keeps your shared MCP server sign-ins, so you don't have to re-authenticate MCP servers after switching. See Hot-swap Codex accounts — the Claude flow is identical in shape.
Subagents and teams
Background subagents and Agent Teams teammates can show as expandable child rows under the lead agent in the worktree agent list and Agent Dashboard. Select a child to view its transcript in the lead terminal, then select the parent to return; an eye marks the transcript currently shown. This navigation is on by default when Claude status hooks are available. Turn it off under Settings → Agents → Claude subagent navigation if you prefer the lead terminal to stay in view. Start a fresh Claude session after changing this setting.
Hooks & memory
Claude Code supports per-repo hooks and memory files. Orca surfaces these under Agent hooks & memory.