Skip to main content
Mythos

Commands, settings, and limits for running Claude Code work in parallel, for someone at the keyboard deciding how to split a task across subagents, sessions, teams, or a project.

Delegate inside one session

  • Delegate a side task — ask in plain words: "Use a subagent to …". It runs in its own context and returns a summary.
  • Use a built-in — Explore (read-only search), Plan (plan-mode research), general-purpose (multi-step work).
  • Fork with full context — /subtask <task> starts a subagent that inherits the whole conversation and prompt cache.
  • Define a specialist — Markdown file in .claude/agents/ (project) or ~/.claude/agents/ (all projects); only name and description are required.
  • Call a specialist — type @ and pick it, or run the whole session as it with claude --agent <name>.
  • Check running subagents — /tasks lists them with status and model; attach to or stop any one.
  • Turn fork mode off — CLAUDE_CODE_FORK_SUBAGENT=0 lets Claude wait on subagents in the foreground again.

Run sessions in the background

  • Open agent view — claude agents shows every background session and which ones need you.
  • Dispatch from a shell — claude --bg "<task>"; add --name <name> to label it.
  • Background the current session — /bg (alias /background); /fork copies the session into a new background session.
  • Peek, attach, detach — Space peeks, Enter attaches, ← on an empty prompt detaches. Detaching never stops a session.
  • Manage from a shell — claude attach <id>, claude logs <id>, claude stop <id>, claude agents --json.

Hand work to a coordinator

  • Start a project — claude.ai/code or the desktop Code tab → Projects → New project. Public beta, Pro and Max.
  • Set the brief once — Project settings › Memory › Project instructions, up to 16,000 characters, reaches every new thread.
  • Steer the coordinator — say "propose threads before starting" or "run at most two threads at a time" in the project conversation.
  • Run a thread locally — claude remote-control in the folder (v2.1.280+), then choose Work locally from the + menu.

Message between sessions

  • Name a session — /rename <name> or claude --name <name>; peers address it by that name.
  • See who's reachable — /list-agents (alias /peers); the first line is this session's own name.
  • Send a message — "Let @<name> know …". Claude writes it and delivers with SendMessage.
  • Wait for another session — "Tell me when <session> finishes" gets one notice when it next goes idle (v2.1.236+).
  • Control inbound — crossSessionInbound: accept, hold, or refuse; set it in /config under Messages from your other sessions.
  • Gate cross-machine sends — "isolatePeerMachines": true asks before any message leaves this machine.

Run an agent team

  • Enable teams — set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in env or settings env; off by default.
  • Spawn teammates — "Spawn three teammates: one on UX, one on architecture, one devil's advocate."
  • Split panes — "teammateMode": "auto" uses tmux or iTerm2 when available; default is in-process.

Scale with workflows

  • Ask for a workflow — say "use a workflow" or include ultracode in the prompt.
  • Research across sources — /deep-research <question> runs the bundled cross-checking workflow.
  • Watch or save a run — /workflows; p pauses, x stops, s saves the script as a slash command.

Gotchas

  • /fork changed meaning — with agent view on (v2.1.212+), /fork makes a new background session; the in-session fork is /subtask.
  • /agents is not claude agents — /agents points to subagent files; claude agents opens agent view.
  • Teams hijack named subagents — with agent teams enabled, a subagent Claude names launches as a teammate.
  • Teams share one checkout — teammates don't get worktrees; give each a different set of files.
  • Cloud threads skip repo config — project threads load CLAUDE.md but not repo skills, .mcp.json, hooks, or settings.json.
  • Coordinator limits are advice — thread caps told to a project's coordinator are preferences, not enforced limits.
  • Messages can't grant permission — a cross-session message never approves a prompt or changes another session's config.
  • Parallel work burns plan limits — every subagent, teammate, thread, and workflow agent spends its own tokens.

Contexts

Created with 💜 by One Inc | Copyright 2026