Workflow Orchestration

When a Claude agent runs a Workflow — a script that spawns and coordinates many subagents across named phases — Agent Chat surfaces it as a first-class run instead of a raw tool-use block. You get an in-thread approval card, a live progress card, and a dedicated Orchestration panel where you can drill into each phase and each subagent.

This is a Claude-only feature. Codex and OpenCode don't emit workflow runs, and the /workflow command is visible-but-disabled ("Only available with Claude models") for those providers.

Beta: Workflow Orchestration is part of Agent Chat (Beta). Enable it in Settings → Beta Features → Enable Agent Chat.

Starting a Workflow

Type /workflow in the composer (it's in both the / command menu and the + menu, under Workflows) and describe the task you want orchestrated — for example "review this diff across correctness, security, and performance." Selecting the command just inserts /workflow into your draft; you write the rest and send it like any other message.

Claude decides whether the task warrants a Workflow and, if so, writes and runs the orchestration script itself. You don't author the script — you describe the goal.

The Approval Card

Because a Workflow can spawn dozens of subagents and use a lot of tokens, it asks for approval before running. The approval card shows:

• Planned phases — the named stages the Workflow will run (e.g. Find → Verify → Synthesize).
• A token-use caution — a reminder that orchestration fans out across many agents.
• Run once — approve this single run.
• Always for this project — persist a permission rule so future Workflow runs in this project skip the prompt (written to the project's .claude/settings.local.json).
• View script — inspect the exact orchestration script before you approve.
• Deny — reject the run.

Live Progress

Once approved, the card becomes a compact progress line — "phase 2 of 4," a running-agent count, and a progress bar. Click it (or the status pill in the title bar) to open the Orchestration panel.

When the run finishes it collapses to a summary row (completed / failed / stopped) that you can still click to reopen the panel, plus the agent's own written report in the transcript.

The Orchestration Panel

The Orchestration panel is a right-side panel that appears only while a workspace has an active or recent Workflow run (it's the first panel tab Codemux shows conditionally). It gives you the full picture:

• Run header — name, status, and live ticking stats (agents, tokens, elapsed).
• Phase cards — one per phase, each expandable, with per-phase agent / token / elapsed rollups and status-filter chips (all / running / issues).
• Agent rows — every subagent in a phase, with a finding badge when it reports structured findings or issues.
• Agent drill-in — click a subagent to see its prompt, recent tool calls, and result. When its activity points at a file, an Open action jumps you straight to it in the editor. Press Esc to back out.

Stopping a Run

The panel has a Stop button that interrupts the run. Stop currently interrupts the whole turn rather than the workflow alone.

Current Limitations

• Claude only. Codex and OpenCode never produce workflow runs; the progress pill and Orchestration panel never appear for them.
• Pause isn't supported yet — the panel's Pause button is present but disabled.
• Per-agent Restart is a stub in the drill-in.
• Stop interrupts the whole turn, not just the workflow — there's no "stop this workflow only" control yet.
• Phase and token attribution are approximate. Subagents are attributed to the running workflow heuristically, and token / agent totals are rolled up from multiple sources rather than one authoritative counter.
• Long results are truncated before they reach the panel.

Related

• Agent Chat — the chat pane that hosts workflow runs, including the Subagents card the panel builds on
• Settings — Beta Features and per-project Permissions
• OpenFlow — the older, separate multi-agent orchestration surface