> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tyba.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Subagents

> Watch a Claude Code session's subagent tree unfold live.

When Claude Code hands work off to a subagent, its TUI shows a spinner and nothing else — something is running, but not what. TYBA opens that up: the **Agents** panel lists every subagent the moment it starts, and a split shows the transcript of whoever is working, live.

## The Agents panel

It opens on its own the moment the session's **first subagent** starts — as long as the session is in the active workspace. Missed that, or closed it since? The **Agents** button in an agent session's toolbar opens it by hand.

The **orchestrator** — the session itself — sits at the root of the tree. Under it, each subagent shows:

| Field    | What it shows                          |
| -------- | -------------------------------------- |
| Type     | Which subagent it is                   |
| Task     | What it was asked to do                |
| Status   | **Running** (pulsing) or **done**      |
| Duration | How long it has been running — or took |
| Summary  | Only once it's done: what it did       |

Clicking a subagent focuses its transcript in the split — reopening the split too, if you had closed it.

## The transcript split

<Steps>
  <Step title="Opens on the first subagent">
    The session pane splits: the terminal on one side, the transcript viewer on the other.
  </Step>

  <Step title="Streams the work live">
    The subagent's own text, every tool it calls — one compact line, with the tool's name and target — and each call's result.
  </Step>

  <Step title="Scroll follows the tail">
    Like `tail -f`: new output pushes the view down. Scroll up to read something that passed, and it stops following — until you're back at the bottom, where auto-scroll picks up again on its own.
  </Step>

  <Step title="The summary gets highlighted on completion">
    When the subagent finishes, what it did shows up highlighted right in the transcript.
  </Step>
</Steps>

Closing the split — or closing the Agents panel — disarms that automatic behavior **for that session**: TYBA won't reopen anything on its own after that. Getting back is the same path as always: the **Agents** button in the toolbar, then a click on a subagent in the list.

<Note>
  **Firing off a subagent doesn't ask for approval.** What it does afterward is what counts: every command the subagent runs goes through the same approvals inbox as the session, with the same [risk classification](/en/security/risk-classification) — green passes on its own, yellow and red wait for you.
</Note>

<Note>
  **Subagents exist in Claude Code sessions.** Codex sessions don't spawn subagents — the Agents panel stays empty in them.
</Note>

## See also

<CardGroup cols={2}>
  <Card title="Claude Code and Codex" icon="robot" href="/en/agent/claude-code-and-codex">
    Where an agent session is born.
  </Card>

  <Card title="Risk classification" icon="shield" href="/en/security/risk-classification">
    What lands in each inbox color.
  </Card>
</CardGroup>