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

# Agent-to-Agent

> Understand how Traycer agents delegate work, create child agents, and coordinate inside a Task.

Agent-to-agent communication lets Traycer agents coordinate with each other inside the same Task.

Use it when running agents need to split work, ask another agent to investigate something, get a review, or share results without losing the larger Task context.

## What It Does

An agent can:

* create a child agent
* send another agent instructions
* ask for a reply or send a fire-and-forget message
* read another agent's transcript
* coordinate from the originating chat or agent session

The result is still visible in the Task. Child chats and child terminal agents appear in the [Chats](/panels/chats) tree under the agent that created them, so the lineage is not hidden.

```text theme={null}
Chat: plan the implementation
├─ Chat: review the database changes
├─ Terminal Agent: inspect failing tests
│  └─ Chat: summarize the failure cause
├─ Chat: update the docs plan
└─ Terminal Agent: verify the final changes
```

The tree shows where each session came from. It does not mean agents can only talk to their parent.

```mermaid theme={null}
---
title: Any agent can talk to any other agent
---
flowchart TD
  A[Agent 1]
  B[Sub-agent 1]
  C[Sub-agent 2]
  D[Agent 2]
  E[Sub-agent 3]
  F[Sub-agent 4]

  A --> B
  A --> C
  B --> A
  C --> A

  D --> E
  D --> F
  E --> D
  F --> D

  B --> E
  C --> F
  E --> C
```

## Lineage And Sessions

The agent that starts another agent is the **parent**. The new agent is the **child**.

The child agent has its own session, model, mode, transcript, and run state. It does not merge into the parent chat. The parent can read the result, continue the conversation, or use the child agent's work as context for the next step.

This is why agent-to-agent work shows up as hierarchy in Chats instead of as one flat transcript. Communication can still happen between multiple visible agent sessions when the selected agent paths support it.

## Agent Selection

Traycer uses agent-selection instructions to choose the right child agent for delegated work. Configure those defaults in [Settings > Agents](/settings/agents).

## Agent-To-Agent Support

| Coding agent    | Chat      | Terminal Agent |
| --------------- | --------- | -------------- |
| **Claude Code** | Supported | Supported      |
| **Codex**       | Supported | Not supported  |
| **OpenCode**    | Supported | Not supported  |
| **Cursor**      | Supported | Not supported  |
| **Traycer**     | Supported | Not supported  |

Terminal-agent support is narrower than chat support today. Codex and OpenCode Terminal Agents can run terminal-style work, but they do not receive agent-to-agent messages.

Plain [Terminals](/panels/terminals) do not participate. They are shell sessions, not agent sessions.

For the broader distinction, see [Terminal Agents VS Terminals](/concepts/terminal-agents-vs-terminals).

## Related Pages

* [Chats](/panels/chats) explains where parent and child agent sessions appear.
* [Agents & Models](/agents-and-models/coding-agents) lists supported coding-agent paths.
* [Settings > Agents](/settings/agents) explains global and workspace-specific agent-selection instructions.