Skip to main content
Traycer has two terminal-looking surfaces with very different roles. One is an agent session; the other is a shell. They can look similar because both use a terminal surface. The difference is that Terminal Agents are still Traycer agent sessions, while Terminals are just shells.

​
Terminal Agents

A Terminal Agent runs a coding agent in a PTY, but Traycer still wraps that session with Task context. Terminal Agents can receive:
  • Traycer’s system prompt for Regular Mode or Epic Mode
  • the Task id and agent identity
  • artifact instructions for specs, tickets, stories, and reviews
  • guidance for creating or updating artifacts as markdown files
  • Traycer skills and planning/execution instructions
  • agent-to-agent communication instructions when that agent path supports them
That means a Terminal Agent is not the same as opening the coding-agent CLI yourself. Traycer prepares the session so the agent understands the Task, the artifact model, and the multi-agent environment.

​
Supported Terminal Agent Paths

Terminal Agents currently support: For the full chat and terminal compatibility matrix, see Agents & Models.

​
Plain Terminals

A Terminal is a shell session. Use it to run commands yourself: package scripts, tests, dev servers, logs, local debugging, or one-off shell work. A plain Terminal does not receive Traycer’s agent prompt, does not use Traycer skills, does not create artifacts by itself, and does not participate in agent-to-agent communication. It is still part of the Task, but it is not an agent session.

​
Launch Setup

When you create a Terminal Agent, you choose its launch setup:
  • workspace folder or worktree
  • coding agent
  • model, when supported
  • Regular Mode or Epic Mode
  • thinking effort, when supported
  • terminal-agent CLI arguments, when supplied
Those choices stay fixed after launch. Start a new Terminal Agent when you need a different mode, model, workspace folder, worktree, or argument set. Worktree choices are covered in Worktrees. Traycer also keeps the upstream coding-agent session id for the Terminal Agent. When the app or Host restarts and the same Terminal Agent is reopened on its original Host, Traycer resumes the underlying coding-agent session instead of starting from scratch. Plain Terminals do not have agent mode, model, thinking effort, or artifact behavior. They only need the shell/workspace context used to start the terminal.

​
Agent-To-Agent Communication

Claude Code Terminal Agents can participate in Traycer’s agent-to-agent system today. Codex and OpenCode Terminal Agents can run terminal-style work, but they do not receive agent-to-agent messages. When a Terminal Agent participates, it still appears in the Task’s chat hierarchy so you can see where delegated terminal work came from. The coordination model is covered in Agent-to-Agent. Multi-agent defaults are configured in Settings > Agents. Supported agent paths are listed in Agents & Models. If you are looking for a terminal-style coding agent, use Chats. If you are looking for a shell you operate yourself, use Terminals.