Launch presets

A launch preset is the set of arguments Coldtea passes to an agent CLI when you start a pane. You set them once per agent under Settings, then Agents, and Coldtea reuses them for every new pane of that agent.

Each agent has its own row, marked with whether Coldtea found the CLI (see Connect agents). Drag the rows to reorder them; the order sets the quick-launch shortcut each agent gets.

Autonomy

Autonomy controls how much the agent does without asking. The options differ per agent because each CLI has its own permission model, and Coldtea maps each preset onto that CLI's own flags.

Claude:

• Supervised: asks before edits and commands.
• Plan: read-only, proposes a plan without making changes.
• Auto-edit: applies edits without asking, still prompts for other actions.
• Locked-down: never prompts, for trusted scripted runs.
• Full autonomy: skips all permission checks. Marked as dangerous.

Codex:

• Supervised: workspace-write sandbox, asks on request.
• Plan / read-only: read-only sandbox, only trusted commands run unprompted.
• Locked-down: read-only, never asks, for trusted scripted runs.
• Full access: skips approvals. Marked as dangerous.

Gemini:

• Supervised: prompts for approval.
• Plan: read-only mode.
• Auto-edit: auto-approves edit tools.
• Full autonomy: auto-approves all tools. Marked as dangerous.

OpenCode:

• Supervised: runs OpenCode's native interface, where OpenCode owns setup, model switching, and permission prompts.
• Plan: asks before edits, using OpenCode's built-in plan agent.

OpenCode has no full-autonomy preset. Its unattended-run flag is not available on every OpenCode version, so Coldtea does not ship it as a preset; use OpenCode's own permission config for that.

Each preset describes itself under the row, so you can see what it does before you launch.

Model and reasoning effort

Model sets which model the agent launches with. Leave it empty to use the agent's own default. OpenCode expects a provider/model value here.

Reasoning effort appears for the agents that support it, Claude and Codex. Leave it on the default to inherit the CLI's own setting. Gemini and OpenCode have no reasoning-effort control.

Advanced arguments

The advanced field holds launch arguments Coldtea does not offer as a control. Anything you put there is kept: when Coldtea reads your saved arguments back into the controls, whatever it does not recognize stays in the advanced field rather than being dropped. Each row links to that CLI's own argument reference.

Coldtea preserves the CLI's last-wins behavior, so a duplicate flag you add by hand lands after the preset's flags and still takes effect.

Agent behavior and custom prompts

Two more groups on the same screen shape how agents work, separate from launch arguments.

Auto pane labeling lets agents name their own panes. You can still rename a pane by hand at any time.

Custom prompts add standing instructions for specific workflows. The task prompt is a message Coldtea gives agents whenever they work on a Coldtea task, so you can set house rules once, such as summarize the task first and log progress at each milestone, instead of repeating them in every session.

Where to go next

• Connect agents if an agent shows as not installed here.
• Cloud agent credentials for the cloud-run equivalent, launch defaults.
• Agent matrix for what each agent supports.