Execution modes
DOCS / WORK WITH VIBES

Execution modes

Decide what the agent can do, and where it should stop for your input.

Four levels of control

ModeFile editsShell and delegationBest for
planRead-onlyRestricted by read-only policyExploration and proposing changes.
manualApproval requiredApproval requiredReviewing each change and command.
auto-editAllowed automaticallyApproval requiredMoving quickly through code changes.
autoAllowed automaticallyAllowed automaticallyTasks with clear scope and trusted execution.

Switch modes during a session

The UI and API can change the mode while a session is active. The agent also has a set_mode tool. The mode is a policy layer over the tool-approval gate, rather than a different agent implementation.

To set it in a streaming API request, include a mode field alongside the messages.

json
{
  "messages": [{ "role": "user", "content": "Explain this repository" }],
  "mode": "plan"
}

Planning and clarification

A plan can be offered for review before implementation. Vibes can also call ask_user with a structured questionnaire. That halts the run until your response arrives, keeping decisions in the conversation instead of guessing.

Understand the execution boundary

Structured file operations are contained within the workspace by the sandbox. Shell commands run real host binaries. A working directory is not an operating-system jail, so choose an execution mode appropriate to the repository and task.

Improve this page Grounded in the Vibes source.

Find a guide, command, or concept.