---
title: "How to Enable YOLO Mode in Nova | AgentRQ Guidelines"
url: https://agentrq.com/guidelines/yolo-mode/nova
description: "Nova's YOLO mode is unleash: nova --unleash, or /unleash on --force (alias /yolo). /approve auto is the halfway option. What each removes."
---

![](https://agentrq.com/assets/agent-icons/nova.svg) Checked October 30, 2026 | [All YOLO Mode guides](https://agentrq.com/guidelines/yolo-mode/)

# How to Enable YOLO Mode in Nova

Compass AI's Nova calls its YOLO mode **unleash**, or unguarded mode. Start Nova with `nova --unleash`, or type `/unleash on --force` in a running session. `/yolo` is an alias for `/unleash`. If you only want fewer prompts, `/approve auto` lets low-risk actions through and keeps asking about the rest.

This page is one of our [YOLO mode guides](https://agentrq.com/guidelines/yolo-mode/), and part of our guide to [YOLO mode in every coding agent](https://agentrq.com/blog/what-is-yolo-mode-and-how-to-turn-it-on-in-every-coding-agent). Nova is closed source, so everything below was checked against its README and changelog (Compass-Agentic-Platform/nova) and the help text and command definitions in the published npm package (@compass-ai/nova 1.1.62) on October 30, 2026.

![Animated sketch of YOLO mode in AgentRQ: claude waits to run go test, YOLO is flipped on for the task, and every later edit and test run lands auto-allowed in the Trajectory view](https://agentrq.com/assets/sketches/yolo-mode.svg)

## Nova's Approval Modes

Nova's README describes three approval modes, and the package adds unleash on top:

| Mode | What runs without asking |
| --- | --- |
| Manual (default) | nothing: every change is reviewed |
| Strict | nothing: every operation needs explicit approval |
| Auto | low-risk operations. Riskier ones still ask. |
| Unleash | everything, including destructive actions |

Nova's help text describes unleash as "removes safety guardrails", and Nova makes you confirm it: `/unleash on` needs `--force` (or `-f`). Nova calls it a transient setting, as opposed to one saved to your config.

We found no sandbox for the commands Nova runs on your machine. The nearest thing is `nova --worktree`, which runs the session in a separate git worktree so its changes stay off your main checkout. Nova also backs up files before it modifies them, and `/undo` rolls back the last change.

## How to Enable YOLO Mode in Nova

| Where | YOLO | Halfway |
| --- | --- | --- |
| Command line | `nova --unleash` |  |
| In a session | `/unleash on --force` (or `/yolo on -f`) | `/approve auto` |
| ACP server | `nova acp --unleash` | the default |

bash

```bash
nova --unleash
```

`/unleash off` turns it off again, and `/unleash status` shows where you are. `/approve` cycles through the approval modes, or takes one directly: `/approve auto`, `/approve manual`, `/approve strict`.

### The Halfway Option

`/approve auto` is the middle ground: low-risk operations run on their own and anything riskier stops for you. Nova decides what counts as low risk, so read what it asks about before relying on it. Nova's agent files can also list allowed and denied tools, which narrows what an agent can do at all.

## How to Enable YOLO Mode in Nova Through AgentRQ

Nova's own unleash switch covers a whole session. AgentRQ lets you make the decision per task, and answer from somewhere other than the terminal.

### Approve From the AgentRQ Task Instead of the Terminal

Connect Nova to an AgentRQ workspace through the [ACP Gateway](https://agentrq.com/docs/connect-acp-agent) ([Nova setup guide](https://agentrq.com/docs/agents/nova)). Log in once, then start the bridge:

bash

```bash
npx @agentrq/acp-gateway@latest --login --agent nova
npx @agentrq/acp-gateway@latest --agent nova
```

Leave `--unleash` off. Be aware that `nova acp` does not start in Manual mode: as far as we can tell from the package, its ACP sessions use Auto approval, so low-risk operations run without asking and only riskier ones become permission requests. Its ACP session modes, **Default**, **Code** and **Plan**, shape how the agent works rather than what it asks about.

Each permission request now shows up in the AgentRQ task on the web, on your phone or in Slack, together with what Nova wants to do. Answer **Allow Once**, **Always Allow** or **Deny** from wherever you are, and Nova carries on. If nobody answers within 30 minutes, the gateway cancels the turn instead of guessing. Change the limit with `--permission-timeout`.

### Turn On YOLO for One Task

Flip the **YOLO** toggle on a task, or when you create it, to put just that task in [YOLO mode](https://agentrq.com/features/yolo-mode). Every permission request in it is approved automatically and Nova never waits, while every other task in the workspace still asks. [Scheduled tasks](https://agentrq.com/features/task-scheduling), [event triggers](https://agentrq.com/features/events) and [workflow](https://agentrq.com/features/workflows) steps have the same switch, so an unattended job can run in YOLO while your interactive work stays supervised.

![The YOLO toggle on a task in AgentRQ being switched on, then off again](https://agentrq.com/assets/guidelines/yolo-mode-task-toggle.gif)

### Turn YOLO On or Off in Workspace Settings

To make YOLO the default for a whole workspace, open the workspace, go to **Settings**, choose the **Automations** tab and flip **YOLO Mode (Execute All)**. Click **Update Workspace** to save. Switch it off the same way. The switch is off by default, and every permission request in the workspace is approved automatically while it is on.

![Workspace Settings in AgentRQ: the YOLO Mode (Execute All) switch turned on and saved, then off and saved](https://agentrq.com/assets/guidelines/yolo-mode-workspace-settings.gif)

### A Safe YOLO Setup for Nova

- → **Use a worktree.** Run YOLO work with `--worktree` or in a throwaway clone, so it never lands on your main checkout unreviewed.
- → **Allow the boring tools, not everything.** **Always Allow** adds the tool to the workspace's auto-approved list, so the routine calls stop asking and the risky ones still do. Prune that list in workspace settings now and then.
- → **Leave the workspace-wide switch off.** Turn YOLO on per task instead, so it never outlives the job you trusted.
- → **Bring your own sandbox.** Nova runs commands on your machine, so put YOLO tasks in a container or VM.
- → **Read the record.** The [tool call history](https://agentrq.com/features/tool-call-history) lists every call the task made, including the ones that were auto-approved.

## FAQ

**How do I enable YOLO mode in Nova?** Start it with `nova --unleash`, or type `/unleash on --force` in a running session. `/yolo` is an alias for `/unleash`.

**What is the difference between unleash and /approve auto in Nova?** Auto approves low-risk operations and still asks about risky ones. Unleash removes the guardrails and approves everything.

**What is Nova's default approval mode?** Manual. Every change is reviewed before Nova applies it.

**Does Nova have a sandbox?** Not that we found. It can run a session in a separate git worktree and back up files before changes, but commands run on your machine.

**How do I approve Nova actions remotely?** Connect `nova acp` to [AgentRQ](https://agentrq.com) through the ACP Gateway. Its permission requests show up in the task on the web, your phone or Slack.

For every other agent, see [what YOLO mode is and how to turn it on in every coding agent](https://agentrq.com/blog/what-is-yolo-mode-and-how-to-turn-it-on-in-every-coding-agent).