---
title: "How to Enable YOLO Mode in Poolside | AgentRQ Guidelines"
url: https://agentrq.com/guidelines/yolo-mode/poolside
description: "Poolside pool YOLO mode: switch to the Allow all approval mode with Shift+Tab or /mode always-allow, or run pool exec --unsafe-auto-allow headless."
---

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

# How to Enable YOLO Mode in Poolside

Poolside's coding agent, `pool`, calls its YOLO mode **Allow all**. Press Shift+Tab until it shows, or type `/mode always-allow`. For a headless run, use `pool exec` with `--unsafe-auto-allow`.

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). Everything below was checked against the pool README, changelog and Permissions docs (poolsideai/pool, version 1.0.16) 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)

## What YOLO Mode Turns Off in Poolside

Allow all approves tool calls automatically. Two things still stop it. Deny rules in `settings.yaml` still apply. And switching from Plan back to Build always needs your review, even under Allow all.

## How to Enable YOLO Mode in Poolside

| Approval mode | ID | What it does |
| --- | --- | --- |
| Always ask | `default` | Asks for anything not already allowed |
| Accept edits | `accept-edits` | Approves workspace file reads and writes |
| Auto | `auto` | A classifier model rates each request by risk |
| Allow all | `always-allow` | Approves tool calls automatically |

In a session, **Shift+Tab** cycles through the approval modes, and `/mode <approval-mode>` jumps to one:

text

```text
/mode always-allow
```

There is no startup flag for Allow all in interactive `pool`. For scripts and CI, `pool exec` takes `--unsafe-auto-allow`:

bash

```bash
pool exec -p "scan cmd/cli code for vulnerabilities" -o json --unsafe-auto-allow
```

Poolside's docs say to use it only in trusted, sandboxed environments.

### The Halfway Options

- → **Accept edits** approves file reads and writes in the workspace and still asks about commands.
- → **Auto** runs low-risk actions, runs medium-risk ones with a notice, and asks about high-risk ones. It needs a classifier model in `~/.config/poolside/settings.yaml` under `pool.auto_mode_classifier`.
- → **Permission rules** in `settings.yaml` allow or deny shell commands by pattern, such as `git log *`, and paths such as `~/.ssh/**`. A deny always wins. Commands with pipes or subshells always ask.

### Sandbox

`pool acp` takes a `--sandbox` flag, such as `--sandbox required`. Sandbox settings live under the `sandbox` key in `settings.yaml` and set the container image, read-only or read-write workspace access, extra mounts and allowed network destinations. Poolside's docs do not say whether Allow all changes the sandbox, so treat them as separate settings.

## How to Enable YOLO Mode in Poolside Through AgentRQ

Poolside's own 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 Poolside to an AgentRQ workspace through the [ACP Gateway](https://agentrq.com/docs/connect-acp-agent) ([Poolside setup guide](https://agentrq.com/docs/agents/poolside)):

bash

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

Then start the bridge with the same command minus `--login`. `pool` is itself built on ACP: the terminal app drives Poolside's agent through `pool acp`, and the approval mode is a session setting of that server. Leave it on **Always ask**, so Poolside asks instead of approving on your behalf. Each permission request now shows up in the AgentRQ task on the web, on your phone or in Slack, together with the command or edit it is asking about. Answer **Allow Once**, **Always Allow** or **Deny** from wherever you are, and Poolside 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 Poolside 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 Poolside

- → **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.** Workspace settings also has **YOLO Mode (Execute All)**. Turn YOLO on per task instead, so it never outlives the job you trusted.
- → **Keep Poolside's deny rules.** They still apply under AgentRQ's YOLO, so put `git push *`, `rm *` and secret paths like `~/.ssh/**` in `settings.yaml`.
- → **Use the sandbox for unattended runs.** Poolside's own advice for `--unsafe-auto-allow` is a trusted, sandboxed environment.
- → **Commit first.** Start every YOLO task from a clean git tree, so any change is one `git reset` away.
- → **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 Poolside?** Switch the approval mode to **Allow all**: press Shift+Tab until it shows, or type `/mode always-allow`.

**How do I run pool without prompts in CI?** Use `pool exec` with `--unsafe-auto-allow`. Tool calls run without prompts, and deny rules still apply.

**Does Allow all skip everything in Poolside?** No. Deny rules still apply, and switching from Plan back to Build always needs your review.

**What is Auto mode in Poolside?** An approval mode where a classifier model rates each request. Low-risk actions run, medium-risk ones run with a notice, and high-risk ones ask you.

**How do I approve Poolside tool calls remotely?** Connect Poolside to [AgentRQ](https://agentrq.com) through the ACP Gateway, with the approval mode on Always ask. 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).