> ## Documentation Index
> Fetch the complete documentation index at: https://docs.entire.io/llms.txt
> Use this file to discover all available pages before exploring further.

# runner

> Set up and tune this repository's trail runners.

Manage the trail runner configs in `.entire/runners/`.

```bash theme={null}
entire runner SUBCOMMAND
```

`entire runner` is experimental and appears under [labs](/cli-reference/labs). A [runner](/glossary#runner) scores and reviews a branch's changes; this command manages the per-repository set: risk, confidence, drift, security, review, and others.

## runner setup

Create and tailor this repository's trail runners.

```bash theme={null}
entire runner setup [RUNNER] [flags]
```

`setup` customizes runner templates using repository documentation and structure, merged pull requests, issues, frequently changed code, and past trail findings.

Without an action flag, `setup` opens an interactive action picker. In a non-interactive environment, you must pass `--yes`, `--defaults-only`, `--print-prompt`, or `--dry-run`.

Pass a runner name, such as `risk` or `trail-risk`, to customize only that runner.

Customization uses your configured summary provider. If none is configured and several agents are installed, Entire asks which to use. Pass `--agent NAME` to select one for this run without saving the choice.

| Flag                    | Description                                                                                                                    |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
| `--agent NAME`          | Text-generation agent to use for customization. Only applies to `--yes`, `--dry-run`, or customization selected in the picker. |
| `--debug-dir DIRECTORY` | Write the prompt as `prompt.txt` and, when a provider runs, its raw response as `response.txt`, to this directory.             |
| `--defaults-only`       | Create generic default runners and stop. Does not call a provider.                                                             |
| `--dry-run`             | Run customization and show the result as a diff without writing runner files, even in a repository with no runners.            |
| `--limit N`             | How many recent pull requests, issues, and trails to sample. Defaults to `20`.                                                 |
| `--print-prompt`        | Create defaults if missing, then print the customization prompt instead of running a provider.                                 |
| `--run`                 | Deprecated alias for `--yes`.                                                                                                  |
| `--sources SOURCES`     | Comma-separated data sources to gather: `repo`, `prs`, `checkpoints`, `trails`, or `all`. Defaults to `all`.                   |
| `-y, --yes`             | Create defaults if missing, then customize runners in place. Add `--agent` to skip provider selection too.                     |

`--defaults-only`, `--print-prompt`, and `--dry-run` are mutually exclusive and take precedence over `--yes`.

```bash theme={null}
# Print the customization prompt for every runner
entire runner setup --print-prompt

# Create defaults if missing and customize them with Codex
entire runner setup --yes --agent codex

# Preview changes to the risk runner using repository data only
entire runner setup risk --dry-run --sources repo --agent codex
```

<Warning>
  `--yes` and customization selected in the picker rewrite files in `.entire/runners/`. Review changes with `git diff -- .entire/runners/` before committing.
</Warning>

## Continue With

<CardGroup cols={2}>
  <Card title="review" icon="code-review" href="/cli-reference/review">
    Run a multi-agent review against a branch.
  </Card>

  <Card title="Glossary" icon="book" href="/glossary#runner">
    See how runners and trails fit together.
  </Card>
</CardGroup>