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

# Quickstart

> Set up a provider, run a scan, then read the findings. Five steps from install to report.

<Steps>
  <Step title="Set up a provider">
    ```bash theme={null}
    agentgg init
    ```

    Pick a provider and paste a credential.
  </Step>

  <Step title="Run a scan">
    ```bash theme={null}
    agentgg scan ./src -o ./out
    ```

    The validate, score, and dedup phases run by default.
  </Step>

  <Step title="Read the status">
    ```bash theme={null}
    agentgg status ./out
    ```

    Read what the scan found.
  </Step>

  <Step title="Browse the findings">
    ```bash theme={null}
    agentgg view ./out
    ```

    Browse the findings in a local web UI.
  </Step>

  <Step title="Scan only what changed">
    <Tip>
      To scan only the files a pull request changed, see [Scan a pull request](/cli/guides/scan-a-pull-request).
    </Tip>
  </Step>
</Steps>

## Where the findings go

A scan writes its findings to the output directory.

```
out/
├── summary.md            ← human report
├── findings/...          ← one .md per finding (GHSA-shaped)
└── state/                ← what `status` and `revalidate` read
    ├── scan.json         ← root path + timestamps
    ├── recon.json        ← the recon brief (phase 1)
    ├── plan.json         ← which agents queued / skipped + why (phase 2)
    ├── runs/<id>.json    ← one per scan / recon / revalidate / score / summary
    ├── agents/<slug>.json← per-agent resume sidecar
    └── files/<path>.json ← FileRecord per scanned source file
```

Read more about this directory on the [output and state](/cli/output-and-state) page.