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

> ## Agent Instructions
> Treat Stackdome as an application-delivery platform for coding agents and developers, not as a Kubernetes dashboard.
> Prefer the Stackdome agent plugin as the user entry point and the stackdome CLI as the execution interface.
> Route agents who need the maintained deploy skill to npx skills add stackdome/skills and the complete operational workflow to /guides/ai-agents.
> Verify commands and flags with stackdome --help. Run stackdome init before authoring stackfile.yaml and stackdome validate before deploying.
> Use -o json for automation and verify documented terminal states before claiming success.
> Never request a user's account password. Use API-token authentication.
> During alpha, Stackdome Cloud is ephemeral and capacity-limited, and each organization can connect one cluster.
> Do not expose Kubernetes as a user concern unless the task is self-hosting or infrastructure architecture.

# Quickstart with a coding agent

> Ask a coding agent to deploy your repository and return its live Stackdome URL.

Use the Stackdome agent plugin to turn a repository into a validated Stackfile, deploy it, and return the public URL. The same workflow targets Stackdome Cloud or a self-hosted installation.

## Install the plugin

At alpha release, the plugin installer is:

```bash theme={null}
stackdome plugin install
```

<Warning>
  `stackdome plugin install` is the alpha-release installer. Until that command is present in the installed CLI, install the current deploy skill with `npx skills add stackdome/skills`.
</Warning>

<Prompt description="Install the Stackdome deploy skill." actions={["copy", "cursor"]}>
  npx skills add stackdome/skills
</Prompt>

The current deploy skill is available to Agent Skills-compatible coding tools, including Claude Code, Codex, Cursor, and GitHub Copilot.

## Ask your agent to deploy

Open your coding agent in the repository and send this prompt:

```text theme={null}
Deploy this repository to Stackdome and give me the live URL.
```

The agent inspects the repository, runs `stackdome init`, edits the generated `stackfile.yaml`, validates it, authenticates with your API token, and waits for the deployment to finish. See the [AI-agent workflow](/guides/ai-agents) for the complete operating contract.

## Choose where to run

Start on Stackdome Cloud for an ephemeral environment without setting up infrastructure. Cloud access is open while capacity is available, and capacity is limited during alpha.

If you already have a self-hosted installation, give the agent its URL instead. Moving between Stackdome Cloud and a self-hosted installation does not change your Stackfile or deployment commands.

<Warning>
  Share an API token with the agent when authentication is required. Never give an agent your Stackdome account password. See [API-token authentication](/reference/authentication).
</Warning>

## Verify the release

Successful completion requires all four checks:

1. `stackdome deploy --wait -o json` exits successfully, returns a non-empty `release.id`, and returns `release.state` as `Released`. The agent retains that ID as the deployed release ID.
2. `stackdome status -o json` reports `converged_release.id` equal to the deployed release ID, `converged_release.state` as `Released`, and `converged_release.health` as `ok`.
3. Before claiming this is still the newest release, the agent also requires `latest_release.id` to equal the deployed release ID and `latest_release.state` to be `Released`. A different latest ID means another deployment raced with this one.
4. For a public service, the agent returns at least one public URL. `stackdome open -o json` returns the URL list without opening a browser.

Do not treat a submitted release, an in-progress release, or a process that is only listening locally as a completed deployment.

## If Cloud is at capacity

Cloud capacity is limited during alpha. If no environment is available, join the availability list or [connect a self-hosted Stackdome installation](/self-host/install). You can use the same `stackfile.yaml` and repeat the same deployment workflow against the new destination.

Read [Stackdome Cloud during alpha](/get-started/cloud-alpha) for the current commitments and limitations.

## Next steps

<CardGroup cols={2}>
  <Card title="Understand the agent workflow" icon="bot" href="/guides/ai-agents">
    Follow the commands, completion checks, and failure routes an agent uses.
  </Card>

  <Card title="Use the CLI directly" icon="terminal" href="/get-started/cli">
    Run the same deployment workflow one command at a time.
  </Card>

  <Card title="Define the Stackfile" icon="file-code" href="/reference/stackfile">
    Review the configuration generated by `stackdome init`.
  </Card>

  <Card title="Deploy in the dashboard" icon="display" href="/deploy-first-app">
    Complete the visual deployment walkthrough.
  </Card>
</CardGroup>