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

# Get Started

> One command. One editable .mdx file. Your first workflow runs in 30 seconds.

<Steps>
  <Step title="Run one command">
    From inside your project:

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    bunx smithers-orchestrator init
    ```

    `init` asks one question, which coding agent do you prefer, shows what it detected (Claude Code, Codex, Pi, ...), and scaffolds `.smithers/` with the focused authoring pack (`create-workflow`, `create-skill`, `docs-driven-development`), installs dependencies, and installs that agent's plugin (or skill). Former recipes live under `examples/init-pack/`; piped or non-interactive callers (CI, agents, `--yes`) skip the question and install defaults, and `--no-tutorial` skips the guided session.

    **`create-workflow`** is the scaffold's star: describe the workflow you want and it writes that plus a companion skill document. Re-running `init` later only offers to update files that drifted.
  </Step>

  <Step title="Make sure your agent knows Smithers">
    Your agent drives Smithers. Two ways to give it the context it needs:

    * **Have your agent read the docs.** Ask it to run `bunx smithers-orchestrator docs` (concise index) or `bunx smithers-orchestrator docs-full`, or point it at [`https://smithers.sh/llms-full.txt`](https://smithers.sh/llms-full.txt). Quick, no install.
    * **Install the plugin or skill for your harness** so context is always loaded. Each page below has the exact install:

    | Harness         | Install the plugin / skill                        |
    | --------------- | ------------------------------------------------- |
    | Claude Code     | [Claude Code plugin + skill](/agents/claude-code) |
    | Codex           | [Codex skill + MCP](/agents/codex)                |
    | Pi              | [Pi plugin + skill](/agents/pi)                   |
    | Any other agent | [Set up in your harness](/agents/setup)           |

    <Note>
      `init` already installs the best integration for your preferred agent: the Claude Code plugin, the Hermes/OpenClaw native plugins, or the curated skill for Codex, Pi, OpenCode, Kimi, Amp, and Antigravity. Use the page above for your harness to wire additional agents or add MCP.
    </Note>
  </Step>

  <Step title="Ask your agent to create a workflow">
    You don't run Smithers, your coding agent does: you describe outcomes, it picks and runs the workflow. Ask it, in plain language:

    > **"Use create-workflow to build a workflow that checks my API and keeps iterating until tests pass."**

    Your agent runs `create-workflow`; a durable run completes and reports the generated workflow and companion skill path back to you.

    Run it yourself in a terminal and a cheap, fast model narrates the result: a short recap plus a self-contained HTML summary that opens in your browser (written under `.smithers/reports/`). Pass `--no-report`, or set `SMITHERS_NO_REPORT=1`, to skip it.

    <Note>
      This runs the coding agent `init` detected (Claude Code, Codex, ...), so have one installed and signed in.
    </Note>
  </Step>

  <Step title="Ask your agent to open the run UI">
    To watch a run live in your browser, ask your agent:

    > **"Open the Smithers UI for that run."**

    Your agent runs `bunx smithers-orchestrator ui <RUN_ID>`, which opens the run's live status card (stages, output, any approval gates) in your browser. Keep it open while you hand off more work.
  </Step>
</Steps>

## Read next

Your agent ran a workflow; pick what you need next.

<CardGroup cols={2}>
  <Card title="Talk to your agent" icon="comments" href="/guide/talk-to-your-agent">
    **How-to:** phrase requests so your agent picks the right workflow every time.
  </Card>

  <Card title="Watch and steer" icon="gauge" href="/guide/watch-and-steer">
    **How-to:** follow a live run, clear approvals, and redirect without touching code.
  </Card>

  <Card title="What you can do" icon="list-check" href="/guide/what-you-can-do">
    **Reference:** the catalog of outcomes you can hand off, and what to say.
  </Card>

  <Card title="The few concepts you need" icon="lightbulb" href="/guide/concepts">
    **Explanation:** the handful of ideas behind durable runs, gates, and loops.
  </Card>
</CardGroup>