docs(studio): cover the browser app and its model connection

content/docs/studio/cloud-runs.mdx

@@ -79,6 +79,19 @@ The result lands in `runs/` beside your local runs, so the
   your plan's limit, Studio tells you and offers a local run instead.
 </Callout>
 
+## From the terminal or Studio
+
+Without Claude Code, sign in and run the checklist in the cloud from the
+terminal, or from Settings in Studio:
+
+```sh
+npx stuntdouble login
+npx stuntdouble run <checklist> --cloud
+```
+
+It pushes the same files, runs the checklist in your workspace and writes the
+result beside your local runs. This path is for workspaces on a paid plan.
+
 ## Next
 
 - [Re-check every deploy automatically](/tutorials/building-workflows)

content/docs/studio/files-and-commands.mdx

@@ -45,12 +45,16 @@ Studio writes the `runs/` folders. Don't edit them by hand.
 
 ## The CLI
 
-The `stuntdouble` package takes three commands:
+The `stuntdouble` package takes these commands:
 
 ```sh
-npx -y stuntdouble mcp      # the local MCP server over stdio (your agent starts this)
-npx stuntdouble view        # the viewer over this folder's .stuntdouble/
-npx -y stuntdouble doctor   # check Node, Chrome, the viewer port and billing
+npx stuntdouble studio            # open Studio in your browser (--port, --no-open)
+npx stuntdouble run <checklist>   # run one on your model connection (--resume, --max-steps, --cloud)
+npx stuntdouble login | logout    # sign in or out for cloud runs (--workspace <slug>)
+npx -y stuntdouble mcp            # the local MCP server over stdio (your agent starts this)
+npx stuntdouble view              # the read-only viewer over this folder's .stuntdouble/
+npx -y stuntdouble doctor         # check Node, Chrome, the viewer port and billing
 ```
 
-`view` also takes a folder: `npx stuntdouble view path/to/project`.
+`studio` and `view` also take a folder: `npx stuntdouble studio path/to/project`.
+In a terminal, `npx stuntdouble` on its own opens Studio.

content/docs/studio/index.mdx

@@ -8,7 +8,7 @@ description: "Stunt Double Studio is the free local app: run a checklist in Chro
 
 Check your change before you push it. Studio runs a Stunt Double checklist in
 a Chrome on your own machine, from the coding agent session you already have
-open. Point it at localhost, staging or production. An actor goes through the
+open or from Studio in your browser. Point it at localhost, staging or production. An actor goes through the
 flow, judges each check and leaves the evidence in your project.
 
 <PageFacts
@@ -23,9 +23,11 @@ flow, judges each check and leaves the evidence in your project.
 
 - **Runs on your machine.** The actor drives a local Chrome, so it reaches
   `localhost`, a staging site behind your VPN, or production.
-- **Runs on your existing subscription.** Your coding agent is the actor, so
-  local runs use your Claude plan (or your API key, if Claude Code uses one).
-  Stunt Double makes no model calls for local runs.
+- **Runs on the model you already have.** From your coding agent, the agent
+  is the actor, so local runs use your Claude plan (or your API key, if Claude
+  Code uses one). Studio in your browser uses a connection you set up: an
+  Anthropic API key or an OpenAI-compatible endpoint. Stunt Double makes no
+  model calls for local runs.
 - **Runs are files.** Actors, checklists and every run live in
   `.stuntdouble/` in your project. Commit them, review them in a pull
   request, and share them with your team like any other file.
@@ -47,6 +49,12 @@ Then, in Claude Code:
 /stuntdouble run <checklist>
 ```
 
+Or open Studio in your browser, on your own model connection:
+
+```sh
+npx stuntdouble studio
+```
+
 [Install and set up](/studio/install) covers each step and other agents.
 
 ## Studio and cloud runs
@@ -62,7 +70,7 @@ needs a public or preview URL for the cloud.
 | | Studio | Cloud runs |
 | --- | --- | --- |
 | Where the browser runs | Chrome on your machine | Hosted browsers |
-| Who pays for the model | Your Claude plan or API key | Your Stunt Double plan |
+| Who pays for the model | Your Claude plan, or your own API key | Your Stunt Double plan |
 | Account | None | A Stunt Double workspace |
 | Verdicts | Self-judged by your agent | Independent judge |
 | When it runs | When you ask | On demand, on a schedule or on a trigger |

content/docs/studio/install.mdx

@@ -1,20 +1,28 @@
 ---
 title: "Install and set up"
 icon: "rocket"
-description: "Install Stunt Double Studio in Claude Code or any MCP client, check your machine with doctor, and write your first actor and checklist."
+description: "Install Stunt Double Studio in Claude Code or any MCP client, or open it in your browser with npx stuntdouble studio, then write your first actor and checklist."
 ---
 
 # Install and set up
 
-Install the plugin once, then set up each project you want to test.
+There are two ways to use Studio, and both read and write the same
+`.stuntdouble/` files in your project:
+
+- **From your coding agent.** Install the plugin once, then set up each
+  project. Your agent's session is the actor.
+- **[In your browser](#open-studio-in-your-browser).** Run
+  `npx stuntdouble studio` in a project, on a model connection you set up.
 
 ## Before you start
 
 - **Node 22.18 or later.** Check with `node --version`.
 - **Google Chrome.** Or Playwright's Chromium, if you'd rather not install
   Chrome (`npx playwright install chromium`).
-- **A coding agent.** Claude Code gets the full plugin: the local app, the
-  `/stuntdouble` commands and the [cloud runs](/studio/cloud-runs) server.
+- **A coding agent or a model key.** Claude Code gets the full plugin: the
+  local server, the `/stuntdouble` commands and the
+  [cloud runs](/studio/cloud-runs) server. Studio in your browser needs an
+  Anthropic API key or an OpenAI-compatible endpoint instead.
 
 ## Install in Claude Code
 
@@ -89,6 +97,31 @@ ask your agent to set up and run a checklist in plain words.
 The package is [`stuntdouble` on npm](https://www.npmjs.com/package/stuntdouble),
 under the Apache-2.0 license.
 
+## Open Studio in your browser
+
+In your project folder, run:
+
+```sh
+npx stuntdouble studio
+```
+
+Studio opens on `127.0.0.1` and covers setup, actors and checklists, runs,
+the live view and results. A project with no `.stuntdouble/` yet asks for the
+address to test and starts you with a first actor and checklist to edit.
+
+Set the model in Settings: an Anthropic API key (or `ANTHROPIC_API_KEY` from
+your environment), or an OpenAI-compatible endpoint such as OpenAI,
+OpenRouter, or a local model in Ollama or LM Studio. The key stays in
+`~/.stuntdouble/credentials.json`, readable by you only, and never goes into
+the project. Studio never uses a Claude subscription.
+
+A run your agent starts shows up in Studio, and the other way round. To run a
+checklist from the terminal on the same connection:
+
+```sh
+npx stuntdouble run <checklist>
+```
+
 ## No account needed
 
 Studio never asks you to sign in. You only need a Stunt Double account when you

content/docs/studio/troubleshooting.mdx

@@ -60,6 +60,10 @@ If `ANTHROPIC_API_KEY` is set in your environment, doctor adds a note: when
 Claude Code uses that key, local runs are billed to it rather than your Claude
 plan.
 
+Studio in your browser, and `npx stuntdouble run`, use only the connection
+you set in Settings: your Anthropic API key or OpenAI-compatible endpoint is
+billed for those runs. They never use a Claude subscription.
+
 [Cloud runs](/studio/cloud-runs) are billed to your Stunt Double plan instead.
 
 ## A hosted server in `/mcp` asks to sign in