From 25d989e4a833bb45583230ba3e8f7458f82059d8 Mon Sep 17 00:00:00 2001 From: Michael Parker Date: Tue, 3 Nov 2026 19:11:35 +0000 Subject: [PATCH 1/2] docs: add Stunt Double Studio section Add a Studio section covering install and setup, local runs, the viewer, the .stuntdouble/ files and commands, moving a checklist to cloud runs, and troubleshooting. Explain on the Claude Code plugin page that the plugin ships both the hosted server (cloud runs) and Studio, and link Studio from the overview and the Connect page. Signed-off-by: Michael Parker --- content/docs/index.mdx | 5 + content/docs/mcp/connect.mdx | 2 +- content/docs/meta.json | 1 + content/docs/studio/cloud-runs.mdx | 85 ++++++++++++++++ content/docs/studio/files-and-commands.mdx | 54 ++++++++++ content/docs/studio/index.mdx | 110 +++++++++++++++++++++ content/docs/studio/install.mdx | 95 ++++++++++++++++++ content/docs/studio/meta.json | 5 + content/docs/studio/run-checklists.mdx | 52 ++++++++++ content/docs/studio/troubleshooting.mdx | 67 +++++++++++++ content/docs/studio/viewer.mdx | 44 +++++++++ content/mcp-clients/claude-code-plugin.mdx | 11 +++ 12 files changed, 530 insertions(+), 1 deletion(-) create mode 100644 content/docs/studio/cloud-runs.mdx create mode 100644 content/docs/studio/files-and-commands.mdx create mode 100644 content/docs/studio/index.mdx create mode 100644 content/docs/studio/install.mdx create mode 100644 content/docs/studio/meta.json create mode 100644 content/docs/studio/run-checklists.mdx create mode 100644 content/docs/studio/troubleshooting.mdx create mode 100644 content/docs/studio/viewer.mdx diff --git a/content/docs/index.mdx b/content/docs/index.mdx index 2c1b044..f72054b 100644 --- a/content/docs/index.mdx +++ b/content/docs/index.mdx @@ -106,6 +106,11 @@ Each name links to its definition in **[Core concepts](/concepts)**. description: "How well AI agents can use a website: the public ranking and how to raise a score.", href: "/index-ranking", }, + { + title: "Stunt Double Studio", + description: "The free local app: run a checklist in your own Chrome, from your coding agent.", + href: "/studio", + }, { title: "MCP server", description: "Endpoint, clients, scopes, and every tool, prompt and resource.", diff --git a/content/docs/mcp/connect.mdx b/content/docs/mcp/connect.mdx index 49bf8fa..5fb1923 100644 --- a/content/docs/mcp/connect.mdx +++ b/content/docs/mcp/connect.mdx @@ -4,7 +4,7 @@ icon: "plug" description: "Set up a client from Integrations in your workspace, pick the right MCP endpoint, and see or revoke what a connection can do." --- -Every client connects to the same server and signs in with OAuth the first time it needs your account. No API keys. This page covers what the Stunt Double app does for you and the endpoints on offer; the [client pages](/mcp/clients/claude-code) cover each client's own setup, sign-in and troubleshooting. +Every client connects to the same server and signs in with OAuth the first time it needs your account. No API keys. This page covers what the Stunt Double app does for you and the endpoints on offer; the [client pages](/mcp/clients/claude-code) cover each client's own setup, sign-in and troubleshooting. This hosted server is where cloud runs happen; to run a checklist on your own machine with no account, see [Stunt Double Studio](/studio). ## From Integrations in your workspace diff --git a/content/docs/meta.json b/content/docs/meta.json index 089cfec..bd1a51e 100644 --- a/content/docs/meta.json +++ b/content/docs/meta.json @@ -12,6 +12,7 @@ "---Agent readiness---", "index-ranking", "---Extend and integrate---", + "studio", "mcp", "...api", "stuntkit", diff --git a/content/docs/studio/cloud-runs.mdx b/content/docs/studio/cloud-runs.mdx new file mode 100644 index 0000000..9040a7d --- /dev/null +++ b/content/docs/studio/cloud-runs.mdx @@ -0,0 +1,85 @@ +--- +title: "Cloud runs" +icon: "automation" +description: "Move a Studio checklist to a Stunt Double workspace with /stuntdouble cloud for parallel, scheduled and independently judged runs." +--- + +# Cloud runs + +Studio answers "did I break this?" on your machine. Cloud runs keep +answering it after you've moved on: on every deploy, every pull request and +every night, with nobody watching. + +Cloud runs are the paid step, on the hosted MCP server the Claude Code plugin +also installs. They add: + +- **Parallel, unattended and scheduled runs** in hosted browsers. +- **Triggers** on deploys, pull requests and Figma changes. +- **An independent judge**, so the agent that went through the flow doesn't + grade its own work. +- **Interviews, design reviews and feedback triage.** +- **Index scoring** from the [Stunt Double Index](/index-ranking). +- **Team sharing**, plus [Slack](/integrations/slack), + [Linear](/integrations/linear) and [GitHub](/integrations/github). + +## Move a checklist to the cloud + +```text +/stuntdouble cloud +``` + + + + +### Agree to the upload + +Studio tells you what leaves your machine: the actor, the checklist and its +URL. Cloud runs on the Free plan may go into the research corpus. It goes on +only when you agree. + + + + +### Sign in and pick a workspace + +The first time, Claude Code shows the hosted server's sign-in: a code sent to +your email, or Google. Pick a workspace, and Studio saves it in +`stuntdouble.json`. + + + + +### Give it a URL the cloud can reach + +Hosted browsers can't reach your `localhost`. If the checklist points at a +local URL, Studio asks for a public or preview URL, writes it to the +checklist, and moves the local origin to `local_base_url` so your local runs +keep using it. On the Startup plan and above, a +[device](/integrations/self-hosted-workers) can reach private sites instead. + + + + +### Push and run + +Studio creates or updates the project, actor and checklist in your workspace, +writes their cloud ids back into your files, and starts a run. Running the +command again updates the same checklist instead of making a copy. + +The result lands in `runs/` beside your local runs, so the +[viewer](/studio/viewer) lists both, with a link to the run in the dashboard. + + + + + + Cloud runs need a Stunt Double plan. The Free plan includes 60 compute + minutes a month and 2 actors. Hobby, Startup, Pro and Enterprise add more. + See [pricing](https://www.stuntdouble.io/pricing). If a run would go past + your plan's limit, Studio tells you and offers a local run instead. + + +## Next + +- [Re-check every deploy automatically](/tutorials/building-workflows) +- [MCP server](/mcp): every tool the hosted server offers diff --git a/content/docs/studio/files-and-commands.mdx b/content/docs/studio/files-and-commands.mdx new file mode 100644 index 0000000..aad6503 --- /dev/null +++ b/content/docs/studio/files-and-commands.mdx @@ -0,0 +1,54 @@ +--- +title: "Files and commands" +icon: "code" +description: "What Studio keeps in .stuntdouble/, which files to commit, and every /stuntdouble command and CLI command." +--- + +# Files and commands + +## The files + +Everything lives in `.stuntdouble/` at the project root. Commit all of it +except `.live/`, which setup adds to `.gitignore`. + +| Path | What it holds | +| --- | --- | +| `stuntdouble.json` | Project settings: `local_base_url`, `headless`, and the workspace a cloud push goes to | +| `actors/.json` | One actor: name, description, instructions and knowledge | +| `checklists/.json` | One checklist: its actor, URL, instructions and checks | +| `runs/-/` | One run: `run.json`, `activity.jsonl` and `shots/` | +| `.live/` | The state of a run in progress. Not committed | + +Actors and checklists use the same fields as the hosted server, with slugs in +place of ids, so a [cloud push](/studio/cloud-runs) sends them unchanged. Each +check has a `key` that never changes, since verdicts and cloud ids follow it. + +Studio writes the `runs/` folders. Don't edit them by hand. + + + Actor knowledge can hold a login for the actor to use. These files are + committed, so put only test accounts in them, never real credentials. + + +## Commands in Claude Code + +| Command | What it does | +| --- | --- | +| `/stuntdouble setup` | Checks your machine, then writes an actor and a checklist for this project | +| `/stuntdouble run ` | Runs a checklist in your local Chrome | +| `/stuntdouble run resume` | Carries on a run that stopped before it finished | +| `/stuntdouble open` | Opens the viewer | +| `/stuntdouble cloud ` | Moves a checklist to a workspace and starts a [cloud run](/studio/cloud-runs) | +| `/stuntdouble doctor` | Checks Node, Chrome, the viewer port and how local runs are billed | + +## The CLI + +The `stuntdouble` package takes three 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 +``` + +`view` also takes a folder: `npx stuntdouble view path/to/project`. diff --git a/content/docs/studio/index.mdx b/content/docs/studio/index.mdx new file mode 100644 index 0000000..81aebe5 --- /dev/null +++ b/content/docs/studio/index.mdx @@ -0,0 +1,110 @@ +--- +title: "Overview" +icon: "run" +description: "Stunt Double Studio is the free local app: run a checklist in Chrome on your own machine, from your coding agent, and keep every run as files in your project." +--- + +# Stunt Double Studio + +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 +flow, judges each check and leaves the evidence in your project. + + + +## What you get + +- **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 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. +- **A viewer for the evidence.** A local page shows each check's verdict, the + screenshots and the activity log as the run happens, with a button to stop + it. + +## Start here + +```sh +claude plugin marketplace add stunt-double/stuntdouble-mcp +claude plugin install stuntdouble@stuntdouble +``` + +Then, in Claude Code: + +```text +/stuntdouble setup +/stuntdouble run +``` + +[Install and set up](/studio/install) covers each step and other agents. + +## Studio and cloud runs + +Studio verdicts are self-judged: the same agent that went through the flow +decides whether each check passed. When you need more, a +[cloud run](/studio/cloud-runs) on the hosted server adds an independent +judge, runs in parallel and on a schedule, and triggers on deploys, pull +requests and Figma changes. `/stuntdouble cloud ` moves a local +checklist to a workspace unchanged. + +| | 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 | +| 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 | + +## In this section + + diff --git a/content/docs/studio/install.mdx b/content/docs/studio/install.mdx new file mode 100644 index 0000000..feb95fb --- /dev/null +++ b/content/docs/studio/install.mdx @@ -0,0 +1,95 @@ +--- +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." +--- + +# Install and set up + +Install the plugin once, then set up each project you want to test. + +## 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. + +## Install in Claude Code + + + + +### Add the plugin + +```sh +claude plugin marketplace add stunt-double/stuntdouble-mcp +claude plugin install stuntdouble@stuntdouble +``` + +Plugins load when a session starts, so start a new Claude Code session after +installing. + + + + +### Set up your project + +Open Claude Code in your project folder and run: + +```text +/stuntdouble setup +``` + +Setup runs [doctor](/studio/troubleshooting#doctor) first and tells you how +local runs are billed. It then asks for three things: + +- the URL to test (localhost is fine), +- who the user is, +- what must be true when they're done. + +From your answers it writes `.stuntdouble/` with an actor, a checklist of 3 to +8 checks and a `.gitignore`. See [files and commands](/studio/files-and-commands) +for what each file holds. + + + + +### Run it + +```text +/stuntdouble run +``` + +Replace `` with the checklist's file name, without `.json`. +[Run a checklist](/studio/run-checklists) explains what happens next. + + + + + + Setup offers to allow Studio's browser tools for this project, so Claude Code + stops asking before each click. It adds the permission to + `.claude/settings.local.json` only if you agree. + + +## Other agents + +Any MCP client can start the local server over stdio: + +```sh +npx -y stuntdouble mcp +``` + +Add that command as a stdio server in your client's MCP settings. The +`/stuntdouble` commands are Claude Code plugin commands, so in other clients +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. + +## No account needed + +Studio never asks you to sign in. You only need a Stunt Double account when you +move a checklist to [cloud runs](/studio/cloud-runs). diff --git a/content/docs/studio/meta.json b/content/docs/studio/meta.json new file mode 100644 index 0000000..5abb80d --- /dev/null +++ b/content/docs/studio/meta.json @@ -0,0 +1,5 @@ +{ + "title": "Stunt Double Studio", + "icon": "run", + "pages": ["index", "install", "run-checklists", "viewer", "files-and-commands", "cloud-runs", "troubleshooting"] +} diff --git a/content/docs/studio/run-checklists.mdx b/content/docs/studio/run-checklists.mdx new file mode 100644 index 0000000..70cec3e --- /dev/null +++ b/content/docs/studio/run-checklists.mdx @@ -0,0 +1,52 @@ +--- +title: "Run a checklist" +icon: "checklist" +description: "Start a local run with /stuntdouble run, resume an interrupted run, and read the result Studio reports back." +--- + +# Run a checklist + +```text +/stuntdouble run +``` + +## What happens + +1. Studio checks the checklist file. If a field is wrong, it names the field + so your agent can fix it and try again. +2. It prints a link to the [viewer](/studio/viewer), where you can watch the + run and stop it. +3. An actor opens Chrome on your machine and goes through the flow. Page text + and screenshots stay with the actor, so your main session stays short. +4. Studio reports the result, for example "Failed: 3 of 4 checks passed", + then each failed or unjudged check with its evidence, and the viewer link. + It offers to fix what failed and run again. + +If the checklist sets `local_base_url` in `stuntdouble.json`, a local run +swaps the checklist URL's origin for it. That's how one checklist tests +localhost on your machine and a preview URL in the cloud. + +## Scores + +A checklist with only pass/fail checks has no score: it passes when every +pass/fail check passes. A checklist with two or more weighted checks and a +`pass_threshold` gets a score, and passes when the score meets the threshold. + +## Verdicts are self-judged + +In Studio, the agent that went through the flow also decides whether each +check passed. That's fast and free, and good for catching what you +broke. For a second opinion, a [cloud run](/studio/cloud-runs) adds an +independent judge. + +## Resume a run + +If a run ends early, because you closed the session, the actor was +interrupted or you stopped it from the viewer, carry on where it left off: + +```text +/stuntdouble run resume +``` + +Checks already judged keep their verdicts, and the actor judges only the ones +left. diff --git a/content/docs/studio/troubleshooting.mdx b/content/docs/studio/troubleshooting.mdx new file mode 100644 index 0000000..b1ccec7 --- /dev/null +++ b/content/docs/studio/troubleshooting.mdx @@ -0,0 +1,67 @@ +--- +title: "Troubleshooting" +icon: "terminal" +description: "Fix Studio problems: run doctor, update Node, find Chrome, free the viewer port, and see which account pays for local runs." +--- + +# Troubleshooting + +## Doctor + +Start here. Doctor checks everything a local run needs, one line each: + +```text +/stuntdouble doctor +``` + +Outside Claude Code, run it in a terminal: + +```sh +npx -y stuntdouble doctor +``` + +A `FAIL` line blocks local runs until you fix it. A `note` line is worth +reading but doesn't block anything. + +## Node + +Studio needs Node 22.18 or later. On an older Node, the local server stops at +start with a message naming the version it found. Update Node, then restart +Claude Code. + +If the Studio tools are missing altogether, the local server didn't start. +Check `node --version` and that `npx` works, then look at the server in `/mcp`. +The first tool listing takes a second or two while `npx` starts. That's +normal. + +## Chrome + +Studio uses Google Chrome, or Playwright's Chromium when Chrome isn't +installed. If doctor reports no Chrome, install Google Chrome, or run: + +```sh +npx playwright install chromium +``` + +## The viewer port + +The viewer starts at port 4747 and moves to the next free port if that one is +taken. Doctor tells you which. Always open the link Studio prints rather than +typing the port. + +## Billing + +Stunt Double makes no model calls for local runs. Your coding agent does the +work, so local runs count against whatever account Claude Code is signed in +with: your Claude plan, or your API key if Claude Code uses one. Run `/status` +in Claude Code to see which. + +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. + +[Cloud runs](/studio/cloud-runs) are billed to your Stunt Double plan instead. + +## Skills or commands missing after install + +Plugins load when a session starts. Start a new Claude Code session. diff --git a/content/docs/studio/viewer.mdx b/content/docs/studio/viewer.mdx new file mode 100644 index 0000000..4daa260 --- /dev/null +++ b/content/docs/studio/viewer.mdx @@ -0,0 +1,44 @@ +--- +title: "The viewer" +icon: "monitor" +description: "Studio's local viewer shows each check's verdict, the screenshots and the activity log while a run happens, and lets you stop the run." +--- + +# The viewer + +The viewer is a local page over your project's `.stuntdouble/` folder. It +lists every run, local and cloud, and updates while a run is going. + +## Open it + +Every run prints its viewer link. To open the viewer at any other time: + +```text +/stuntdouble open +``` + +Someone without Claude Code, such as a teammate reviewing your branch, can open +it from the project folder: + +```sh +npx stuntdouble view +``` + +Open the link it prints. Press Ctrl C to stop the viewer. + +## What it shows + +- **Verdicts.** Each check's result and the evidence behind it. +- **Screenshots.** What the actor saw at each step. +- **The activity log.** Every action the actor took, in order. + +## Stop a run + +Select **Stop** while a run is going. The actor stops at its next step and +ends the run. Checks it already judged keep their verdicts, and +`/stuntdouble run resume` picks up a stopped run later. + +## The port + +The viewer listens on `127.0.0.1`, starting at port 4747. If that port is +taken, it uses the next free one, so always use the link Studio prints. diff --git a/content/mcp-clients/claude-code-plugin.mdx b/content/mcp-clients/claude-code-plugin.mdx index 0fc5091..9c0c867 100644 --- a/content/mcp-clients/claude-code-plugin.mdx +++ b/content/mcp-clients/claude-code-plugin.mdx @@ -4,6 +4,15 @@ description: Install the Stunt Double plugin for Claude Code to get the MCP serv The plugin installs the same hosted MCP server as the [Claude Code](/mcp/clients/claude-code) page, plus the [skills](/mcp/skills) (such as `verify-change` and `run-user-interview`) and the [subagents](/mcp/agents) that know which tools to call for one kind of job. Pick it over the plain server when you want Claude to follow a tested recipe instead of working out each step. If you already added the server with `claude mcp add`, remove it (`claude mcp remove stuntdouble`) so the tools don't load twice. +## What the plugin ships + +The plugin ships two servers: + +- **The hosted server, for cloud runs.** Parallel, scheduled and independently judged runs in a Stunt Double workspace, plus interviews, design reviews and feedback triage. It needs you to sign in. +- **[Stunt Double Studio](/studio), the free local app.** It runs a checklist in Chrome on your own machine, on your Claude plan, and keeps each run as files in `.stuntdouble/`. It needs no account. Start with `/stuntdouble setup`. + +`/stuntdouble cloud ` moves a Studio checklist to a workspace unchanged. See [cloud runs](/studio/cloud-runs). + {/* setup */} You can also install it from `/plugin` inside Claude Code: add the marketplace, then pick **stuntdouble** from the **Discover** tab and choose a scope (just you, this repository, or every project). @@ -14,6 +23,7 @@ The plugin's server signs in the same way as the plain server: run `/mcp`, choos ## Check it works +- Run `/stuntdouble doctor` to check that Studio can run locally. - Type `/stuntdouble:` to list the skills, for example `/stuntdouble:verify-change`. Claude also picks a skill on its own when your request matches it. - Run `/agents` to see the subagents the plugin added. - Ask: "List my Stunt Double workspaces." @@ -26,6 +36,7 @@ The plugin's server signs in the same way as the plain server: run `/mcp`, choos ## Next +- [Stunt Double Studio](/studio): run checklists locally, for free - [Skills](/mcp/skills) and [agents](/mcp/agents): what each one does - [Automate from a conversation](/tutorials/automate-with-mcp): what to ask for once you're connected - [Tools](/mcp/tools): every tool, prompt and resource From 81ac1d13e9255881a3b5b93fb78e682b1f2ddfe2 Mon Sep 17 00:00:00 2001 From: Michael Parker Date: Tue, 3 Nov 2026 19:19:46 +0000 Subject: [PATCH 2/2] docs(studio): correct scoring, the run result and cloud push wording A single weighted check makes a run scored and pass_threshold defaults to 100. The run result example matches what Studio prints, the requirements name Playwright's Chromium, screenshots in runs/ are flagged as committed, and troubleshooting explains the hosted server the plugin adds. Signed-off-by: Michael Parker --- content/docs/studio/files-and-commands.mdx | 2 ++ content/docs/studio/index.mdx | 5 +++-- content/docs/studio/run-checklists.mdx | 8 +++++--- content/docs/studio/troubleshooting.mdx | 5 +++++ 4 files changed, 15 insertions(+), 5 deletions(-) diff --git a/content/docs/studio/files-and-commands.mdx b/content/docs/studio/files-and-commands.mdx index aad6503..a1e8086 100644 --- a/content/docs/studio/files-and-commands.mdx +++ b/content/docs/studio/files-and-commands.mdx @@ -28,6 +28,8 @@ Studio writes the `runs/` folders. Don't edit them by hand. Actor knowledge can hold a login for the actor to use. These files are committed, so put only test accounts in them, never real credentials. + Screenshots in `runs/` are committed too and can hold personal data, so + test with accounts that hold none. ## Commands in Claude Code diff --git a/content/docs/studio/index.mdx b/content/docs/studio/index.mdx index 81aebe5..d7c16a1 100644 --- a/content/docs/studio/index.mdx +++ b/content/docs/studio/index.mdx @@ -15,7 +15,7 @@ flow, judges each check and leaves the evidence in your project. items={[ { label: "Price", value: "Free" }, { label: "Account", value: "None needed" }, - { label: "You need", value: "Node 22.18 or later and Google Chrome" }, + { label: "You need", value: "Node 22.18 or later and Google Chrome (or Playwright's Chromium)" }, ]} /> @@ -56,7 +56,8 @@ decides whether each check passed. When you need more, a [cloud run](/studio/cloud-runs) on the hosted server adds an independent judge, runs in parallel and on a schedule, and triggers on deploys, pull requests and Figma changes. `/stuntdouble cloud ` moves a local -checklist to a workspace unchanged. +checklist to a workspace with the same actor and checks. A localhost URL +needs a public or preview URL for the cloud. | | Studio | Cloud runs | | --- | --- | --- | diff --git a/content/docs/studio/run-checklists.mdx b/content/docs/studio/run-checklists.mdx index 70cec3e..673d18a 100644 --- a/content/docs/studio/run-checklists.mdx +++ b/content/docs/studio/run-checklists.mdx @@ -18,7 +18,7 @@ description: "Start a local run with /stuntdouble run, resume an interrupted run run and stop it. 3. An actor opens Chrome on your machine and goes through the flow. Page text and screenshots stay with the actor, so your main session stays short. -4. Studio reports the result, for example "Failed: 3 of 4 checks passed", +4. Studio reports the result, for example "failed. 3/4 checks passed", then each failed or unjudged check with its evidence, and the viewer link. It offers to fix what failed and run again. @@ -29,8 +29,10 @@ localhost on your machine and a preview URL in the cloud. ## Scores A checklist with only pass/fail checks has no score: it passes when every -pass/fail check passes. A checklist with two or more weighted checks and a -`pass_threshold` gets a score, and passes when the score meets the threshold. +pass/fail check passes. A checklist with one or more weighted checks gets a +score. It passes when the score meets `pass_threshold` (100 if you leave it +out) and no pass/fail check failed. Informational checks are recorded, never +scored. ## Verdicts are self-judged diff --git a/content/docs/studio/troubleshooting.mdx b/content/docs/studio/troubleshooting.mdx index b1ccec7..9e6d3c6 100644 --- a/content/docs/studio/troubleshooting.mdx +++ b/content/docs/studio/troubleshooting.mdx @@ -62,6 +62,11 @@ plan. [Cloud runs](/studio/cloud-runs) are billed to your Stunt Double plan instead. +## A hosted server in `/mcp` asks to sign in + +The plugin also adds the hosted server for [cloud runs](/studio/cloud-runs). +You can leave it signed out, since local runs don't use it. + ## Skills or commands missing after install Plugins load when a session starts. Start a new Claude Code session.