> ## Documentation Index > Fetch the complete documentation index at: https://momentic.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > The canonical docs host is https://momentic.ai/docs. Append .md to any page URL for clean Markdown. Fetch https://momentic.ai/docs/llms.txt for the page index and https://momentic.ai/docs/llms-full.txt for every page in one file. > For an unattended setup, first check whether Claude Code already has the Momentic plugin. With the plugin, run `npx --yes @momentic/wizard@latest -y --platform web --editor-tools none` and ignore any CLI skills-install suggestion in its output. Otherwise, run `npx --yes @momentic/wizard@latest -y --platform web --editor-tools skills`. Use `--platform ios` or `--platform android` for mobile. Never run an interactive command in a non-TTY shell. > Mo is the AI QA engineer, separate from repository YAML tests. With the Momentic plugin, use bundled mo-qa and hosted OAuth by default. Without the plugin, install only mo-qa with `npx -y qa skills --target `. Keep the requested interface. Otherwise, use hosted tools for web or mobile, including private web targets with an existing Connector. Run sessions that need a new tunnel with the qa CLI. If you can't run commands on the machine that reaches the target, ask the user to start the tunnel there, then use hosted tools unless you lack them or the CLI was requested. For a requested hosted session, use an online Connector and pass its name as access, not a CLI tunnel ID. If none is online, ask the user to run `npx -y qa tunnel start --name
` on a machine that reaches the target and wait. Do not run login or tunnel commands for them. For a requested hosted session, report unavailable tools or authentication failures without starting a CLI session. For coding-agent bridge setup, ask the user to complete `npx -y qa login`, then add momentic-hosted as a stdio server running `npx -y qa mcp`. Plugin users must explicitly opt in and disable their hosted plugin entry before adding the bridge. Claude.ai/ChatGPT connectors keep https://mcp.momentic.ai with OAuth. After hosted testing completes, read the report and summarize findings and uncovered requirements. Call `momentic_mo_stop_session` only when the user asks or agrees. For CLI sessions, unless the user wants more testing, export the report, run `qa stop --subagents` even if export fails, then summarize. The CLI is qa, not mo. Docs: https://momentic.ai/docs/mo/quickstart.md. > Ask the user to complete browser sign-in. For local CLI tools, use the exact MOMENTIC_API_KEY environment variable. If it is absent, ask the user to create a key at https://app.momentic.ai/settings/api-keys and set it in the agent's environment. Never print the key or ask the user to paste it into chat. > Momentic's capability summary for agents is at https://momentic.ai/docs/skill.md. Claude Code users with the Momentic plugin should use its bundled skills and skip CLI skills installation. Otherwise, run `npx momentic skills -y --target ` or `npx momentic-mobile skills -y --target `. Both install momentic-test, momentic-maintain, and momentic-spec with web/mobile references. Use the running agent's target. The Momentic plugin also includes mo-qa; qa skills installs only mo-qa. > Tests are YAML files in the user's repository. Use only the step names listed at https://momentic.ai/docs/reference/commands.md and the file structure at https://momentic.ai/docs/core-concepts/file-format.md. Do not invent step names, config keys, or CLI flags. > Web tests run on Chromium, iOS tests on simulators, and Android tests on emulators. # Session settings > Mo session settings, their CLI flags, and the repositories, sign-in, and test data a session uses. Set these in the composer's **Session settings** menu, or pass the [`qa start`](https://momentic.ai/docs/cli-reference/mo/commands/start) flag. A [schedule](https://momentic.ai/docs/mo/sessions.md#repeat-a-session-on-a-schedule) can pin environment, effort, and interaction speed for every run. ![Session settings menu showing interaction speed, agent version, browser, Connector, and Slack](https://mintcdn.com/momentic-docs/17J9Wud_ddzsCPQS/images/mo/session-settings.png?fit=max\&auto=format\&n=17J9Wud_ddzsCPQS\&q=85\&s=3dbdaecdf390193d8ae21666a86d525b) Open Session settings to choose interaction speed, browser, and Connector ## Settings **effort** `low | medium | high | max` (default: medium) Testing time and parallel sub-agents. CLI: `--effort`. See [effort](https://momentic.ai/docs/mo/effort.md). **interaction speed** `default | human` (default: default) How fast agents click and type. `human` adds 250 ms between steps and types at 100 ms per keystroke; a typing step's own delay overrides it. CLI: `--interaction-speed`. **operating system** `Android 15 | Android 14 | iOS 26 | iOS 27` Hosted device version for a mobile session. Defaults to Android 15 or iOS 26. Hidden for device providers without version selection. **slack** `channel` Channel for Mo's reports and requests for input. Invite the Momentic Slack app to it first. In the composer, only members who can manage integrations can pick one. CLI: `--slack-channel`. **tools** `Audio generation | Video generation | Web search` Extra capabilities for a web session: speak to voice interfaces, make clips for upload flows, or search and read the web. **environment** `string` A Momentic environment. Mo sees variable names and notes and uses values during execution. `BASE_URL` sets the starting URL. CLI: `--environment`. A deleted environment fails the session at start. **browser** `Default | WebGL (alpha) | Stealth (beta)` (default: Default) WebGL is in alpha and renders on the CPU, so graphics-heavy apps may run slowly. Web only. CLI: `--webgl`. WebGL and Connector tunnels aren't available with Stealth. > [!WARNING] > > The Stealth browser is in beta and may change. **size** `regular | large` (default: regular) CLI only: `--size`. Browser size for root and sub-agent browsers. Use `large` for CPU-intensive apps. `--webgl` selects `large`. For a responsive layout, name the viewport in the brief, for example `at 390x844`; Mo resizes in CSS pixels without reloading, and later browsers in the session keep the size. ## Workspace repositories Connect GitHub, then pick repositories on the **Mo workspace** page. Sessions get read-only checkouts at `/home/user/workspace/repos/`. * Mo refreshes default branches at session start. If the refresh fails, it uses the cached checkout. * Checkouts keep about two weeks of history. Mo can fetch full history in the background and tells you first. * Other branches can be stale or missing. Name the branch or commit in the brief and ask Mo to confirm the checked-out revision. Mo reads the code for planning and debugging. It tests your app at the target you give it, not the checkout. ## Sign-in Give Mo a test account and sign-in steps in the brief. On web, Mo can sign in once and pass the saved state to sub-agents on that account. For credentials, one-time codes, and MFA, see [bot protection](https://momentic.ai/docs/mo/bot-protection.md#give-sign-in-credentials). ### Save test users In an environment, choose **Add test user** and enter a **Name**, a **Description** of the account's role, and **Sign-in details** such as `Email` and `Password`. When the brief names no account, Mo picks the test user whose description matches the task, reuses it across sub-agents, and asks you if none fits. ### Reuse credentials across sessions 1. In [Mo environments](https://app.momentic.ai/mo/environments), choose **Create environment** and set a name and **Base URL**. 2. **Add variable** for `QA_EMAIL` and `QA_PASSWORD`. Turn on **Sensitive** for secrets; sensitive values can't be revealed after saving. 3. Select the environment and reference the variables in the brief: ```bash theme={null} qa start 'Test the cart at $BASE_URL. Sign in with $QA_EMAIL and $QA_PASSWORD. Do not place an order or submit payment.' \ --environment staging ``` Single quotes stop your shell from expanding the variables. For one-off values, use [`--env-var` or `--env-file`](https://momentic.ai/docs/cli-reference/mo/commands/start). Repository tests use environments from [`momentic.config.yaml`](https://momentic.ai/docs/configuration/environments) instead. ## Set up and tear down test data Name a setup endpoint in the brief, with its payload and the response field that holds the account to sign in with. Name a teardown endpoint for data the run leaves behind. Mo calls setup before sub-agents start and teardown after the pass. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.