> ## 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 <agent>`. 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 <name> <address>` 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 <id> --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 <agent>` or `npx momentic-mobile skills -y --target <agent>`. 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.

# Effort

> How Mo's effort level sets testing time, parallel sub-agents, and session cost.

Effort sets how long Mo tests and how many sub-agents it runs at once. Set it in
the composer's **Session settings** or with
[`qa start --effort`](https://momentic.ai/docs/cli-reference/mo/commands/start). The default is
`medium`.

```mermaid theme={null}
flowchart LR
  effort["Effort level"] --> time["Testing time and parallel sub-agents"]
  time --> deadline["Deadline"]
  deadline --> repro["Finish bug reproductions in progress"]
  repro --> report["Coverage and unfinished checks"]
```

| Effort | Testing time | Use it for |
| - | - | - |
| `low` | \~15 minutes | Most pull requests |
| `medium` | \~30 minutes | A small feature or one area of the product |
| `high` | \~1 hour | A larger feature spanning several areas |
| `max` | \~2 hours | An entire application |

## How the clock works

* Testing time counts minutes while Mo or its sub-agents work, or while Mo waits
  on them. Time spent clarifying the request doesn't count.
* Mo and its sub-agents get reminders as the deadline approaches.
* At the deadline, Mo stops the sub-agents still working, lets bug reproductions
  in progress finish, and reports what it covered and what it left unfinished.
* If you change the request mid-session, Mo can restart the clock for the new
  scope.

## Area splitting at `high` and `max`

On web, Mo can split a broad request into areas and hand each to a coordinating
agent that plans and steers its own sub-agents. Mo covers the rest itself.
Sessions started for a GitHub pull request don't split.

In Momentic's evaluations on a full open-source web app, a one-hour `high`
session finds several times as many confirmed bugs as a general-purpose coding
agent given the same hour. Splitting at `max` finds more than three times as
many confirmed bugs as the same session without the split.

## Cost

A session bills:

* The active runtime of its agents, not the session's wall time.
* Hosted browser time for web, or simulator and emulator time for mobile.
* Model inference, at cost.

Higher effort runs more agents for longer. `max` runs many more flows than the
other levels, so its total is higher even when its cost per bug found is lower.
Reserve it for full-application coverage.

The **Mo** tab in
[Settings > Usage](https://app.momentic.ai/settings/usage?usageTab=mo) shows
estimated usage for a date range, with a daily chart and CSV export.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.