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

# Magnitude Harness

> Use the optional Magnitude Harness

Magnitude includes a built-in harness optimized for local models.

* **Uses smaller contexts well:** Keeps context focused instead of burying the model in irrelevant history.
* **Compacts without stopping:** Local models compact more often, so compaction runs in the background with no waiting.
* **Makes tool calls reliable:** Validates calls and gives clear recovery feedback when the model gets them wrong.
* **Breaks doom loops:** Stops repeated or runaway tool behavior before the model gets stuck.
* **Prevents overthinking:** Cuts off excessive reasoning and gets the model back on task.

Select **Magnitude Harness** during setup, or run `magnitude` from the directory you want the agent to work in.

<video autoPlay muted loop playsInline preload="metadata" title="Choosing and running a recommended local model with Magnitude Harness" className="w-full rounded-xl" src="https://mintcdn.com/magnitude-798d9d41/jGblqSqtaD0ED-cO/videos/maglocaldemo.mp4?fit=max&auto=format&n=jGblqSqtaD0ED-cO&q=85&s=13738d7c93273539a001657f2f3dd2f0" data-path="videos/maglocaldemo.mp4" />

## Work with a project

The harness can inspect and edit files, run commands, and execute scripts in the current directory. Type `@` to mention a file or directory. You can paste or drag images into the composer.

Enter bash mode with `/bash` or start a message with `!` to run a shell command directly.

Run `/init` to create an `AGENTS.md` file for project conventions, architecture, tests, and other instructions.

## Sessions

Conversations are saved automatically. Use `/resume` or `Ctrl+R` to open a recent conversation and `/new` to start another one.

When a conversation approaches the model context limit, Magnitude compacts older work into a summary and continues the session.

## Commands and shortcuts

Type `/` to browse available commands. Common commands include `/models`, `/catalog`, `/hardware`, `/setup`, `/bash`, `/init`, `/resume`, and `/new`.

| Shortcut      | Action                         |
| ------------- | ------------------------------ |
| `Enter`       | Send or confirm                |
| `Shift+Enter` | Add a new line                 |
| `Ctrl+T`      | Select reasoning level         |
| `Ctrl+R`      | Open recent conversations      |
| `Esc`         | Close a menu or interrupt work |
| `Ctrl+C`      | Clear input or exit while idle |

## Skills

Skills add reusable capabilities to the harness. Install them in the current project or globally with a compatible skill installer such as `npx skills add`.

Magnitude loads skills from `.claude/skills`, `.agents/skills`, and `.magnitude/skills` in the current project and from the matching directories in your home directory. Project skills take priority over global skills with the same name.

Review a skill before installing it. Skills can run commands, install dependencies, open websites, and interact with external services.

## Web search

Set `EXA_API_KEY` before starting the harness to enable web search through Exa.