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

# focus

> Token-efficient graph slice for a single file

Extracts the minimal graph context relevant to the given file: direct imports, functions defined, callers, and (optionally) type declarations.

Output is structured markdown for direct injection into LLM context windows, keeping token usage minimal while preserving semantic relevance. Use `--output json` for structured consumption by tools.

**Aliases:** `ctx`, `context`

## Synopsis

```bash theme={null}
supermodel focus <file> [flags]
```

## Flags

| Flag           | Description                                              |
| -------------- | -------------------------------------------------------- |
| `--depth`      | Import traversal depth (default `1`)                     |
| `--types`      | Include type/class declarations                          |
| `--force`      | Re-analyze even if cache is fresh                        |
| `-o, --output` | Output format: `markdown` \| `json` (default `markdown`) |
| `-h, --help`   | Help for focus                                           |

## Examples

```bash theme={null}
supermodel focus internal/api/client.go

# Walk imports two hops deep, include types
supermodel focus internal/api/client.go --depth 2 --types

# JSON for tool consumption
supermodel focus internal/api/client.go -o json
```