> ## 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.

# Introduction

<CardGroup cols={2}>
  <Card title="API" icon="code" href="/api-reference">
    Hit the endpoints directly. Best for SDKs, services, and CI integrations.
  </Card>

  <Card title="CLI" icon="terminal" href="/cli/install">
    A local binary that analyzes your repo and writes graph sidecars next to your source files. Best for day-to-day work in the terminal.
  </Card>
</CardGroup>

## CLI quickstart

The fastest path: install the binary, go to your repo, and run `supermodel`. If no config exists, it handles setup automatically; after that it starts the live graph watcher.

### 1. Install

```bash theme={null}
curl -fsSL https://supermodeltools.com/install.sh | sh
```

Other options: `npm install -g @supermodeltools/cli` or build from source. See [Installation](/cli/install).

### 2. Start the live graph watcher

```bash theme={null}
cd /path/to/your/repo
supermodel
```

If no config exists, `supermodel` launches setup automatically. It authenticates you, confirms the repo, offers to install the Claude Code hook, and enables writing `.graph.*` sidecars next to source files.

Then `supermodel` builds the graph and stays running as the live watcher. Press `Ctrl+C` to stop and clean generated sidecars.

### 3. Tell your agent the sidecars exist

Pipe the awareness prompt into your agent's instructions file:

```bash theme={null}
supermodel skill >> CLAUDE.md
# or AGENTS.md, .cursorrules, etc.
```

Use `>>` to append to existing instructions instead of replacing them. If the Supermodel block is already present, skip this step or remove the old block before running it again.

The prompt explains the naming convention (`Foo.py` → `Foo.graph.py`), the three sections inside each sidecar (`[deps]`, `[calls]`, `[impact]`), and tells the agent to read the sidecar before the source file.

### 4. What you get

After the watcher runs, each source file gets one `.graph.*` sidecar with dependency, call, and impact sections:

```
src/
├── login.go
└── login.graph.go     ← deps, calls, impact, domains, and blast radius
```

Example output shape from a generated graph file:

```go theme={null}
// cmd/login.graph.go
// [deps]
// imports     internal/auth/doc.go
// imports     internal/auth/handler.go
// imported-by main.go

// [calls]
// init → LoginWithToken    internal/auth/handler.go:109
// init → Login             internal/auth/handler.go:29

// [impact]
// risk        MEDIUM
// domains     CoreConfig · SupermodelAPI
// direct      1
// transitive  1
// affects     main.go
```

Your agent reads these via `cat` and `grep` like any other file. No prompt changes, no extra context windows.

### 5. Keep it running

The bare `supermodel` command is the live graph watcher. Run it any time you want graph files to stay fresh as you code:

```bash theme={null}
supermodel
```

Live refreshes are driven by hook notifications. If you are not using a hook, run `supermodel --fs-watch` to watch local file changes directly.

For one-shot analysis (no watcher), use:

```bash theme={null}
supermodel analyze
```

### 6. What to do with the graph

Once a graph is cached, every other command reuses it instantly:

| Goal                                 | Command                                   |
| ------------------------------------ | ----------------------------------------- |
| Find unreachable functions           | `supermodel dead-code`                    |
| See what a change impacts            | `supermodel blast-radius path/to/file.go` |
| Codebase health report               | `supermodel audit`                        |
| Find usages of a symbol              | `supermodel find handleRequest`           |
| Token-efficient context for one file | `supermodel focus path/to/file.go`        |

Start with the [`supermodel` watcher reference](/cli/commands/supermodel) or the [`analyze` one-shot reference](/cli/commands/analyze).