> ## 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.

# analyze

> Upload a repository and run the full analysis pipeline

Archives the repository, uploads it to the Supermodel API, and runs call graph generation, dependency analysis, and domain classification. Results are cached locally by content hash. Subsequent commands (`dead-code`, `blast-radius`, `graph`) reuse the cache automatically.

By default, `.graph.*` shard files are written next to each source file. Pass `--no-shards` to skip writing graph files.

## Synopsis

```bash theme={null}
supermodel analyze [path] [flags]
```

## Flags

| Flag           | Description                               |
| -------------- | ----------------------------------------- |
| `--no-shards`  | Skip writing `.graph.*` shard files       |
| `--force`      | Re-analyze even if a cached result exists |
| `-o, --output` | Output format: `human` \| `json`          |
| `-h, --help`   | Help for analyze                          |

## Examples

```bash theme={null}
# Analyze the current directory
supermodel analyze

# Re-analyze without using the cache, output JSON
supermodel analyze --force -o json

# Run analysis without writing sidecar files
supermodel analyze --no-shards
```