The agent that turns websites into APIs!
---
title: Slash commands
description: Commands available inside the interactive CLI.
---
While in the interactive prompt, the following slash commands are available:
| Command | What it does |
|------------------------|-----------------------------------------------------------|
| `/settings` | Configure model, agent provider, SDK, output directory. |
| `/history` | View past runs with token usage and cost. |
| `/messages <run_id>` | View the full message log for a previous run. |
| `/help` | List all commands. Alias: `/commands`. |
| `/exit` | Quit the CLI. |
## Mode cycling
Press **`Shift+Tab`** to cycle between modes:
```text
agent → manual → engineer → collector → agent ...
```
The current mode is shown in the prompt. Each mode has its own behavior. See
[Usage modes](/docs/modes/manual).
## Direct subcommands
Outside the interactive CLI, you can use direct subcommands:
| Command | What it does |
|---------------|------------------------------------------------------------|
| `agent` | Run an autonomous browser capture and generation pipeline. |
| `collector` | Run AI-powered data collection and export JSON/CSV files. |
| `engineer` | Re-run generation against an existing capture. |
| `list` | List generated scripts and runs; supports `--json`. |
| `show` | Inspect one run; supports `--json`. |
| `run` | Execute a generated client with its language toolchain. |
Scripted flags are command-specific: `agent`, `engineer`, and `run` support
`--json` and `--json-stream`; `list` and `show` support `--json`; and `run`
also supports `--no-interactive` for script selection and dependency prompts. See
[Scripted usage](/docs/cli/scripted-usage).
Manual mode is available only inside the interactive REPL because it opens a
visible browser for human-driven capture.