Slash commands
Commands and keys of the interactive session.
Running reverse-api-engineer opens a full-screen session: the conversation
scrolls above an input bar fixed to the bottom. Type / to open the command
menu; Tab completes and Enter runs the highlighted command.
| Command | What it does |
|---|---|
/new | End the open run and start a new capture. |
/model | Choose the model. In collector mode, the collector's own model. |
/effort | How hard the agent thinks, for Claude models (low to max). |
/mode | Switch between agent, manual, engineer and collector. |
/settings | SDK, agent provider, models, output and sync, changed in place. |
/history | Past runs with their cost; open one to resume or re-engineer it. |
/resume [run_id] | Show a past run's conversation as it was and continue it, on any SDK. |
/output | Everything from the session, unfolded. |
/open | Open the latest generated client. |
/clear | Clear the conversation and its spend. |
/help | What rae does, its modes, commands and keys. Alias: /commands. |
/exit | Quit. Alias: /quit. |
/resume works for runs that saved their SDK session, which agent and engineer
runs do from this release on. Older runs and collector runs cannot be resumed.
Keys
| Key | What it does |
|---|---|
Enter | Send. While the agent works, the message is queued. |
Esc | Stop the run, or close a menu. |
↑ / ↓ | Earlier prompts; in a menu, move, around from either end. |
Tab | Complete a command. |
Shift+Tab | Cycle the mode: agent → manual → engineer → collector. |
Ctrl+E | Cycle the effort level. |
Ctrl+O | Show the full output of folded steps. |
PageUp / PageDown | Scroll the conversation. End jumps back to the latest. |
Option+Delete | Delete the word before the cursor (also Ctrl+W). |
Ctrl+U | Delete to the start of the input. |
Ctrl+C | Stop the run, else clear the input, else quit. |
Ctrl+D | Quit. |
Option+Delete needs the terminal to send Option as Meta: in Terminal, Settings >
Profiles > Keyboard > Use Option as Meta key. Cmd+Delete doesn't reach the
session in Terminal or Warp; use Ctrl+U.
Click a file or URL in the conversation to open it. Drag over text to select
it: it is copied to the clipboard when you let go. RAE copies with pbcopy
on macOS and wl-copy, xclip or xsel on Linux; otherwise, and over SSH,
it asks the terminal to copy (OSC 52), which most modern terminals do.
The status row under the input shows the run's id, which /resume and
reverse-api-engineer show take. Once the agent has verified
the client, its step lists the run's folder, and with real-time sync on, the
synced copy in ./scripts, as full paths.
When the agent asks a question, its options show under the input: pick one
with the arrow keys, press Space to pick several when the question allows
it, or type your own answer.
Direct subcommands
Outside the session, 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. |
In a terminal, agent, engineer and collector open the session in their
mode and start the run, keeping options such as --headless and
--output-dir for the prompts you type next. agent and engineer print
plain output instead with --json, --json-stream or --no-interactive;
collector does when it runs outside a terminal.
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.
Manual mode is available only inside the interactive session because it opens a visible browser for human-driven capture.