CLI for managing CloudCruise browser automation workflows and runs. Designed for coding agents to fix and edit CloudCruise workflows.
npm install -g @cloudcruise/clicloudcruise auth login --api-key "sk_..."Install skill files so your coding agent has the full CLI and workflow DSL reference:
cloudcruise install --skills # Claude Code + Cursor
cloudcruise install --skills --target claude # Claude Code only
cloudcruise install --skills --target cursor # Cursor only# List all workflows in your workspace
cloudcruise workflows list
# Get a workflow
cloudcruise workflows get <workflow_id> > workflow.json
# Start a run and wait for completion
cloudcruise run start <workflow_id> --wait
# Start a debug run with snapshots on every node
cloudcruise run start <workflow_id> --wait --debug
# Inspect a failed run
cloudcruise run get <session_id>
# Update a workflow
cloudcruise workflows update <workflow_id> --file workflow.json --version-note "Fixed login selector"After a --debug run, use snapshot commands to diagnose failures:
# Download HTML snapshot, screenshots, and metadata for a node
cloudcruise snapshot fetch <session_id> <node_id>
# Suggest unique XPath selectors for interactive elements
cloudcruise snapshot suggest <session_id> <node_id>
# Test an XPath selector against a snapshot
cloudcruise snapshot test '//button[@id="submit"]' <session_id> <node_id>
# Work with a local HTML file instead of fetching from the API
cloudcruise snapshot suggest --file ./snapshots/page.html
cloudcruise snapshot test '//input[@name="email"]' --file ./snapshots/page.html| Command | Description |
|---|---|
auth login |
Save API key (--profile <name>) |
auth status |
Check authentication (--profile <name>) |
auth logout |
Remove credentials (--profile, --all) |
auth switch <name> |
Set the active profile |
auth profiles |
List all profiles |
workflows list |
List all workflows in your workspace |
workflows get <id> |
Get workflow definition |
workflows update <id> |
Update workflow (new version) |
run start <id> |
Start a run (--wait, --debug) |
run get <id> |
Get run status and results |
run list |
List runs with filters |
run interrupt <id> |
Stop a running session |
run errors <id> |
Error analytics |
run snapshots <id> <node_id> |
Get debug snapshot metadata |
snapshot fetch <session_id> <node_id> |
Download HTML, screenshots, and metadata |
snapshot suggest [session_id] [node_id] |
Suggest unique XPath selectors |
snapshot test <xpath> [session_id] [node_id] |
Test an XPath selector against a snapshot |
utils uuid |
Generate UUIDs for node IDs |
install --skills |
Install skill files for coding agents |
MIT