Skip to main content

CLI Overview

Open source at https://github.com/CloudCruise/cloudcruise-cli. Report bugs via GitHub issues or Discord. The CloudCruise CLI provides a command-line interface for managing workflows and runs. It’s designed for coding agents to diagnose, fix, and verify workflow failures — but works just as well for manual use.

Installation

npm install -g @cloudcruise/cli
Or run without installing:
npx @cloudcruise/cli --help

Setup

Get your API key at CloudCruise Settings.
cloudcruise auth login --api-key "sk_..."
Or set the CLOUDCRUISE_API_KEY environment variable. All commands also accept --api-key and --base-url overrides.

Coding Agent Integration

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
This copies a CLI usage reference and a complete workflow DSL reference (all node types, XPath best practices, variables, JSONata, error classification) into your project where the agent can discover them.

Quick Start

cloudcruise workflows get <workflow_id> > workflow.json

cloudcruise run start <workflow_id> --wait

cloudcruise run get <session_id>

cloudcruise workflows update <workflow_id> --file workflow.json --version-note "Fixed selector"

Error-Fix-Verify Loop

You can use the CLI to fix existing workflow errors. Here’s how a coding agent could sequence CLI commands:
# 1. Diagnose — inspect the failed run
cloudcruise run get <session_id>
cloudcruise workflows get <workflow_id> > workflow.json

# 2. Reproduce — re-run with debug snapshots
cloudcruise run start <workflow_id> --input '{}' --wait --debug

# 3. Inspect — examine both the screenshot and the HTML snapshot
cloudcruise run snapshots <session_id> <node_id>

# 4. Fix — edit the workflow, then push the update
cloudcruise workflows update <workflow_id> --file workflow.json --version-note "Fixed XPath"

# 5. Verify — confirm the fix
cloudcruise run start <workflow_id> --input '{}' --wait
The --debug flag forces every node to capture a page snapshot, which is essential for diagnosing selector issues. Without it, failed runs often lack snapshots.

Commands

CommandDescription
auth login --api-key "sk_..."Save API key to ~/.cloudcruise/config.json
auth statusCheck authentication status
auth logoutRemove saved credentials
workflows get <id>Get workflow definition with nodes and edges
workflows update <id> --file <path>Update workflow (creates a new version)
run start <id>Start a run (returns session_id)
run start <id> --waitStart and stream events until completion
run start <id> --wait --debugStart with debug snapshots on every node
run get <id>Get run status, errors, screenshots, output
run listList runs (supports --workflow, --status, --limit)
run interrupt <id>Stop a running session
run errors <id> --since 24hError analytics for a workflow
run snapshots <id> <node_id>Debug snapshots for a specific node
utils uuidGenerate a random UUID for new node IDs
install --skillsInstall skill files for coding agents

Next Steps

  • Explore the Run API for detailed execution options
  • Learn about Vault API for secure credential management
  • Check out Workflow API to manage your workflows
  • Set up Webhooks for event notifications