Skip to main content

CLI Flags Reference

Complete documentation of all command-line flags and options for the Claude Code Templates CLI.

Component Installation Flags

—agent

string
Install specific agent component (supports comma-separated values)
Usage:
Format: Direct name or category/name Examples:
  • frontend-developer
  • development-team/react-specialist
  • security-team/penetration-tester

—command

string
Install specific command component (supports comma-separated values)
Usage:
Format: Direct name or category/name

—mcp

string
Install specific MCP component (supports comma-separated values)
Usage:
Available MCPs:
  • web-fetch
  • filesystem-access
  • github-integration
  • memory-integration
  • mysql-integration
  • postgresql-integration
  • deepgraph-react
  • deepgraph-typescript
  • deepgraph-vue
  • deepgraph-nextjs

—setting

string
Install specific setting component (supports comma-separated values)
Usage:
Categories:
  • permissions/ - Permission configurations
  • model/ - Model selection settings
  • telemetry/ - Telemetry controls
  • retention/ - Data retention policies
  • security/ - Security settings
  • statusline/ - Statusline configurations

—hook

string
Install specific hook component (supports comma-separated values)
Usage:
Hook Types:
  • PreToolUse hooks
  • PostToolUse hooks
  • Stop hooks
  • Notification hooks

—skill

string
Install specific skill component (supports comma-separated values)
Usage:

Template and Configuration Flags

—template

string
Specify template (e.g., common, javascript-typescript, python, ruby)
Usage:
Available Templates:
  • common - Universal configuration
  • javascript-typescript - Node.js, React, Vue, Next.js
  • python - Django, Flask, FastAPI
  • ruby - Rails, Sinatra
  • go - Go projects
  • rust - Rust/Cargo projects

—language

string
Specify programming language (deprecated, use —template)
Usage:
Deprecated: Use --template instead.

—framework

string
Specify framework (deprecated, use —template)
Usage:
Deprecated: Use --template instead.

—directory

string
Target directory (default: current directory)
Usage:
Alias: -d

Execution Flags

—yes

boolean
Skip prompts and use defaults
Usage:
Behavior: Uses detected project type and default options. Alias: -y

—dry-run

boolean
Show what would be copied without actually copying
Usage:
Behavior: Displays files that would be created/modified without making changes.

—verbose

boolean
Enable verbose logging for debugging and development
Usage:
Behavior: Outputs detailed debugging information.

Analytics and Dashboard Flags

—analytics

boolean
Launch real-time Claude Code analytics dashboard
Usage:
Port: 3333 URL: http://localhost:3333

—chats

boolean
Launch mobile-first chats interface (AI-optimized for mobile devices)
Usage:

—agents

boolean
Launch Claude Code agents dashboard (opens directly to conversations)
Usage:

—chats-mobile

boolean
Launch mobile-first chats interface (same as —chats)
Usage:

—plugins

boolean
Launch Plugin Dashboard to view marketplaces, installed plugins, and permissions
Usage:

—skills-manager

boolean
Launch Skills Dashboard to view and explore installed Claude Code Skills
Usage:

—teams

boolean
Launch Agent Teams Dashboard to review multi-agent collaboration sessions
Usage:

—2025

boolean
Launch 2025 Year in Review dashboard (showcase your Claude Code usage statistics)
Usage:

—tunnel

boolean
Enable Cloudflare Tunnel for remote access (use with —analytics, —chats, or —2025)
Usage:
Behavior: Creates public URL for remote access. Restriction: Only works with dashboard flags.

Statistics and Analysis Flags

—command-stats

boolean
Analyze existing Claude Code commands and offer optimization
Usage:
Alias: --commands-stats

—hook-stats

boolean
Analyze existing automation hooks and offer optimization
Usage:
Alias: --hooks-stats

—mcp-stats

boolean
Analyze existing MCP server configurations and offer optimization
Usage:
Alias: --mcps-stats

Health and Verification Flags

—health-check

boolean
Run comprehensive health check to verify Claude Code setup
Usage:
Aliases: --health, --check, --verify

Global Agent Flags

—create-agent

string
Create a global agent accessible from anywhere (e.g., customer-support)
Usage:
Installation: Creates executable in /usr/local/bin/ or ~/.claude-code-templates/bin/

—list-agents

boolean
List all installed global agents
Usage:

—remove-agent

string
Remove a global agent
Usage:

—update-agent

string
Update a global agent to the latest version
Usage:

Sandbox and Execution Flags

—sandbox

string
Execute Claude Code in isolated sandbox environment (e.g., e2b)
Usage:
Supported Providers:
  • e2b - E2B sandbox
  • docker - Docker containers
  • cloudflare - Cloudflare Workers

—prompt

string
Execute the provided prompt in Claude Code after installation or in sandbox
Usage:

—e2b-api-key

string
E2B API key for sandbox execution (alternative to environment variable)
Usage:
Alternative: Set E2B_API_KEY environment variable.

—anthropic-api-key

string
Anthropic API key for Claude Code (alternative to environment variable)
Usage:
Alternative: Set ANTHROPIC_API_KEY environment variable.

Workflow Flags

—workflow

string
Install workflow from hash (#hash) OR workflow YAML (base64 encoded) when used with component flags
Usage:
Behavior:
  • Standalone: Installs workflow from hash
  • With components: Treats as YAML workflow definition

Session Management Flags

—clone-session

string
Download and import a shared Claude Code session from URL
Usage:
Behavior: Downloads session data and imports into local Claude Code.

—studio

boolean
Launch Claude Code Studio interface for local and cloud execution
Usage:

Version and Help Flags

—version

boolean
Display version information
Usage:
Alias: -v

—help

boolean
Display help information
Usage:
Alias: -h

Flag Combinations

Common Combinations

Install multiple components:
Analytics with remote access:
Install and execute prompt:
Sandbox execution:
Dry run installation:
Directory-specific installation:
Verbose debugging:

Invalid Combinations

Tunnel without dashboard:
Multiple exclusive flags:

Flag Priority

When multiple flags are present:
  1. Sandbox execution - Runs first if present
  2. Component installation - If no sandbox
  3. Dashboard launch - If no components
  4. Health check - If specified
  5. Interactive menu - If no flags

Environment Variables vs Flags

Some flags have environment variable equivalents: Flags take precedence over environment variables.

Default Values

Next Steps