Cli Reference

Complete reference for every Claude Code CLI flag and pattern you'll need. Covers the basics like interactive vs headless mode, but the real value is in the headless agent patterns. If you're spawning agents in CI/CD or automation, the session control and permission flags here are critical to avoid hangs. Shows exactly which flags to combine for headless execution, how to define custom subagents inline with JSON, and the streaming output formats for real-time monitoring. The examples are practical: piping logs for analysis, multi-turn sessions with resume, structured output validation. Keep this open when you're writing scripts that call Claude programmatically.

skills.sh installs: 491
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill cli-reference --agent claude-code

Installs into .claude/skills of the current project.

Files

CLI Reference

Complete reference for Claude Code command-line interface.

When to Use

"What CLI flags are available?"
"How do I use headless mode?"
"Claude in automation/CI/CD"
"Output format options"
"System prompt via CLI"
"How do I spawn agents properly?"

Core Commands

Command	Description	Example
`claude`	Start interactive REPL	`claude`
`claude "query"`	REPL with initial prompt	`claude "explain this project"`
`claude -p "query"`	Headless mode (SDK)	`claude -p "explain function"`
`cat file \| claude -p`	Process piped content	`cat logs.txt \| claude -p "explain"`
`claude -c`	Continue most recent	`claude -c`
`claude -c -p "query"`	Continue via SDK	`claude -c -p "check types"`
`claude -r "id" "query"`	Resume session	`claude -r "auth" "finish PR"`
`claude update`	Update version	`claude update`
`claude mcp`	Configure MCP servers	See MCP docs