CLI reference

claude [OPTIONS] [PROMPT]

# Standard interactive session
claude

# Interactive session with a specific model
claude --model claude-opus-4-6

# Print mode: execute a task and exit
claude --print "Explain the code in src/auth.ts"
claude -p "Generate unit tests for utils/date.ts"

# Print mode with JSON format
claude --print --output-format json "List the functions in this file"

# Stream-json mode (for real-time processing)
claude --print --output-format stream-json "Analyze this project"

# Limit the number of turns (agentic mode)
claude --max-turns 5 "Refactor the auth module"

# Restrict available tools
claude --allowedTools "Read,Bash" "Analyze without modifying files"

# Resume the last session
claude --continue

# Resume a session by ID
claude --resume abc123

# Verbose (debug)
claude --verbose "Why is this test failing?"

# Start a session in an isolated worktree
claude --worktree "Implement the payment feature"

# With a specific model
claude -w --model claude-opus-4-5 "Refactor the auth module"

# Minimal startup, no project context at all
claude --bare --print "Generate a UUID v4 in TypeScript"

# In a shell script (starts ~10x faster)
claude --bare --print --output-format json "Parse this JSON" < data.json

# In CI/CD for a one-off task
claude --bare --print --max-turns 1 "Check the syntax of this YAML file" < config.yml

# Pull the last active web session into the terminal
claude --teleport

# If multiple sessions are available, a list is shown for you to pick from

# Use the "code-reviewer" agent defined in .claude/agents/code-reviewer.md
claude --agent code-reviewer "Review the changes in src/api/"

# Security agent for an audit
claude --agent security-auditor --print "Analyze this file" < src/auth.ts

# Technical writing agent
claude --agent tech-writer "Generate documentation for this module"

# Session capped at $0.50
claude --max-budget-usd 0.50 "Analyze and refactor the src/ directory"

# In CI/CD to prevent runaway costs
claude \
  --print \
  --max-budget-usd 1.00 \
  --max-turns 20 \
  "Run the tests and fix any errors"

# Pass a file as input
cat src/auth.ts | claude --print "Add JSDoc comments to this code"

# Chain commands
git diff HEAD~1 | claude --print "Summarize these changes in bullet points"

# Pass a prompt via standard input
echo "Explain the Observer Design Pattern" | claude --print

# Integration in a shell script
RESULT=$(claude --print --output-format json "Analyze this code" < src/main.ts)
echo $RESULT | jq '.content[0].text'

# Read from a file
claude --print "What are the security risks here?" < config/database.yml

# Non-interactive execution with strict control
ANTHROPIC_API_KEY="sk-ant-..." \
  claude \
  --print \
  --max-turns 1 \
  --output-format json \
  "Check code quality in src/"

# Agentic mode with multiple turns
claude \
  --print \
  --max-turns 10 \
  --dangerously-skip-permissions \
  "Run the test suite and fix the errors"

# With environment variables in the config
claude \
  --print \
  --allowedTools "Read,Bash,Write" \
  --system-prompt "You are a security expert. Do not modify any files." \
  "Audit this project"

claude agents

# Example output
# ID          STATUS      BRANCH                    SINCE
# agent-a3f2  running     feat/refactor-auth        5m ago
# agent-b8c1  running     feat/add-tests            2m ago
# agent-d9e4  completed   fix/memory-leak           12m ago

claude config [SUBCOMMAND] [OPTIONS]

# Examples
claude config list

claude config get model
# -> claude-sonnet-4-6

claude config set model claude-opus-4-6

claude config add allowedTools "Bash"
claude config remove allowedTools "Bash"

# With scope (global by default)
claude config --global set model claude-haiku-4-5

claude mcp [SUBCOMMAND] [OPTIONS]

claude mcp add [OPTIONS] <name> -- <command> [args...]

# Add a stdio MCP (local, via npx)
claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/projects

# Add an MCP with project scope
claude mcp add --scope project postgres -- \
  npx -y @modelcontextprotocol/server-postgres postgresql://localhost/mydb

# Add an MCP with an environment variable
claude mcp add github -e GITHUB_TOKEN=ghp_xxx -- \
  npx -y @modelcontextprotocol/server-github

# Add an MCP via SSE transport (HTTP)
claude mcp add --transport sse my-api https://api.example.com/mcp

# Add a Python MCP (via uvx)
claude mcp add my-script -- uvx my-python-package

claude mcp remove [--scope <scope>] <name>

claude mcp remove filesystem
claude mcp remove --scope project postgres

claude mcp list
# Shows: name, status (connected/disconnected), available tools, scope

# Show MCP logs (useful for debugging)
claude mcp logs github

# Follow logs in real time
claude mcp logs -f filesystem

# Show the full configuration for an MCP
claude mcp get github

claude doctor

# Example output
claude doctor
# -> Claude Code v1.x.x (up to date)
# -> Anthropic API reachable
# -> ANTHROPIC_API_KEY valid
# -> MCP filesystem: connected (5 tools)
# x MCP github: connection error (GITHUB_TOKEN missing)
# -> File permissions: OK

# Update Claude Code to the latest version
claude update

# Check version without updating
claude --version

{
  "type": "result",
  "subtype": "success",
  "cost_usd": 0.0023,
  "is_error": false,
  "duration_ms": 1842,
  "num_turns": 1,
  "result": "Response text here...",
  "session_id": "abc123"
}

# Line-by-line processing
claude --print --output-format stream-json "prompt" | while IFS= read -r line; do
  echo "$line" | jq -r 'select(.type == "content_block_delta") | .delta.text // empty'
done