Discover CLI Flags Quickly with claude --help
When you can't remember a flag name, claude --help is faster than searching the docs. The output is structured by category and includes descriptions, types, and defaults.
# Full flag reference
claude --help
# Shorter alias
claude -h
The output lists every available flag with its type and default value — --model, --output-format, --max-turns, --debug, and all the rest. Flags are grouped logically so you can scan quickly.
For subcommands, pass --help to the specific command:
# Config subcommand options
claude config --help
# MCP subcommand options
claude mcp --help
A few patterns worth knowing:
# Check your current version before filing a bug report
claude --version
# Validate your setup is healthy
claude doctor
# Run the doctor check in CI to catch misconfigured environments early
claude doctor && echo "Claude Code environment OK"
The doctor command checks your Node version, API key, and environment for common issues. Running both --version and doctor together is the fastest first step when something behaves unexpectedly.
When in doubt, claude --help — it's always accurate and always in sync with your installed version.
Log in to leave a comment.
When Claude writes error messages, button labels, validation text, or onboarding flows, it defaults to generic developer-speak. Add a "Users" section to your CLAUDE.md describing who your actual users are — their technical level, industry jargon, and what they care about — so Claude writes copy that makes sense to THEM, not to developers.
Use the --agent flag with custom markdown files in .claude/agents/ to launch purpose-built Claude sessions with restricted tools and scoped system prompts.
Every project has traps — the billing module that silently fails if you forget to queue the job, the legacy table with column names that don't match the model, the config value that must be set before tests run. Document these gotchas in your CLAUDE.md so Claude avoids the same mistakes your team spent days debugging.