docs/guide/getting-started/quick-start.md
This guide walks you through your first RTK commands after installation.
RTK is installed and verified:
rtk --version # rtk x.y.z
rtk gain # shows token savings dashboard
If not, see Installation.
# For Claude Code (global — applies to all projects)
rtk init --global
# For a single project only
cd /your/project && rtk init
This installs the hook that automatically rewrites commands. Restart your AI assistant after this step.
--dry-runTo see exactly what init would change before it touches anything, add --dry-run:
rtk init --global --dry-run
Every would-be file create/update/patch is printed with a [dry-run] would ... prefix, then a [dry-run] Nothing written. footer. Nothing on disk is modified, no settings.json is patched, and the telemetry consent prompt is skipped. Combine with -v to also print the full content RTK would write:
rtk init --global --dry-run -v
--dry-run works for every init flavour (--agent cursor, --gemini, --codex, --copilot, --uninstall, ...). It cannot be combined with --show.
Once the hook is installed, nothing changes in how you work. Your AI assistant runs commands as usual — the hook intercepts them transparently and rewrites them before execution.
For example, when Claude Code runs cargo test, the hook rewrites it to rtk cargo test before it executes. The LLM receives filtered output with only the failures — not 500 lines of passing tests. You never see or type rtk.
RTK covers all major ecosystems — Git, Cargo/Rust, JavaScript, Python, Go, Ruby, .NET, Docker/Kubernetes, and more. See What RTK Optimizes for the full list.
After a few commands, see how much was saved:
rtk gain
Total commands : 12
Input tokens : 45,230
Output tokens : 4,890
Saved : 40,340 (89.2%)
Commands RTK doesn't recognize run through passthrough — output is unchanged, usage is tracked:
rtk proxy make install