RTK Integration

RTK filters and compresses shell command outputs before they reach the LLM context window. Works with any agent/model (Claude, MiniMax, GPT, Gemini, OpenClaw, etc.) — model-agnostic.

Setup

1. Install RTK (auto — run on skill install)

When this skill is installed, immediately run the setup script to install RTK if not already present:

CODEBLOCK0

The script handles installation automatically (Linux/macOS), adds RTK to PATH, and verifies the install.

Manual install if needed:

CODEBLOCK1

2. Initialize hooks (optional, for Claude Code / OpenCode auto-rewriting)

CODEBLOCK2

⚠️ For OpenClaw agents: hooks don't auto-apply. Use rtk <cmd> explicitly (see below).

3. Check token savings

CODEBLOCK3

For config customization, see references/config.md.

Core Rule: Always Use RTK Prefixes

When executing shell commands, always prefer the RTK version over the raw command. RTK adds <10ms overhead and reduces output by 60–90%.

See the full command reference: references/commands.md

Quick reference (most common)

CODEBLOCK4

When NOT to use RTK

• - Interactive commands (ssh, vim, htop) — use directly
• Already-compressed output (jq-piped JSON, single-line results)
• When you need the full raw output for debugging

rtk gain — Token Savings Report

Run rtk gain whenever user asks about token savings. Output example:

CODEBLOCK5