Rtk
Rtk helps you set up and troubleshoot Rust Token Killer, a CLI tool that rewrites shell commands into token-efficient versions for AI agents. Install via Homebrew, script, or Cargo, then initialize RTK for your specific agent—Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, or OpenCode. Use direct `rtk` commands like `rtk git status` or `rtk read` when automatic hooks aren't available.
Rtk installs and configures Rust Token Killer to reduce shell-command token output for AI coding agents.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-28
Rtk installs and configures Rust Token Killer to reduce shell-command token output for AI coding agents. Rtk helps you set up and troubleshoot Rust Token Killer, a CLI tool that rewrites shell commands into token-efficient versions for AI agents. Install via Homebrew, script, or Cargo, then initialize RTK for your specific agent—Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, or OpenCode. Use direct `rtk` commands like `rtk git status` or `rtk read` when automatic hooks aren't available.
Use it when
- Rtk requires initialization for your specific agent—Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, or OpenCode.
- Rtk can be installed via Homebrew, script, or Cargo depending on your system.
Install
akillness/jeo-skills/rtk · repository language: TypeScript
generated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is rtk?
Rtk is Rust Token Killer, a CLI tool that rewrites shell commands into token-efficient versions for AI agents. Rtk helps you set up and troubleshoot the tool, which works with Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, and OpenCode. It reduces token usage by optimizing command output for AI processing.
How to use rtk with my agent?
Rtk requires initialization for your specific agent—Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, or OpenCode. After installation, run setup commands to configure Rtk for your chosen agent. You can then use direct `rtk` commands like `rtk git status` or `rtk read` when automatic hooks aren't available, or rely on automatic integration once configured.
How do I install and set up rtk?
Rtk can be installed via Homebrew, script, or Cargo depending on your system. After installation, initialize Rtk for your specific agent using setup commands. Rtk setup and configuration help you connect the tool to your chosen AI agent platform, enabling automatic token-efficient command rewriting.
What are rtk's main features?
Rtk's main features include token-efficient command rewriting, support for multiple AI agents (Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, OpenCode), automatic hooks for seamless integration, and direct command execution via `rtk` commands when needed. Rtk optimizes shell output to reduce token consumption in AI workflows.
Can I use rtk without automatic hooks?
Yes, Rtk supports direct command execution when automatic hooks aren't available. Use commands like `rtk git status` or `rtk read` to manually invoke token-efficient rewrites. This flexibility allows Rtk to work in environments where automatic integration isn't possible or preferred.
Which agents does rtk support?
Rtk supports Claude Code, Codex, Gemini CLI, Cursor, Copilot, Windsurf, Cline, and OpenCode. After installing Rtk, you initialize it for your specific agent, and it then optimizes command output for that platform's token efficiency requirements.
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Find and learn about the Rtk skill”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
RTK Optimizer detects high-verbosity shell commands and suggests RTK wrappers to dramatically reduce token usage—achieving up to 92% savings on git log, 90% on cargo test and pytest, and similar gains across build tools and package managers. The skill automatically proposes optimizations when it spots commands like git diff, find, or test frameworks, then executes the wrapped version to preserve context window space.
rtk-tdd enforces the red-green-refactor cycle for Rust development, automatically guiding you through failing tests, minimal implementations, and refactoring phases. It provides Rust-idiomatic testing patterns using anyhow/thiserror, cfg(test) modules, and Arrange-Act-Assert workflows, with pre-commit gates ensuring code quality.
add-rtk deploys rtk, a CLI proxy that compresses output from common development commands (git, cargo, pytest, docker, kubectl, and others), directly into Claude Code agent containers. The skill automates binary installation, container mounting, and hook configuration so every Bash call routes through rtk transparently, delivering 60–90% token savings without manual intervention.
Ship orchestrates the full release cycle for RTK projects: quality verification, semantic versioning, changelog generation, git tagging, and remote push to activate CI/CD pipelines. Follow pre-release checklists, execute the multi-step workflow, and verify post-release artifacts automatically.
tdd-rust guides you through test-driven filter implementation for RTK using the Red-Green-Refactor cycle. Start with real command output fixtures, write failing tests that verify both output format and ≥60% token reduction, then implement the minimum code to pass. Lock output format with snapshot tests and integrate into your CLI.
This skill provides systematic performance analysis for the RTK CLI tool, measuring startup time against a <10ms target, memory usage under 5MB, and token savings between 60–90%. It includes baseline capture, regression detection with flamegraph profiling, and common optimization techniques like LazyLock initialization and zero-copy string processing.
More skills design-patterns (Apache-2.0)