RTK Token Optimization
RTK (Rust Token Killer) reduces LLM token consumption by 60-90% by filtering and compressing command outputs. Use when user asks about token savings, token optimization, RTK usage, `rtk gain`, `rtk discover`, or `rtk proxy`. Triggers on mentions of token reduction, RTK commands, or checking command cost.
Best use case
RTK Token Optimization is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
RTK (Rust Token Killer) reduces LLM token consumption by 60-90% by filtering and compressing command outputs. Use when user asks about token savings, token optimization, RTK usage, `rtk gain`, `rtk discover`, or `rtk proxy`. Triggers on mentions of token reduction, RTK commands, or checking command cost.
Teams using RTK Token Optimization should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/rtk-optimization/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How RTK Token Optimization Compares
| Feature / Agent | RTK Token Optimization | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
RTK (Rust Token Killer) reduces LLM token consumption by 60-90% by filtering and compressing command outputs. Use when user asks about token savings, token optimization, RTK usage, `rtk gain`, `rtk discover`, or `rtk proxy`. Triggers on mentions of token reduction, RTK commands, or checking command cost.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# RTK Token Optimization RTK is a high-performance CLI proxy written in Rust. It intercepts commands like `git status`, `npm install`, etc., and rewrites their output to be dramatically more token-efficient. ## Meta Commands (always use rtk directly) ```bash rtk gain # Show token savings analytics rtk gain --history # Show command usage history with savings rtk discover # Analyze Claude Code history for missed opportunities rtk proxy <cmd> # Execute raw command without filtering (for debugging) ``` ### Run a specific command with RTK rewriting ```bash rtk <command> [args...] # Example: rtk git status # Example: rtk npm test ``` ## Installation ```bash # Quick install (Linux/macOS) curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/master/install.sh | sh # macOS/Linux via Homebrew brew install rtk-ai/tap/rtk # Or via cargo (use the explicit Git URL — plain `cargo install rtk` # may install the wrong package due to a name collision) cargo install --git https://github.com/rtk-ai/rtk rtk ``` ## Installation Verification ```bash rtk --version # Should show: rtk X.Y.Z rtk gain # Should work (not "command not found") which rtk # Verify correct binary ``` ⚠️ **Name collision**: If `rtk gain` fails, you may have reachingforthejack/rtk (Rust Type Kit) installed instead. ## Initialization This plugin already installs the Claude Code hook — no `rtk init` needed. - `rtk init --global` patches `~/.claude/settings.json` with a `rtk hook claude` PreToolUse entry — the non-plugin alternative to this plugin. Don't combine them: the hook would fire twice (redundant, not harmful). - `rtk init` (per-project) installs no hook — it only injects RTK instructions into the project `CLAUDE.md` and creates a `.rtk/filters.toml` filter template. ## How the Plugin Works When installed as a Claude Code plugin, RTK's `PreToolUse` hook intercepts every `Bash` tool call and rewrites commands through `rtk rewrite` before execution. This is transparent to Claude — commands run normally but produce compressed, token-efficient output. All rewrite and permission logic lives in the `rtk rewrite` binary (deny rules pass through to Claude Code's native handling; ask rules rewrite but still prompt the user). ## Configuration Config file: `~/.config/rtk/config.toml` (Linux) or `~/Library/Application Support/rtk/config.toml` (macOS). View with `rtk config`, create with `rtk config --create`. ```toml # Exclude commands from auto-rewriting (prefix, subcommand, or ^regex) [hooks] exclude_commands = ["git rebase", "docker exec"] ``` - `RTK_DISABLED=1 <command>` — disable RTK for a single invocation - `RTK_HOOK_AUDIT=1` — enable hook audit logging - Per-project overrides: `.rtk/filters.toml` in the project root ## Requirements - RTK >= 0.23.0 - `jq` (for JSON parsing in the hook script) - If either is missing, the hook warns once on stderr and passes through — safe to install without RTK ## Token Savings Examples | Command | Raw tokens | RTK tokens | Savings | |---------|-----------|------------|---------| | `git status` | ~800 | ~50 | 94% | | `npm install` | ~2000 | ~200 | 90% | | `ls -la` | ~400 | ~80 | 80% |
Related Skills
use-zod
Answer questions about the Zod schema validation library and help build schemas, parsers, refinements, transforms, codecs, and error formatters. Use when developers: (1) ask about Zod APIs like `z.object`, `z.string`, `z.array`, `z.union`, `z.discriminatedUnion`, `parse`, `safeParse`, `z.infer`; (2) define request/response/form schemas in TypeScript; (3) handle `ZodError` or customize error messages; (4) migrate between Zod v3 and v4 (entry-point split, `formatError` → `treeifyError`/`prettifyError`, unified `error` param replacing `message`/`errorMap`). Triggers on: "zod", "z.object", "z.string", "z.array", "z.union", "z.infer", "z.input", "z.output", "ZodError", "$ZodError", "safeParse", "parseAsync", "z.codec", "treeifyError", "prettifyError", "flattenError", "discriminatedUnion", "zod/v4", "zod/v3", "zod/mini", "z.coerce", "superRefine".
workflow
Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow sdk", "queue", "event", "push", "subscribe", or step-based orchestration.
wpds
Use when building UIs leveraging the WordPress Design System (WPDS) and its components, tokens, patterns, etc.
wp-wpcli-and-ops
Use when working with WP-CLI (wp) for WordPress operations: safe search-replace, db export/import, plugin/theme/user/content management, cron, cache flushing, multisite, and scripting/automation with wp-cli.yml.
wp-rest-api
Use when building, extending, or debugging WordPress REST API endpoints/routes: register_rest_route, WP_REST_Controller/controller classes, schema/argument validation, permission_callback/authentication, response shaping, register_rest_field/register_meta, or exposing CPTs/taxonomies via show_in_rest.
wp-project-triage
Use when you need a deterministic inspection of a WordPress repository (plugin/theme/block theme/WP core/Gutenberg/full site) including tooling/tests/version hints, and a structured JSON report to guide workflows and guardrails.
wp-plugin-development
Use when developing WordPress plugins: architecture and hooks, activation/deactivation/uninstall, admin UI and Settings API, data storage, cron/tasks, security (nonces/capabilities/sanitization/escaping), and release packaging.
wp-playground
Use for WordPress Playground workflows: fast disposable WP instances in the browser or locally via @wp-playground/cli (server, run-blueprint, build-snapshot), auto-mounting plugins/themes, switching WP/PHP versions, blueprints, and debugging (Xdebug).
wp-phpstan
Use when configuring, running, or fixing PHPStan static analysis in WordPress projects (plugins/themes/sites): phpstan.neon setup, baselines, WordPress-specific typing, and handling third-party plugin classes.
wp-performance
Use when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers), database/query optimization, autoloaded options, object caching, cron, HTTP API calls, and safe verification.
wp-block-development
Use when developing WordPress (Gutenberg) blocks: block.json metadata, register_block_type(_from_metadata), attributes/serialization, supports, dynamic rendering (render.php/render_callback), deprecations/migrations, viewScript vs viewScriptModule, and @wordpress/scripts/@wordpress/create-block build and test workflows.
wp-abilities-api
Use when working with the WordPress Abilities API (wp_register_ability, wp_register_ability_category, /wp-json/wp-abilities/v1/*, @wordpress/abilities) including defining abilities, categories, meta, REST exposure, and permissions checks for clients.