rtk-token-killer

rtk-token-killer is a skill for Claude Code, Codex from S3YED/appie-kit. It costs 63 tokens per session (520 once invoked), scanned C, original, MIT.

A Rust command-line tool that filters and summarises developer command output before it reaches an AI agent's context. Rust is the programming language used to build the tool.

In plain words
What is it for?
Getting compact listings, file reads, searches, Git output, test failures, diffs, JSON, dependency information, and summaries from commands such as Docker, GitHub, and database tools.
Why use it?
It reduces repetitive terminal output so the agent can focus on errors, warnings, and the most relevant results.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/s3yed/appie-kit/rtk-token-killer
Any agent
npx skills add S3YED/appie-kit --skill rtk-token-killer
Clone the repo
git clone --depth 1 https://github.com/S3YED/appie-kit

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for rtk-token-killer

README.md
[![agentmods](https://agentmods.dev/badge/skills/s3yed/appie-kit/rtk-token-killer.svg)](https://agentmods.dev/skills/s3yed/appie-kit/rtk-token-killer)
Your own site
<a href="https://agentmods.dev/skills/s3yed/appie-kit/rtk-token-killer"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/rtk-token-killer.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 520 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.00520
Opus 5 $0.00032 $0.00260
Sonnet 5 $0.00013 $0.00104
Haiku 4.5 $0.00006 $0.00052

Measured 5d ago against content hash 1ea96edb69ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade C, and why

rtk-token-killer scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh # Linux/macOS -> ~/.local/bin

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh # Linux/macOS -> ~/.local/bin
skills/automation/rtk-token-killer/SKILL.md · 41 lines

What it actually says

rtk — Rust Token Killer (token discipline)

A single Rust binary that filters and summarises command output before it hits the LLM context. ~80% fewer tokens on common dev commands, <10ms overhead, 100+ commands. Apache-2.0. Directly serves token-reduction doctrine.

Install

brew install rtk                                  # macOS
curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh   # Linux/macOS -> ~/.local/bin
rtk --version

Use it (prefix the command)

rtk ls            rtk tree           rtk read <file>        # token-optimized read/list
rtk git status    rtk git diff       rtk git log            # compact git
rtk grep <pat>    rtk find -name x   rtk diff a b           # condensed search/diff
rtk test          rtk err <cmd>                             # tests: only failures; cmd: only errors/warnings
rtk gh ...        rtk docker ...     rtk psql ...           # compact gh/docker/db
rtk json <file>   rtk env            rtk deps               # compact json/env/deps

rtk smart gives a 2-line technical summary of output.

rtk init -g       # installs a global hook so common commands route through rtk automatically

Without the hook, just prefix manually with rtk.

When to use

  • DEFAULT for any read-only inspect command whose raw output is large (file reads, listings, grep, git status/diff/log, test runs, logs, docker ps, json).
  • Pairs with token discipline: reference-over-inline, deltas-over-dumps — rtk enforces it at the shell layer.
  • Not for commands whose full output you genuinely need verbatim (then run the raw command).

Verified

Tested on macOS (rtk 0.42.4): rtk git status, rtk ls return compact output correctly.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 41 lines · 63 tokens per session scan C 1ea96edb69ae

Subscribe to this mod's changes

rtk-token-killer is a skill published in the GitHub repository S3YED/appie-kit (7 stars, last pushed 10d ago), licensed MIT. It adds 63 tokens to every session and 520 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

seo-geo-optimizer

Comprehensive SEO/GEO/AEO analysis toolkit for optimizing content visibility across traditional search engines (Google, Bing), AI platforms (ChatGPT, Perplexity, Claude, Gemini, Grokipedia), answer engines (Google AI Overviews, Bing Copilot, featured snippets), voice assistants (Google Assistant, Siri, Alexa), and…

ViryaZheng/recomby-geo · 121 tokens

internal-linking-optimizer

Use when improving internal link structure, anchor text, orphan pages, crawl depth, site architecture, or link equity flow. 内链优化/站内架构.

ViryaZheng/recomby-geo · 38 tokens

geo-review-html

Render an interactive, self-contained HTML companion for a GEO content brief (04-content-brief) or a publish-ready draft (05-production), so a NON-technical client reviewer (founder, organizer staff, the domain expert filling slots) can fill REQUIRED-FILL slots, leave section-level comments, and approve/return work in…

ViryaZheng/recomby-geo · 140 tokens

geo-pipeline

Entry point + orchestrator for the recomby-geo GEO (Generative Engine Optimization) workflow on OpenAI Codex CLI. Use when the user wants to run any stage of the GEO pipeline on a client folder — intake, visibility audit, content-gap analysis, content brief, draft production, distribution, or monthly re-audit — or…

ViryaZheng/recomby-geo · 169 tokens

follow-up-writer

Use when drafting a post-event follow-up message to someone met at a conference.

staruhub/CrewClaw · 21 tokens

schedule

Create, list, remove or inspect this bot's scheduled work — recurring jobs ("every morning at 7 tell me X", "every weekday at 9 post the standup") and one-shot follow-ups ("check back in 20 minutes", "watch that deploy until it lands", "remind me on Friday"). Use whenever something must happen on a schedule…

xrgarcia/slashbin-ai-team · 92 tokens