oktk

name	oktk
version	2.4.0
description	LLM Token Optimizer - Reduce AI API costs by 60-90%. Compresses CLI outputs (git, docker, kubectl) before sending to GPT-4/Claude. AI auto-learning included. By Buba Draugelis 🇱🇹
author	Buba Draugelis
license	MIT
homepage	https://github.com/satnamra/openclaw-workspace/tree/main/skills/oktk
tags	["optimization","tokens","cost-savings","cli","filtering","llm"]
requires	{"bins":["node"]}
openclaw	{"emoji":"🔪","category":"optimization"}

oktk - CLI Output Compressor for LLMs

The Problem

When you run commands through an AI assistant, the full output goes into the LLM context:

$ git status
# Returns 60+ lines, ~800 tokens
# Your AI reads ALL of it, you pay for ALL of it

Every token costs money. Verbose outputs waste your context window.

The Solution

oktk sits between your commands and the LLM, compressing outputs intelligently:

┌──────────┐     ┌──────────┐     ┌──────────┐
│ Command  │ ──► │   oktk   │ ──► │   LLM    │
│ (800 tk) │     │ compress │     │ (80 tk)  │
└──────────┘     └──────────┘     └──────────┘
                      │
                 90% SAVED

When Does It Work?

Automatically when you run supported commands through OpenClaw:

Command	What oktk does	Savings
git status	Shows only: branch, ahead/behind, file counts	90%
git log	One line per commit: hash + message + author	85%
git diff	Summary: X files, +Y/-Z lines, file list	80%
npm test	Just: ✅ passed or ❌ failed + count	98%
ls -la	Groups by type, shows sizes, skips details	83%
curl	Status code + key headers + truncated body	97%
grep	Match count + first N matches	80%
docker ps	Container list: name, image, status	85%
docker logs	Last N lines + error count	90%