name: "3-Layer Token Compressor — Cut AI API Costs 40-60%" description: "Pre-process prompts through 3 compression layers before sending to paid APIs. Uses a local Ollama model to intelligently compress messages and summarize history. Same quality, fewer tokens, lower bills." author: "@TheShadowRose" version: "1.1.0" tags: ["token-optimization", "cost-reduction", "compression", "api-costs", "prompt-optimization", "budget"] license: "MIT"

3-Layer Token Compressor — Cut AI API Costs 40-60%

Pre-process prompts through 3 compression layers before sending to paid APIs. Uses a free local Ollama model to do the compression work — your paid API only sees the condensed result.

Runtime Requirements

Ollama is required at runtime. The compressor sends prompts to your local model — not to any external API.

What This Skill Sends to the Local Model

This skill sends the following to your local Ollama model:

No data is sent to external APIs. All compression happens locally.

Side Effects

Setup

const TokenCompressor = require('./src/token-compressor');

const compressor = new TokenCompressor({
  ollamaHost: 'localhost',      // default
  ollamaPort: 11434,            // default
  compressionModel: 'llama3.1:8b',  // default — any Ollama model works
  maxUncompressedTurns: 10,     // keep last N turns verbatim
  cacheMaxSize: 100,
  cacheTTL: 3600000             // 1 hour
});

See README.md for full API documentation and usage examples.