Skills
.Work. You
Rest

omniroute-compression

Community

Cut context tokens by up to 95% automatically.

Software Engineering#prompt optimization#cost reduction#llm routing#context window#token compression#api configuration#mcp accessibility
Authordiegosouzapw
Version1.0.0
Installs0

System Documentation

What problem does it solve?

OmniRoute token compression reduces oversized prompts so your AI sessions fit context windows, run faster, and cost less.

Core Features & Use Cases

  • RTK compression for terminal, build, test, and git output while preserving developer intent with major token savings (about 60–90%).
  • Caveman compression for chat history and human prose to shrink inputs (about 46% input) with configurable intensities for longer sessions.
  • Stacked mode (RTK → Caveman) for mixed coding and discussion workflows to maximize savings (about 78–95%).
  • MCP accessibility-tree filtering for browser/Playwright tool results by collapsing repeated lines and truncating overly verbose text (about 60–80%); configured via thresholds.

Quick Start

Enable maximum savings by setting compression to stacked mode with the pipeline rtK → caveman for your OmniRoute instance.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: omniroute-compression
Download link: https://github.com/diegosouzapw/OmniRoute/archive/main.zip#omniroute-compression

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.