Prompt and Output Compression

Configures command, prose and stacked compression, reducing token use by 60 to 90 percent.

Install

npx skills add cheaper-inference/OmniRoute --skill omni-compression -g -a claude-code -y

Press to copy:C Claude CodeX CodexU CursorA Ask your agent

Repository: cheaper-inference/OmniRoute83.6k
Category: AI and agents
Updated: 4d ago
License: MIT
Context cost: Mediumabout 1,555 tokens
Runs scripts: No, instructions only

What it does

Configure RTK (command output), Caveman (prose), and stacked compression modes. Manage language packs, custom rules, and test prompt compression reducing tokens by 60, 90%.

Overview

Configure RTK (command output), Caveman (prose), and stacked compression modes. Manage language packs, custom rules, and test prompt compression reducing tokens by 60, 90%.

Authentication

All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.

Endpoints

POST /api/compression/preview

Preview compression for a message payload

curl -X POST http://localhost:20128/api/compression/preview \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/compression/language-packs

List Caveman compression language packs

curl http://localhost:20128/api/compression/language-packs \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

GET /api/compression/rules

List Caveman compression rule metadata

curl http://localhost:20128/api/compression/rules \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

POST /api/compression/compare

POST compression › compare

curl -X POST http://localhost:20128/api/compression/compare \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{}'

POST /api/compression/compare/verify

POST compression › compare › verify

curl -X POST http://localhost:20128/api/compression/compare/verify \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/compression/engines

GET compression › engines

curl http://localhost:20128/api/compression/engines \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

POST /api/compression/retrieve

POST compression › retrieve

Read the whole SKILL.md on GitHub