llm-transpile

Saved declaration

{}

Saved declaration

{
  "name": "llm-transpile",
  "source": {
    "sha": "261654dc3ae771060379c43ea794b676b97eeb82",
    "url": "https://github.com/epicsagas/llm-transpile.git",
    "source": "url"
  },
  "homepage": "https://github.com/epicsagas/plugins",
  "description": "Token-optimized document reader — silently compresses .md, .html, and .txt files on every Read, cutting context usage by ~30% with zero workflow change. Adaptive 4-stage compression auto-escalates as token budget fills."
}

Hooks

"./.claude-plugin/hooks.json"

Saved declaration

{
  "name": "llm-transpile",
  "hooks": "./.claude-plugin/hooks.json",
  "author": {
    "url": "https://github.com/epicsagas",
    "name": "epicsagas"
  },
  "license": "Apache-2.0",
  "version": "0.4.1",
  "homepage": "https://github.com/epicsagas/llm-transpile",
  "keywords": [
    "transpile",
    "compression",
    "llm",
    "context",
    "token"
  ],
  "interface": {
    "category": "Performance",
    "websiteURL": "https://github.com/epicsagas/llm-transpile",
    "displayName": "LLM Transpile",
    "capabilities": [
      "Read"
    ],
    "developerName": "epicsagas",
    "longDescription": "Silently compresses .md, .html, and .txt files on Read via PostToolUse hook, cutting context usage by ~27% on Markdown (cl100k-measured) with zero workflow change.",
    "shortDescription": "Token-optimized document reader — ~27% Markdown compression (genuine), up to 90% on HTML markup stripping (cl100k-measured)."
  },
  "repository": "https://github.com/epicsagas/llm-transpile",
  "description": "Auto-compress .md, .html, .txt files read by Claude Code via PostToolUse hook."
}