Skills
.Work. You
Rest

lean-ctx

Community

Compress LLM context to accelerate AI coding.

Software Engineering#token-savings#ai-coding#context-compression#cross-session-memory#lean-ctx#shell-hook
Authoryvgude
Version1.0.0
Installs0

System Documentation

What problem does it solve?

LeanCTX tackles the issue of bloated LLM prompts and repetitive context by compressing CLI output and providing a persistent cross-session memory layer for developers.

Core Features & Use Cases

  • Shell Hook: transparently compresses CLI output before it reaches the AI, reducing noise.
  • Context Server: 24 intelligent tools for cached reads, delta updates, dependency graphs, and task-aware relevance scoring.
  • CCP & CEP: cross-session memory with LITM-aware positioning to maintain context across chats and projects and optimize attention.
  • Language support: tree-sitter parsing for 14 languages to extract meaningful APIs and structures.
  • Integration: simple agent hooks to connect with Claude Code, Cursor, Gemini CLI, Codex, Windsurf, and more.

Quick Start

Install LeanCTX and run lean-ctx -c <command> to compress verbose output and preserve context for AI-assisted coding.

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: lean-ctx
Download link: https://github.com/yvgude/lean-ctx/archive/main.zip#lean-ctx

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.