Lean Ctx
Skill Verified ActiveContext Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.
To significantly reduce LLM token consumption and improve the efficiency of AI coding agents by intelligently compressing file content and shell command outputs.
Features
- Context compression for LLM interactions
- Advanced file reading modes
- Shell command output compression
- Integration with AI agents via CLI/MCP
- Local-first operation with opt-in telemetry
Use Cases
- When working with large codebases where AI agents need to read many files.
- When AI agents frequently execute verbose shell commands (e.g., git, build logs).
- To reduce LLM API costs by minimizing token usage.
- For long-running AI agent tasks requiring efficient context management.
Non-Goals
- Processing personal data without user consent.
- Executing arbitrary remote code as instructions.
- Replacing core development tools, but rather enhancing their output for LLMs.
Installation
npx skills add yvgude/lean-ctxRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
VerifiedTrust Signals
Similar Extensions
Manus
100Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.
Risk Management
100Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on "risk", "drawdown", "tilt", "position size", "lot size", "confidence", "revenge trading", "overtrading", "discipline".
Setup Gbrain
100Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. One command from zero to "gbrain is running, and this agent can call it." Use when: "setup gbrain", "connect gbrain", "start gbrain", "install gbrain", "configure gbrain for this machine". (gstack)
Skill Creator
100Guide for creating effective skills
Metal
100Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.
Pathfinder
100Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to "find the ideal path," unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.