# Context Engineering

Master context engineering for AI agent systems.

- Repository: https://github.com/mrgoonie/claudekit-skills (2229 stars)
- Category: Design
- License: see repository
- Last updated: 2026-04-03
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add mrgoonie/claudekit-skills --skill context-engineering -g -a claude-code -y`
Codex: `npx skills add mrgoonie/claudekit-skills --skill context-engineering -g -a codex -y`
Cursor: `npx skills add mrgoonie/claudekit-skills --skill context-engineering -g -a cursor -y`
Gemini CLI: `npx skills add mrgoonie/claudekit-skills --skill context-engineering -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add mrgoonie/claudekit-skills`

## Description

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Context Engineering

Context engineering curates the smallest high-signal token set for LLM tasks. The goal: maximize reasoning quality while minimizing token usage.

## When to Activate

- Designing/debugging agent systems
- Context limits constrain performance
- Optimizing cost/latency
- Building multi-agent coordination
- Implementing memory systems
- Evaluating agent performance
- Developing LLM-powered pipelines

## Core Principles

1. **Context quality > quantity** - High-signal tokens beat exhaustive content
2. **Attention is finite** - U-shaped curve favors beginning/end positions
3. **Progressive disclosure** - Load information just-in-time
4. **Isolation prevents degradation** - Partition work across sub-agents
5. **Measure before optimizing** - Know your baseline

## Quick Reference

| Topic | When to Use | Reference |
|-------|-------------|-----------|
| **Fundamentals** | Understanding context anatomy, attention mechanics | [context-fundamentals.md](./references/context-fundamentals.md) |
| **Degradation** | Debugging failures, lost-in-middle, poisoning | [context-degradation.md](./references/context-degradation.md) |
| **Optimization** | Compaction, masking, caching, partitioning | [context-optimization.md](./references/context-optimization.md) |
| **Compression** | Long sessions, summarization strategies | [context-compression.md](./references/context-compression.md) |
| **Memory** | Cross-session persistence, knowledge graphs | [memory-systems.md](./references/memory-systems.md) |
| **Multi-Agent** | Coordination patterns, context isolation | [multi-agent-patterns.md](./references/multi-agent-patterns.md) |
| **Evaluation** | Testing agents, LLM-as-Judge, metrics | [evaluation.md](./references/evaluation.md) |
| **Tool Design** | Tool consolidation, description engineering | [tool-design.md](./references/tool-design.md) |
| **Pipelines** | Project development, batch processing | [project-development.md](./references/project-development.md) |

The rest: https://github.com/mrgoonie/claudekit-skills/blob/HEAD/.claude/skills/context-engineering/SKILL.md