context-engineering

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

<INSTRUCTIONS>Step-by-step procedures</INSTRUCTIONS>

plugins/ai-ml-tools/skills/ai-multimodal

plugins/ai-ml-tools/skills/context-engineering

plugins/ai-ml-tools/skills/google-adk-python

plugins/backend-tools/skills/backend-development

plugins/backend-tools/skills/better-auth

Audit 0.4.1 · source sha d655ab03f566 · 26 Oct 2026Report an issue or request a re-scan

• Publishermrgoonie GitHub userOwner of the repository this skill is read from
• Source foldermrgoonie/claudekit-skills/.claude/skills/context-engineeringThe exact folder we audited
• LicenceNot declaredAs the repository states it
• Commit pinned for this verdictd655ab03f566A new audit runs when the source changes
• Repository statusNot archivedLast push 206 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its 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…

---
name: context-engineering
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.
version: 1.0.0
---

# 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) |

## Key Metrics

- **Token utilization**: Warning at 70%, trigger optimization at 80%
- **Token variance**: Explains 80% of agent performance variance
- **Multi-agent cost**: ~15x single agent baseline
- **Compaction target**: 50-70% reduction, <5% quality loss
- **Cache hit target**: 70%+ for stable workloads

## Four-Bucket Strategy

1. **Write**: Save context externally (scratchpads, files)
2. **Select**: Pull only relevant context (retrieval, filtering)
3. **Compress**: Reduce tokens while preserving info (summarization)
4. **Isolate**: Split across sub-agents (partitioning)

## Anti-Patterns

- Exhaustive context over curated context
- Critical info in middle positions
- No compaction triggers before limits
- Single agent for parallelizable tasks
- Tools without clear descriptions

## Guidelines

1. Place critical info at beginning/end of context
2. Implement compaction at 70-80% utilization
3. Use sub-agents for context isolation, not role-play
4. Design tools with 4-question framework (what, when, inputs, returns)
5. Optimize for tokens-per-task, not tokens-per-request
6. Validate with probe-based evaluation
7. Monitor KV-cache hit rates in production
8. Start minimal, add complexity only when proven necessary

## Scripts

- [context_analyzer.py](./scripts/context_analyzer.py) - Context health analysis, degradation detection
- [compression_evaluator.py](./scripts/compression_evaluator.py) - Compression quality evaluation

Excerpt, first 4,034 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/mrgoonie/claudekit-skills
git -C claudekit-skills checkout d655ab03f566

Works in

1. 2026-10-26
   ✕BLOCK D 69 / 100

   first audit · source d655ab03f566

Questions about context-engineering

• github.com/mrgoonie/claudekit-skills/tree/main/.claude/skills/co — the audited source at commit d655ab03f566 and every finding aboveObserved · 26 Oct 2026

Spotted something wrong? Report a correction · Methodology