Optimization Articles
Browse 194 articles about Optimization.
How to Use the /compact Command in Claude Code to Prevent Context Rot
Running /compact at 60% context capacity—not 95%—keeps your Claude Code sessions sharp. Learn when and how to compact with specific preservation instructions.
How Context Compounding Works in Claude Code (And How to Stop It)
Every Claude Code message re-reads your entire conversation history. Learn why token costs compound exponentially and how to manage it effectively.
Claude Code MCP Servers and Token Overhead: What You Need to Know
Each connected MCP server loads tool definitions into every message, costing up to 18,000 tokens per turn. Here's how to audit and reduce that overhead.
18 Claude Code Token Management Hacks to Extend Your Session
Stop burning through your Claude Code session limit. These 18 token management techniques can double or triple your effective usage per session.
Claude Code Skills: Why Code Scripts Outperform Markdown Instructions for Agent Tasks
Most Claude Code skills rely too heavily on markdown. Using executable scripts instead reduces tokens by up to 90% and makes agent tasks more reliable.
What Is Claude Code's claude.md File? The Permanent Instruction Manual for Your AI Agent
The claude.md file is loaded into every Claude Code session. Learn what to put in it, how to structure it, and why most users are using it wrong.
What Is Google TurboQuant? The KV Cache Compression That Crashed Memory Chip Stocks
Google's TurboQuant algorithm compresses AI memory to 3 bits with zero accuracy loss, delivering 8x speed and 6x memory reduction on H100 GPUs.
What Is the Context Window in Claude Code? How to Manage It for Consistent Results
Claude's context window is its short-term memory with a hard limit. When it fills with stale data, quality drops. Here's how to keep it fresh and focused.
How to Optimize Web Scraping Skills for AI Agents: 6 Token-Saving Techniques
Learn how to reduce token usage by 90% in web scraping AI agent skills by filtering HTML, hardcoding selectors, batching requests, and using incremental runs.
What Is the Context Window Limit in Claude Code? How to Manage It for Better Results
Claude Code's context window is its short-term memory. When it fills with stale content, quality drops. Here's how to keep it fresh and get consistent outputs.
Claude Code Effort Levels Explained: When to Use Low, Medium, High, and Max
Claude Code's effort level setting controls how much reasoning the model applies. Learn when to use each level to balance quality and token cost.
What Is Context Rot in Claude Code Skills? How Bloated Skill Files Degrade Agent Performance
Context rot happens when skill.md files grow too large and flood the context window. Learn how to keep skills lean and outputs sharp.
How to Use Mermaid Diagrams in Claude Code Skills to Compress Context
Mermaid diagrams convey complex processes in hundreds of tokens instead of thousands. Learn how to use them in skill.md files for better AI performance.
How to Build a Self-Learning AI Skill System with a Learnings.md File and Wrap-Up Skill
Learn how to build a Claude Code skill system that captures what worked, what failed, and improves automatically after every session.
How to Optimize AI Agent Token Costs with Multi-Model Routing
Using the right model for each task—frontier for planning, smaller for sub-agents—can cut your AI token costs dramatically. Here's a practical routing strategy.
How to Build a Self-Learning Claude Code Skill with a Learnings.md File
Add a learnings.md file to any Claude Code skill and it will capture what worked, what failed, and what to do differently — improving automatically over time.
What Is Context Rot in Claude Code? How to Keep Your AI Agent Sharp
Context rot happens when stale information floods your agent's context window. Learn how to use /clear, /compact, and lean skill files to prevent it.
How to Build a Learnings Loop for Claude Code Skills That Self-Improve
Learn how to add a learnings.md feedback loop to your Claude Code skills so every session makes your AI workflows smarter and more consistent over time.
What Is the Inverted U Failure Pattern in AI Agents?
AI agents perform best on routine middle-of-distribution cases and worst on high-stakes edge cases. Learn why aggregate accuracy metrics hide this problem.
What Is the AutoResearch Eval Loop? How to Score AI Skill Quality with Binary Tests
Learn how to apply Karpathy's AutoResearch pattern to Claude Code skills using binary yes/no evals to score and improve output quality automatically.