Token Optimization

This is your reference guide when Claude starts burning through tokens with inefficient MCP server calls. It covers the practical stuff: adding LIMIT clauses to database queries, using compact formats for API schemas, tailing logs instead of dumping entire files, and checking context before fetching documentation you might already have. The anti-patterns table is the most useful part, showing you exactly what not to do (like SELECT * or fetching full API specs when you only need one endpoint). Think of it as a pre-flight checklist before making tool calls. If you're working with MCP servers regularly and want to keep token costs down without sacrificing quality, this will save you from the obvious mistakes.

skills.sh installs: 346
GitHub stars: 47
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add claude-dev-suite/claude-dev-suite --skill token-optimization --agent claude-code

Installs into .claude/skills of the current project.

Files

Token Optimization Best Practices

Deep Knowledge: Use mcp__documentation__fetch_docs with technology: token-optimization for comprehensive documentation.

Guidelines for minimizing token consumption in MCP server and external tool interactions.

When NOT to Use This Skill

This skill focuses on API/tool call optimization. Do NOT use for:

Runtime performance - Use performance skill for speed optimization
Code minification - Use build tools (Vite, Webpack, etc.)
Database query optimization - Use database-specific skills
Algorithm efficiency - Use computer science fundamentals
Prompt engineering - This is about tool usage, not prompt design

General Principles

Principle	Description
Lazy Loading	Load information only when strictly necessary
Minimal Output	Request only needed data, use `limit` and `compact` parameters
Progressive Detail	Start with overview/summary, drill down only if needed
Cache First	Check if information is already in context before external calls