I Built a Skill Resolver for AI Agents - What I Learned About Token Economics

The Problem Nobody Talks About AI coding agents (Claude Code, Codex, Cursor) have a dirty secret: they waste ~50,000 tokens every time they need a new skill. The flow looks like this: Agent gets a task it doesn't know how to do Searches GitHub for SKILL.md files Reads 5-10 of them to compare Picks one Finally starts the actual work Steps 2-4 burn through context window like jet fuel. And here's the kicker — the agent does this every session, because it doesn't remember what it found last time. The Math That Changed My Mind I measured it across 50 sessions: Approach Tokens for skill discovery Tokens for actual task Manual search ~50,000 ~5,000 Pre-loaded (20 skills) 0 (pre-loaded) ~5,000 + 40,000 context tax Resolver ~200 ~5,000 The resolver approach is 250x more efficient than manual search and doesn't waste context on skills you might never use. What I Built SkillsHub — an open-source skill registry with a resolve endpoint that matches natural language task descriptions to the best sk