I built this because Claude Code loads every rule and skill into context on every prompt. With 50+ rules and skills installed, you're burning tokens on Docker best practices while writing a commit message.
ai-nexus runs a hook before Claude starts — it picks 2-3 relevant rules and skills via keyword matching (free) or GPT-4o-mini (~$0.50/mo), and physically hides the rest. Claude doesn't even know they exist.
An ETH Zurich study (https://arxiv.org/pdf/2602.11988) on 12 repos and 5,694 PRs found that loading all rules at once hurts performance by ~3% and increases cost by 20%+.
It also works across tools — write rules and skills in .md once, auto-converts to .mdc (Cursor) and AGENTS.md (Codex).
npx ai-nexus install to try it. Apache 2.0.