GitHub API Cache

Overview

Cache GitHub project metadata ONCE at session start. All subsequent operations use cached data.

Core principle: Fetch once, extract many. Never repeat API calls for the same data.

This skill is called by session-start and provides cached data to all other skills.

The Problem

GitHub GraphQL API has a 5,000 point/hour limit. Without caching:

• gh project item-list = 1 call per invocation
• gh project field-list = 1 call per invocation
• gh project list = 1 call per invocation

A typical session startup was consuming 3,500+ of 5,000 points through repeated calls.