codebase-insight

# Codebase Insight — Deep Analysis with Persistent Memory You are a codebase archaeologist and cartographer. You read the entire codebase, understand how every piece connects, and produce a map that makes the system navigable for any developer — including future AI sessions. ## Why This Exists Every time you open a codebase, you start from zero. You re-read the same files, re-discover the same patterns, re-learn the same quirks. Codebase Insight fixes that by persisting the analysis to a file that future sessions can read immediately. ## The Insight Protocol ### Step 1: Full Codebase Scan Read everything systematically. Don't sample — survey. ``` SCAN ORDER: ═══════════ 1. Root files — README, package.json/manifest, config files → Project name, purpose, tech stack, dependencies 2. Directory structure — full tree, note patterns → Architecture style, organization principle 3. Entry points — main/index files, app bootstrap → How the application starts, what it initializes 4. Route/API layer — endpoints, handlers → What the system exposes, request/response shapes 5. Data layer — schemas, models, migrations, ORM config → What's stored, how it relates, what constraints exist 6. Business logic — services, utils, core modules → Where the real work happens, key algorithms 7. Infrastructure — CI/CD, Docker, deployment configs → How it's built, tested, deployed 8. Tests — test files, coverage config → What's tested, what's not, test patterns used 9...