Explain Code

It reads the actual files before explaining anything, which matters because hallucinating about code structure is worse than useless. The output format is solid, breaking things down into purpose, execution flow, dependencies, and gotchas. It checks CLAUDE.md first for project context, which helps it explain things in terms that make sense for your codebase rather than generic descriptions. Use it when you're inheriting unfamiliar code, debugging complex logic, or onboarding to a new system. The anti-hallucination rules are the real value here, forcing verification before explanation.