Frequently Asked Questions

[Varietyz]

Answers to common questions. This post is updated as patterns emerge from the Q&A.

---

Q: Do I need Claude Code specifically?

The methodology works best with Claude Code because claude-setup, PAG, and the memory governance system are built for it. It also works with Cursor, Windsurf, and similar CLI-based AI tools with adaptation. It does not work with web-based AI chat (no hooks, no validators, no session governance).

Q: What is PAG?

Pattern Abstract Grammar. A structured instruction language designed from thousands of hours of Claude interactions. It maps how the AI works: where it works well, where it struggles, how to constrain it. PAG is how CLAUDE.md policies, agents, workflows, and planning templates are written.

Q: Do I need to read everything before starting?

No. Start with the methodology README. Follow links as concepts interest you. Copy claude-setup into your project when ready. The methodology teaches itself through practice: the AI reads the documents and applies them as you work.

Q: What is the 150-line rule?

Files that stay under 150 lines tend to be easier to review, test, and reason about. When one grows past that, splitting by concern produces modules that are individually comprehensible. It is not a hard rule. It is a constraint that tends to prevent the kind of file bloat that makes AI-generated code unmaintainable.

Q: What is Phase 0?

Infrastructure established before feature development. Validation hooks, CI/CD, configuration management, testing setup. The reasoning: everything built on top depends on these. Setting them up first prevents rework.

---

Have a question not covered here? Post a new Q&A discussion.