feat: initial 24 principles extracted from real multi-project AI dev work

Grouped into 7 themes: Architecture & Design, Cost & Efficiency,
Execution & Error Handling, Autonomy & Agents, Documentation,
Capture & Learning, Content Production.

Each principle grounded in observed patterns, not theory.

CLAUDE.md

@@ -0,0 +1,28 @@
+# AI Dev Principles — Project Instructions
+
+## What is this
+
+A living collection of principles for building software with AI agents. Extracted from real multi-project work, not theorized. Each principle has an origin story.
+
+## Content Rules
+
+- Every principle must come from real experience (observed pattern, correction, or confirmed approach)
+- Include **Origin** where possible — what happened that led to this principle
+- No aspirational fluff — if it's not practiced, it doesn't belong here
+- Principles can evolve or be retired — mark deprecated ones rather than deleting
+
+## Structure
+
+- `README.md` — The principles document (canonical, numbered, grouped by theme)
+- `docs/examples/` — Concrete examples and case studies for select principles
+- `docs/status.md` — Session log
+
+## Language
+
+- English for everything (these principles are language-independent)
+
+## Commits
+
+- `feat:` for new principles
+- `docs:` for examples, refinements, rewordings
+- `fix:` for corrections to existing principles