claude-md-architectlisted

# CLAUDE.md Architect A skill for designing CLAUDE.md files and their supporting documentation systems for Claude Code projects. Grounded in Anthropic's official memory docs (`code.claude.com/docs/en/memory`), HumanLayer's "Writing a good CLAUDE.md" guide, Vercel Engineering's January 2026 AGENTS.md eval (53% → 100% pass rate), Arize AI's prompt-learning SWE-Bench results (+10%), and the ETH Zurich AGENTS.md evaluation (Gloaguen et al., arXiv:2602.11988, ICLR 2026 workshop) — which shows that low-quality context files actively *reduce* task success and add ~20% inference cost. ## Core Mental Model CLAUDE.md is **not** documentation — it is the highest-leverage prompt in a Claude Code project. Every line loads into every session's context and competes with the actual task for the model's attention. The single most important question for any content is: **"Would removing this cause Claude to make mistakes?"** If no, cut it. ### Three Foundational Principles 1. **Minimum Viable Context** — Anthropic targets <200 lines per file; production teams operate at 40–80. Bloat is the #1 cause of Claude ignoring rules. 2. **Progressive Disclosure** — CLAUDE.md should orchestrate, not contain. Point to deeper docs/skills/rules that load on-demand. The orchestrator pattern beats monolithic files even at identical line counts. 3. **Earn Every Line** — Each rule should trace back to a real incident, not a hypothetical one. Promote learnings from auto-memory (MEMORY.md) to CLAUDE.md only