Update protocol, docs-discovery skill, and doc layering
- Switched AI AGENT CORE PROTOCOL to new `[LOADED_DOCS: N files (+K this turn: ...)]` prefix format in all primary instruction files; updated examples and enforcement details.
- Added `docs-discovery` skill for proactive .md doc loading before code search; documented usage and integration as a shared agent skill.
- Introduced `## Protocol History` section and `LLM_PROTOCOL_DECISIONS.md` decision log for cross-repo protocol change tracking.
- Expanded protocol-audit skill and `REPOS.md` to support 8 instruction files (primary/inherit split), new invariants, and known issues.
- Added/updated structured TODO and issues docs for serialization, logging, and SignalR binary protocol.
- Improved cross-references, doc layering, and clarified documentation-first coding workflow.
- Various minor doc clarifications and formatting for protocol consistency.
.NET 9 core framework providing serialization (Binary, JSON, Toon), entity abstractions, database access, services, and shared utilities. Used as the foundation layer for AyCode applications.
LLM Context
Domain rules and key pitfalls live in a single file: .github/copilot-instructions.md
Tool
Auto-loaded
Action needed
GitHub Copilot
✅copilot-instructions.md
None
Claude Code
✅CLAUDE.md → references above
None
Cursor / Windsurf
✅README.md
Read copilot-instructions.md via @file
Solution-level docs in docs/:
Document
Topic
GLOSSARY.md
Core terminology reference
ARCHITECTURE.md
Solution layers, dependency rules
CONVENTIONS.md
Coding conventions
Project-level docs — each project's docs/ folder documents the code it defines:
Loretta
61509f1b95