docs: GOVERNANCE LOCK — AGENTS.md is the ONLY source of guidelines

Establish unambiguous governance:
- AGENTS.md v16.0 is the ONLY document that contains engineering guidelines
- All procedures, harnesses, rules, decision frameworks live in AGENTS.md
- CLAUDE.md, GEMINI.md, and all other documents FOLLOW AGENTS.md
- Other documents ONLY reference AGENTS.md with explicit links
- If any document conflicts with AGENTS.md, AGENTS.md is authoritative

Changes:
- AGENTS.md: Add 'GOVERNANCE LOCK' section at top (5 rules, scope definition)
- CLAUDE.md: Add critical warning (context only, not guidelines)
- Rules: Never add procedures to supplementary documents

Non-negotiable enforcement:
- New guidelines → AGENTS.md only
- Found guidelines elsewhere → move to AGENTS.md, replace with reference
- Conflicting guidance → AGENTS.md wins
- Exception: Project status, architecture context, navigation (CLAUDE.md only)

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

AGENTS.md

@@ -1,13 +1,24 @@
 # K-ArtSell Aegis AI Coding Constitution v16.0
 
-**AGENTS.md IS THE AUTHORITATIVE SOURCE FOR ALL ENGINEERING DECISIONS.**
+## 🔒 GOVERNANCE LOCK
 
-This document supersedes conflicting guidance in CLAUDE.md, MEMORY, or prior conversations. When in doubt, follow AGENTS.md.
+**AGENTS.md IS THE ONLY AUTHORITATIVE SOURCE FOR ENGINEERING GUIDELINES.**
 
-**Hierarchy:**
-1. **AGENTS.md** — This file (AI coding constitution, rules, harnesses)
-2. **CLAUDE.md** — Supplements AGENTS.md (project context, architecture, status)
-3. **Code** — Implementation (must comply with AGENTS.md)
+**Rules (Non-negotiable):**
+1. **All engineering procedures, harnesses, and decision frameworks go in AGENTS.md only.**
+2. **CLAUDE.md, GEMINI.md, and all other .md files follow AGENTS.md. They do NOT define rules.**
+3. **If any document conflicts with AGENTS.md, AGENTS.md wins. Other text is void.**
+4. **Never add guidelines to CLAUDE.md, GEMINI.md, or side documents.**
+5. **Supplementary files reference AGENTS.md with explicit links only.**
+
+**Scope:**
+- **AGENTS.md owns:** Coding rules, development setup, procedures, harnesses, decision frameworks, anti-patterns, workflows
+- **Other files provide:** Project status, architecture context, navigation, references (links to AGENTS.md)
+
+**Enforcement:**
+- Claude Code will not accept conflicting guidance from multiple sources
+- When in doubt, check AGENTS.md section headers
+- If you see conflicting guidance elsewhere, update that document to reference AGENTS.md instead
 
 ## Default execution procedure
 

CLAUDE.md

@@ -1,13 +1,25 @@
 # CLAUDE.md
 
-This file provides project context and architecture for Claude Code (claude.ai/code).
+**⚠️ CRITICAL: This file is for PROJECT CONTEXT ONLY. It does NOT contain engineering guidelines.**
 
-**IMPORTANT: All engineering decisions are governed by AGENTS.md v16.0. This file supplements AGENTS.md but DOES NOT override it.**
+**All engineering guidelines, rules, harnesses, and procedures are in AGENTS.md v16.0 ONLY.**
 
-**Single Source of Truth (Hierarchy):**
-1. **AGENTS.md** — AI coding constitution, principles, rules (authoritative)
-2. **CLAUDE.md** — Project context, status, architecture (supplementary)
-3. **Project code** — Implementation (must comply with AGENTS.md)
+If any section below conflicts with AGENTS.md, AGENTS.md is authoritative and this text is invalid.
+
+**What belongs in AGENTS.md:**
+- Coding principles and rules
+- Development configuration (database, ports, authentication, SSH)
+- Procedures and workflows
+- Decision frameworks
+- Anti-patterns and guardrails
+
+**What belongs in CLAUDE.md:**
+- Project status and timeline
+- Architecture overview (high-level only)
+- File structure and navigation
+- References to AGENTS.md (with explicit links)
+
+**When working: Always check AGENTS.md first. CLAUDE.md is supplementary context only.**
 
 ## ⚖️ Governance: AGENTS.md v16.0 Strategic Principles