feat: initialize tfcode project structure

- Add README.md as living documentation
- Add tfcode.json schema and config template
- Add FORK_MANAGEMENT.md with mirror-based fork strategy
- Add scripts/rebrand.sh for reapplying branding after upstream merges
- Add packages/tf-sync Python module using official ToothFairyAI SDK
- Add packages/tf-mcp-bridge TypeScript module (stub)
- Multi-region support (AU, EU, US)
- Tool sync: MCP servers, Agent Skills, Database Scripts, API Functions

packages/tf-sync/src/tf_sync/agents.py

@@ -0,0 +1,39 @@
+"""
+Agent sync module for tfcode.
+
+NOTE: This module is reserved for future implementation.
+Currently, tfcode only syncs tools (MCP, Skills, Database, Functions).
+Agent sync will be added in a later phase.
+"""
+
+from typing import Any
+
+from pydantic import BaseModel
+
+from tf_sync.config import TFConfig
+
+
+class AgentSyncResult(BaseModel):
+    """Result of agent sync operation."""
+    
+    success: bool
+    agents: list[dict[str, Any]] = []
+    error: str | None = None
+
+
+def sync_agents(config: TFConfig) -> AgentSyncResult:
+    """
+    Sync agents from ToothFairyAI workspace.
+    
+    NOTE: Currently not implemented. Reserved for future use.
+    
+    Args:
+        config: TFConfig instance
+    
+    Returns:
+        AgentSyncResult (currently always returns not implemented)
+    """
+    return AgentSyncResult(
+        success=False,
+        error="Agent sync not yet implemented. Use tools sync for now.",
+    )