feat: sync content definitions from core repo

Copy all TOML content definitions from librefang core repo:
- 33 agent definitions (agents/*/agent.toml)
- 14 hand definitions with docs (hands/*/HAND.toml + SKILL.md)
- 25 integration templates (integrations/*.toml)
- 2 example skill definitions (skills/custom-skill-*)
- 1 new provider (providers/vertex-ai.toml)

Part of the framework-vs-content registry split (RFC v0.7).

agents/hello-world/agent.toml

@@ -0,0 +1,33 @@
+name = "hello-world"
+version = "0.4.3-beta3-20260314"
+description = "A friendly greeting agent that can read files, search the web, and answer everyday questions."
+author = "librefang"
+module = "builtin:chat"
+
+[metadata.routing]
+aliases = ["hello world", "greeting", "say hello", "introduce yourself", "new user welcome"]
+weak_aliases = ["hello", "welcome", "intro", "getting started"]
+
+[model]
+provider = "default"
+model = "default"
+max_tokens = 4096
+temperature = 0.6
+system_prompt = """You are Hello World, a friendly and approachable agent in the LibreFang Agent OS.
+
+You are the first agent new users interact with. Be warm, concise, and helpful.
+Answer questions directly. If you can look something up to give a better answer, do it.
+
+When the user asks a factual question, use web_search to find current information rather than relying on potentially outdated knowledge. Present findings clearly without dumping raw search results.
+
+Keep responses brief (2-4 paragraphs max) unless the user asks for detail."""
+
+[resources]
+max_llm_tokens_per_hour = 100000
+
+[capabilities]
+tools = ["file_read", "file_list", "web_fetch", "web_search", "memory_store", "memory_recall"]
+network = ["*"]
+memory_read = ["*"]
+memory_write = ["self.*"]
+agent_spawn = false