Add load_skill tool to bypass workspace restriction for builtin skills

When restrictToWorkspace is enabled, the agent cannot read builtin skill
files via read_file since they live outside the workspace. This adds a
dedicated load_skill tool that reads skills by name through the SkillsLoader,
which accesses files directly via Python without the workspace restriction.

- Add LoadSkillTool to filesystem tools
- Register it in the agent loop
- Update system prompt to instruct agent to use load_skill instead of read_file
- Remove raw filesystem paths from skills summary

nanobot/agent/subagent.py

@@ -213,7 +213,7 @@ Stay focused on the assigned task. Your final response will be reported back to
 
         skills_summary = SkillsLoader(self.workspace).build_skills_summary()
         if skills_summary:
-            parts.append(f"## Skills\n\nRead SKILL.md with read_file to use a skill.\n\n{skills_summary}")
+            parts.append(f"## Skills\n\nUse load_skill tool to load a skill by name.\n\n{skills_summary}")
 
         return "\n\n".join(parts)