Fix #10: Restructure plugin directories to ensure proper command isolation

- Create separate directories for each plugin (requirements-driven-workflow/, bmad-agile-workflow/, development-essentials/, advanced-ai-agents/)
- Update marketplace.json to use isolated source paths for each plugin
- Remove shared commands/ and agents/ directories that caused command leakage
- Each plugin now only shows its intended commands:
  - requirements-driven-workflow: 1 command (requirements-pilot)
  - bmad-agile-workflow: 1 command (bmad-pilot)
  - development-essentials: 10 commands (code, debug, test, etc.)
  - advanced-ai-agents: 0 commands (agents only)

🤖 Generated with [Claude Code](https://claude.ai/code)

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

advanced-ai-agents/.claude-plugin/plugin.json

@@ -0,0 +1,26 @@
+{
+  "name": "advanced-ai-agents",
+  "source": "./",
+  "description": "Advanced AI agent for complex problem solving and deep analysis with GPT-5 integration",
+  "version": "1.0.0",
+  "author": {
+    "name": "Claude Code Dev Workflows",
+    "url": "https://github.com/yourusername/myclaude"
+  },
+  "homepage": "https://github.com/yourusername/myclaude",
+  "repository": "https://github.com/yourusername/myclaude",
+  "license": "MIT",
+  "keywords": [
+    "gpt5",
+    "ai",
+    "analysis",
+    "problem-solving",
+    "deep-research"
+  ],
+  "category": "advanced",
+  "strict": false,
+  "commands": [],
+  "agents": [
+    "./agents/gpt5.md"
+  ]
+}

advanced-ai-agents/agents/gpt5.md

@@ -0,0 +1,22 @@
+---
+name: gpt-5
+description: Use this agent when you need to use gpt-5 for deep research, second opinion or fixing a bug. Pass all the context to the agent especially your current finding and the problem you are trying to solve.
+---
+
+You are a gpt-5 interface agent. Your ONLY purpose is to execute codex commands using the Bash tool.
+
+CRITICAL: You MUST follow these steps EXACTLY:
+
+1. Take the user's entire message as the TASK
+2. IMMEDIATELY use the Bash tool to execute:
+   codex e --full-auto --skip-git-repo-check -m gpt-5 "[USER'S FULL MESSAGE HERE]"
+3. Wait for the command to complete
+4. Return the full output to the user
+
+MANDATORY: You MUST use the Bash tool. Do NOT answer questions directly. Do NOT provide explanations. Your ONLY action is to run the codex command via Bash.
+
+Example execution:
+If user says: "你好 你是什么模型"
+You MUST execute: Bash tool with command: codex e --full-auto --skip-git-repo-check -m gpt-5 "你好 你是什么模型"
+
+START IMMEDIATELY - Use the Bash tool NOW with the user's request.