feat(plugins): Add repository-explorer plugin for AI-powered codebase analysis

.claude-plugin/marketplace.json

@@ -5,7 +5,7 @@
   },
   "metadata": {
     "description": "Official Repomix plugins for Claude Code",
-    "version": "1.0.1"
+    "version": "1.0.2"
   },
   "plugins": [
     {
@@ -25,14 +25,27 @@
       "name": "repomix-commands",
       "source": "./.claude/plugins/repomix-commands",
       "description": "Slash commands for quick Repomix operations. Pack local and remote repositories with simple commands like /pack-local and /pack-remote.",
-      "version": "1.0.1",
+      "version": "1.0.2",
       "author": {
         "name": "yamadashy"
       },
       "keywords": ["repomix", "commands", "pack", "productivity"],
       "category": "productivity",
       "license": "MIT",
       "strict": false
+    },
+    {
+      "name": "repository-explorer",
+      "source": "./.claude/plugins/repository-explorer",
+      "description": "AI-powered repository analysis agent using Repomix CLI. Analyzes local and remote repositories intelligently by running repomix commands, then reading and searching the generated output files to answer questions about code structure, patterns, and content.",
+      "version": "1.0.0",
+      "author": {
+        "name": "yamadashy"
+      },
+      "keywords": ["repomix", "agent", "repository-analysis", "code-exploration", "ai"],
+      "category": "productivity",
+      "license": "MIT",
+      "strict": false
     }
   ]
 }

.claude/plugins/repomix-commands/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "repomix-commands",
   "description": "Slash commands for quick Repomix operations. Pack local and remote repositories with simple commands like /pack-local and /pack-remote.",
-  "version": "1.0.1",
+  "version": "1.0.2",
   "author": {
     "name": "yamadashy"
   },

.claude/plugins/repomix-commands/commands/pack-local.md

@@ -62,10 +62,38 @@ npx repomix@latest --copy
 npx repomix@latest --include-diffs --include-logs
 ```
 
+## Analyzing the Output
+
+**IMPORTANT**: The generated output file can be very large and consume significant context.
+
+If the user wants to analyze or explore the generated output:
+- **DO NOT read the entire output file directly**
+- **USE an appropriate sub-agent** to analyze the output
+- The sub-agent will efficiently search and read specific sections using grep and incremental reading
+
+**Agent Selection Strategy**:
+1. If `repository-explorer` agent is available, use it (optimized for repomix output analysis)
+2. Otherwise, use the `general-purpose` agent or another suitable sub-agent
+3. The sub-agent should use Grep and Read tools to analyze incrementally
+
+Example:
+```text
+User: "Pack this codebase and analyze it"
+
+Your workflow:
+1. Run: npx repomix@latest
+2. Note the output file location (e.g., repomix-output.xml)
+3. Launch an appropriate sub-agent with task:
+   "Analyze the repomix output file at ./repomix-output.xml.
+   Use Grep tool to search for patterns and Read tool to examine specific sections.
+   Provide an overview of the codebase structure and main components.
+   Do NOT read the entire file at once."
+```
+
 ## Help and Documentation
 
 If you need more information about available options or encounter any issues:
 - Run `npx repomix@latest -h` or `npx repomix@latest --help` to see all available options
 - Check the official documentation at https://github.com/yamadashy/repomix
 
-Remember: Parse the user's natural language request and translate it into the appropriate repomix command.
+Remember: Parse the user's natural language request and translate it into the appropriate repomix command. For analysis tasks, delegate to appropriate sub-agents to avoid consuming excessive context.

.claude/plugins/repomix-commands/commands/pack-remote.md

@@ -69,10 +69,38 @@ npx repomix@latest --remote owner/repo --include "src/**/*.ts"
 npx repomix@latest --remote yamadashy/repomix --copy --style markdown
 ```
 
+## Analyzing the Output
+
+**IMPORTANT**: The generated output file can be very large and consume significant context.
+
+If the user wants to analyze or explore the generated output:
+- **DO NOT read the entire output file directly**
+- **USE an appropriate sub-agent** to analyze the output
+- The sub-agent will efficiently search and read specific sections using grep and incremental reading
+
+**Agent Selection Strategy**:
+1. If `repository-explorer` agent is available, use it (optimized for repomix output analysis)
+2. Otherwise, use the `general-purpose` agent or another suitable sub-agent
+3. The sub-agent should use Grep and Read tools to analyze incrementally
+
+Example:
+```text
+User: "Pack and analyze the yamadashy/repomix repository"
+
+Your workflow:
+1. Run: npx repomix@latest --remote yamadashy/repomix
+2. Note the output file location (e.g., repomix-output.xml)
+3. Launch an appropriate sub-agent with task:
+   "Analyze the repomix output file at ./repomix-output.xml.
+   Use Grep tool to search for patterns and Read tool to examine specific sections.
+   Provide an overview of the repository structure and main components.
+   Do NOT read the entire file at once."
+```
+
 ## Help and Documentation
 
 If you need more information about available options or encounter any issues:
 - Run `npx repomix@latest -h` or `npx repomix@latest --help` to see all available options
 - Check the official documentation at https://github.com/yamadashy/repomix
 
-Remember: Parse the user's natural language request and translate it into the appropriate repomix command with the --remote option.
+Remember: Parse the user's natural language request and translate it into the appropriate repomix command with the --remote option. For analysis tasks, delegate to appropriate sub-agents to avoid consuming excessive context.

.claude/plugins/repository-explorer/.claude-plugin/plugin.json

@@ -0,0 +1,10 @@
+{
+  "name": "repository-explorer",
+  "description": "AI-powered repository analysis agent using Repomix CLI. Analyzes local and remote repositories intelligently by running repomix commands, then reading and searching the generated output files to answer questions about code structure, patterns, and content.",
+  "version": "1.0.0",
+  "author": {
+    "name": "yamadashy"
+  },
+  "keywords": ["repomix", "agent", "repository-analysis", "code-exploration", "ai"],
+  "license": "MIT"
+}