Initial commit

.claude-plugin/plugin.json

@@ -0,0 +1,15 @@
+{
+  "name": "codanna-cc",
+  "description": "Codanna code intelligence integration for Claude Code - semantic search, symbol analysis, and call graph exploration",
+  "version": "0.1.3",
+  "author": {
+    "name": "bartolli"
+  },
+  "commands": [
+    "./commands/x-ray.md",
+    "./commands/symbol.md"
+  ],
+  "mcp": [
+    "./.mcp.json"
+  ]
+}

.mcp.json

@@ -0,0 +1,16 @@
+{
+  "mcpServers": {
+    "codanna-cc": {
+      "command": "codanna",
+      "args": ["--config", ".codanna/settings.toml", "serve", "--watch", "--watch-interval", "5"]
+    },
+    "codanna-cc-sse": {
+      "type": "sse",
+      "url": "http://127.0.0.1:8080/mcp/sse"
+    },
+    "codanna-cc-https": {
+      "type": "sse",
+      "url": "https://127.0.0.1:8443/mcp/sse"
+    }
+  }
+}

README.md

@@ -0,0 +1,3 @@
+# codanna-cc
+
+Codanna code intelligence integration for Claude Code - semantic search, symbol analysis, and call graph exploration

commands/symbol.md

@@ -0,0 +1,36 @@
+---
+allowed-tools: Bash(node:*), Bash(sed:*), Grep, Glob
+description: Looks up a symbol by name. Returns its location, signature, line range, documentation, calls, callers, implementations, and definitions.
+argument-hint: <symbol-name> "<question>"
+---
+
+## Environment
+
+CLAUDE_PLUGIN_ROOT = !`node -e "console.log(process.env.CLAUDE_PLUGIN_ROOT)"`
+
+## Context
+
+Symbol to analyze: **$1**
+
+User's question: **$2**
+
+## Your task
+
+Use the Bash tool to fetch symbol information, then answer the user's question.
+
+**Workflow:**
+1. Execute: `node ${CLAUDE_PLUGIN_ROOT}/codanna-cc/scripts/context-provider.js symbol $1`
+2. Analyze the symbol details returned (includes `[symbol_id:123]` for all symbols)
+3. Answer the question: "$2"
+
+When answering:
+- Reference actual code locations (file:line_range)
+- Explain relationships (calls, called_by, implements, defines)
+- Use the signature and documentation from the symbol
+- Be specific about how the symbol is used in the codebase
+
+**Following relationships:**
+- Use `<symbol_name|symbol_id:ID>` for follow-up queries
+- Commands: `calls`, `callers`, `describe` accept either format
+
+Focus on what the code actually shows, not general programming principles.

commands/x-ray.md

@@ -0,0 +1,103 @@
+---
+allowed-tools: Bash(node:*), Bash(sed:*), Grep, Glob
+description: Deep codebase exploration using semantic search and relationship mapping
+argument-hint: "<query>"
+---
+
+## Environment
+
+CLAUDE_PLUGIN_ROOT = !`node -e "console.log(process.env.CLAUDE_PLUGIN_ROOT)"`
+
+## Search Query Analysis
+
+**User's Original Query**: "$ARGUMENTS"
+
+### Query Optimization
+
+Codanna's semantic search works best with technical terms and specific concepts. Analyze the query above and improve it for code search:
+
+1. **If vague** (e.g., "that parsing thing") → Make it specific (e.g., "language parser implementation")
+2. **If a question** (e.g., "how does parsing work?") → Extract keywords (e.g., "parsing implementation process")
+3. **If conversational** (e.g., "the stuff that handles languages") → Use technical terms (e.g., "language handler processor")
+4. **If too broad** (e.g., "errors") → Add context (e.g., "error handling exception management")
+
+**OptimizedQuery**: _{Claude: Write your improved query here, then use it below}_
+
+Execute this command with your optimized query:
+
+## Your Workflow <Workflow>
+
+### Gather Context <Step_1 GatherContext>
+
+Use the Bash tool to perform semantic code search:
+
+Execute: `node ${CLAUDE_PLUGIN_ROOT}/codanna-cc/scripts/context-provider.js find "$OptimizedQuery" --limit=5`
+
+**What Codanna returns:**
+- Relevance scores (how well each result matches)
+- Symbol signatures and documentation
+- Relationships (calls, called_by, implements, defines)
+- File locations with line ranges
+
+### Your Workflow <Step_2 YourWorkflow>
+
+1. Analyze the results with their relevance scores (focus on results with score > 0.6 (if possible))
+
+2. **To see actual implementation** of interesting results:
+   - Use the line range from the Location field to read just the relevant code
+   - Example: If you see "Location: `src/io/exit_code.rs:108-120`"
+   - Use the Read tool with:
+      - `file_path`: `src/io/exit_code.rs` (use the working directory from your environment context <env> to construct the absolute path)
+      - `offset`: 108 (start line)
+      - `limit`: 13 (calculated as: 120 - 108 + 1)
+   - Formula: `limit = end_line - start_line + 1`
+   - Example: `Read(file_path="/full/path/to/src/io/exit_code.rs", offset=108, limit=13)`
+
+⚠️ **CRITICAL**: Do NOT read entire files! Use offset/limit based on Location fields!
+
+3. **When relationships are shown** (called_by, calls, defines, implements):
+   - If a relationship looks relevant to answering the query, investigate it
+   - Execute: `node ${CLAUDE_PLUGIN_ROOT}/codanna-cc/scripts/context-provider.js describe <relationship_symbol_name|symbol_id:ID>`
+   - Example: If you see "Called by: `initialize_registry [symbol_id:123]`", run: `node ${CLAUDE_PLUGIN_ROOT}/codanna-cc/scripts/context-provider.js describe initialize_registry` or `describe symbol_id:123`
+   - Note: Following 1-2 key relationships per result is typically sufficient
+
+⚠️ **CRITICAL**: Do NOT read entire files! Use offset/limit based on Location fields!
+
+4. Build a complete picture by following key relationships and reading relevant code sections
+
+5. **If needed**, repeat <Step_1: GatherContext> with a refined query based on what you learned.
+
+---
+
+## Tips for Efficient Exploration
+
+**The results include:**
+- Relevance scores (how well each result matches the query)
+- Symbol documentation and signatures
+- Relationships (who calls this, what it calls, what it defines)
+- System guidance for follow-up investigation
+
+**sed (native on unix only):**
+- You can also see actual implementation with `sed`: (works native on Unix based environments):
+   - Use the line range from the Location field to read just the relevant code
+   - Example: If you see "Location: `src/io/exit_code.rs:108-120`"
+   - Execute: `sed -n '108,120p' src/io/exit_code.rs` to read lines 108-120
+   - This shows the actual code implementation, not just the signature. It works like the Read tool.
+
+- Add `--lang=rust` (or python, typescript, etc.) to narrow results by language if you work on multi-language projects
+- Follow relationships that appear in multiple results (they're likely important)
+- Use the `describe` command to get full details about interesting relationships
+
+**Token awareness:**
+- Each search uses ~500 tokens
+- Each relationship follow uses ~300 tokens
+- Each file read uses ~100-500 tokens (depends on size)
+- Staying efficient keeps your context window clean for deeper analysis
+
+**This command is for exploration:**
+- Build understanding of the codebase
+- Identify patterns and integration points
+- Present findings and await user direction
+- Don't start implementing or making changes yet
+
+Based on the gathered context, engage with the user to narrow focus and help the user with further request.

plugin.lock.json

@@ -0,0 +1,53 @@
+{
+  "$schema": "internal://schemas/plugin.lock.v1.json",
+  "pluginId": "gh:bartolli/codanna-plugins:plugins/codanna-cc",
+  "normalized": {
+    "repo": null,
+    "ref": "refs/tags/v20251128.0",
+    "commit": "f724f3fa313f055471a5bfafe77fffb364fdeab3",
+    "treeHash": "82fe3075909d314424d0a6a4335f46bc7d47266c13140cc360effe307085b8c3",
+    "generatedAt": "2025-11-28T10:14:10.890582Z",
+    "toolVersion": "publish_plugins.py@0.2.0"
+  },
+  "origin": {
+    "remote": "git@github.com:zhongweili/42plugin-data.git",
+    "branch": "master",
+    "commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390",
+    "repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data"
+  },
+  "manifest": {
+    "name": "codanna-cc",
+    "description": "Codanna code intelligence integration for Claude Code - semantic search, symbol analysis, and call graph exploration",
+    "version": "0.1.3"
+  },
+  "content": {
+    "files": [
+      {
+        "path": ".mcp.json",
+        "sha256": "d7ea13d023f9d9156cea038ef171925f120ea1c1a1b22db1803c1ce032e52bea"
+      },
+      {
+        "path": "README.md",
+        "sha256": "46c0ce34b8a8916ad4a3a5f01ce07ed566294f7d62e597f40ec502884cc9d7eb"
+      },
+      {
+        "path": ".claude-plugin/plugin.json",
+        "sha256": "1a8bddd0e0381cc42ab7dd0f63fbdbaa688dfc636ee43a3dd3cb99e356cd7774"
+      },
+      {
+        "path": "commands/symbol.md",
+        "sha256": "db3d9c66d6c87f49f5549d480b37d07365a5077a19316c54c7c609cbc9d1b374"
+      },
+      {
+        "path": "commands/x-ray.md",
+        "sha256": "4586f3e540a48c8e65f5e7357f5c7060ffb4f6291a2b432c9dd09662fe441095"
+      }
+    ],
+    "dirSha256": "82fe3075909d314424d0a6a4335f46bc7d47266c13140cc360effe307085b8c3"
+  },
+  "security": {
+    "scannedAt": null,
+    "scannerVersion": null,
+    "flags": []
+  }
+}