Initial commit

.claude-plugin/plugin.json

@@ -0,0 +1,11 @@
+{
+  "name": "codanna-cc-plugin",
+  "description": "Codanna code intelligence integration for Claude Code - semantic search, symbol analysis, and call graph exploration",
+  "version": "0.1.0",
+  "author": {
+    "name": "bartolli"
+  },
+  "commands": [
+    "./commands"
+  ]
+}

README.md

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

commands/ask.md

@@ -0,0 +1,27 @@
+---
+description: Look up a symbol and ask Claude a specific question about it
+argument-hint: <symbol-name> "<question>"
+---
+
+## 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/scripts/context-provider.js symbol $1`
+2. Analyze the symbol details returned
+3. Answer the question: "$2"
+
+When answering:
+- Reference actual code locations (file:line)
+- 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
+
+Focus on what the code actually shows, not general programming principles.

commands/find.md

@@ -0,0 +1,51 @@
+---
+description: Smart semantic search for code with full context
+argument-hint: "<query>"
+---
+
+## Search Query Analysis
+
+**User's Original Query**: "$ARGUMENTS"
+
+### Query Optimization
+
+Claude, analyze the query above and improve it for code search:
+
+1. **If vague** (e.g., "that parsing thing") → Make it specific (e.g., "language parser implementation")
+2. **If a question** (e.g., "how does parsing work?") → Extract keywords (e.g., "parsing implementation process")
+3. **If conversational** (e.g., "the stuff that handles languages") → Use technical terms (e.g., "language handler processor")
+4. **If too broad** (e.g., "errors") → Add context (e.g., "error handling exception management")
+
+**YourOptimizedQuery**: _{Claude: Write your improved query here, then use it below}_
+
+Execute this command with your optimized query:
+
+## Your task
+
+Use the Bash tool to perform semantic code search.
+
+**Workflow:**
+1. Execute: `node .claude/scripts/context-provider.js find "$YourOptimizedQuery" --limit=5`
+2. Analyze the results with their relevance scores
+3. **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`"
+   - 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
+4. **When relationships are shown** (called_by, calls, defines, implements):
+   - If a relationship looks relevant to answering the query, investigate it
+   - Execute: `node .claude/scripts/context-provider.js symbol <relationship_symbol_name>`
+   - Example: If you see "Called by: `initialize_registry`", run: `node .claude/scripts/context-provider.js symbol initialize_registry`
+5. Build a complete picture by following 1-2 key relationships and reading relevant code sections
+6. Present findings to the user with context from search results, relationships, and actual code snippets
+
+**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
+
+**Tips:**
+- Add `--lang=rust` (or python, typescript, etc.) to narrow results by language
+- Follow relationships that appear in multiple results (they're likely important)
+- Use the `symbol` command to get full details about interesting relationships

plugin.lock.json

@@ -0,0 +1,49 @@
+{
+  "$schema": "internal://schemas/plugin.lock.v1.json",
+  "pluginId": "gh:bartolli/codanna-cc-plugin:",
+  "normalized": {
+    "repo": null,
+    "ref": "refs/tags/v20251128.0",
+    "commit": "2e3b9e14b30363c77fcc5a59399c58cc6f4c694b",
+    "treeHash": "8c5367269e5b4f0ab47c9bccfa9aa5089b61c07423f33c4b6607647920e4bc9f",
+    "generatedAt": "2025-11-28T10:14:10.461490Z",
+    "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-plugin",
+    "description": "Codanna code intelligence integration for Claude Code - semantic search, symbol analysis, and call graph exploration",
+    "version": "0.1.0"
+  },
+  "content": {
+    "files": [
+      {
+        "path": "README.md",
+        "sha256": "f784155fbd5c4518b6f332c01976141456c482e3f191771abad1a724902885fb"
+      },
+      {
+        "path": ".claude-plugin/plugin.json",
+        "sha256": "9c3e304d277eb95ed57e5942d6b3334de9ddaf85fcb06e09bc590b785b0c6178"
+      },
+      {
+        "path": "commands/find.md",
+        "sha256": "ec7a1f45bf0899432b2c35c40c9ee90a50bb4189098a5f3d2b4e2c6e309f6023"
+      },
+      {
+        "path": "commands/ask.md",
+        "sha256": "6a7b4f3a923ce513d5492fa5acba217c9cf5cabaf003a17a180de58ab1329cc5"
+      }
+    ],
+    "dirSha256": "8c5367269e5b4f0ab47c9bccfa9aa5089b61c07423f33c4b6607647920e4bc9f"
+  },
+  "security": {
+    "scannedAt": null,
+    "scannerVersion": null,
+    "flags": []
+  }
+}