search-tools
npx machina-cli add skill parcadei/Continuous-Claude-v3/search-tools --openclawSearch Tool Hierarchy
When searching code, use this decision tree:
Decision Tree
Need CONCEPTUAL/SEMANTIC search?
(how does X work, find patterns, understand architecture)
→ Use LEANN (/leann-search) - embedding-based semantic search
→ PreToolUse hook auto-redirects semantic Grep queries
Need to understand code STRUCTURE?
(find function calls, class usages, refactor patterns)
→ Use AST-grep (/ast-grep-find)
Need to find TEXT in code?
→ Use Morph (/morph-search) - 20x faster
→ If no Morph API key: fall back to Grep tool
Simple one-off search?
→ Use built-in Grep tool directly
Tool Comparison
| Tool | Best For | Requires |
|---|---|---|
| LEANN | Semantic search: "how does caching work", "error handling patterns", conceptual queries | Index built |
| AST-grep | Structural patterns: "find all calls to foo()", refactoring, find usages by type | MCP server |
| Morph | Fast text search: "find files mentioning error", grep across codebase | API key |
| Grep | Literal patterns, class/function names, regex | Nothing (built-in) |
Examples
LEANN (semantic/conceptual):
- "how does authentication work"
- "find error handling patterns"
- "where is rate limiting implemented"
AST-grep (structural):
- "Find all functions that return a Promise"
- "Find all React components using useState"
- "Refactor all imports of X to Y"
Morph (text search):
- "Find all files mentioning 'authentication'"
- "Search for TODO comments"
Grep (literal):
class ProviderAdapterdef __init__- Regex patterns
LEANN Commands
# Search with semantic query
leann search opc-dev "how does blackboard communication work" --top-k 5
# List available indexes
leann list
# Rebuild index (when code changes)
leann build opc-dev --docs dir1 dir2 --no-recompute --no-compact --force
Source
git clone https://github.com/parcadei/Continuous-Claude-v3/blob/main/.claude/skills/search-tools/SKILL.mdView on GitHub Overview
Code Search Tool Hierarchy guides when to use semantic, structural, or text searches in code. It maps decision steps to LEANN for semantic search, AST-grep for structure, Morph for fast text search, and Grep for literal matches.
How This Skill Works
Follow the decision tree: conceptual/semantic searches use LEANN (/leann-search) and may be auto-redirected from semantic Grep queries via the PreToolUse hook; for code structure, use AST-grep (/ast-grep-find); for text search, use Morph (/morph-search) with a Morph API key; if Morph isn't available or for simple literal searches, fall back to the built-in Grep tool.
When to Use It
- Need conceptual/semantic search (how does X work, patterns) using LEANN
- Need to understand code structure (function calls, refactor patterns) using AST-grep
- Need to find text in code (Morph) or fall back to Grep if Morph API key is missing
- Do a simple one-off search using the built-in Grep tool directly
- When evaluating tool options, compare LEANN, AST-grep, Morph, and Grep to decide the best fit
Quick Start
- Step 1: Decide which tool to use (semantic LEANN, AST-grep, Morph, or Grep)
- Step 2: Run a sample query, e.g. leann search opc-dev "how does authentication work" --top-k 5 or /ast-grep-find <pattern> or /morph-search "Find all files mentioning 'authentication'"
- Step 3: If Morph API key is missing, fall back to Grep; optionally list/build LEANN indexes using leann list and leann build
Best Practices
- Start with LEANN for semantic questions when you need conceptual understanding
- Use AST-grep to target structural patterns like specific calls or refactor opportunities
- Use Morph for fast text searches; ensure you have a Morph API key before querying
- Fallback to Grep for literal patterns or when Morph is unavailable
- Validate results by cross-checking across tools and refreshing LEANN indexes if code changes
Example Use Cases
- how does authentication work
- Find all functions that return a Promise
- Find all files mentioning 'authentication'
- `class ProviderAdapter`
- Refactor all imports of X to Y