Skill

tree-sitter

From asi

AST-based code analysis using tree-sitter. Use for parsing code structure, extracting symbols, finding patterns with tree-sitter queries, analyzing complexity, and understanding code architecture. Supports Python, JavaScript, TypeScript, Go, Rust, C, C++, Swift, Java, Kotlin, Julia, and more.

npx claudepluginhub plurigrid/asi --plugin asi

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Intelligent code analysis via AST parsing with tree-sitter.

SKILL.md

Similar Skills

smart-explore

72.1k

Performs token-optimized structural code search using tree-sitter AST parsing to discover symbols, outline files, and unfold code without reading full files.

claude-mem

tldr

TLDR code analysis (call graphs, semantic search, impact, dataflow) — ~95% token savings vs raw reads. Auto-invoke for "who calls X", "what affects X", before reading large files or refactoring.

18 tools

darkroom

research-phase

Maps codebase structure, patterns, symbols, and dependencies using ast-grep and bash scripts. Outputs factual maps with paths/line numbers to .artifacts/research/.

4 files7 tools

harness-engineering

Stats

Parent Repo Stars16

Parent Repo Forks5

Last CommitFeb 16, 2026

Used By2 plugins

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Tree-sitter Code Analysis

Intelligent code analysis via AST parsing with tree-sitter.

When to Use

Understanding code structure across multiple languages
Extracting function/class definitions
Finding code patterns with tree-sitter queries
Analyzing code complexity
Symbol extraction and dependency analysis

Setup

MCP server configured in ~/.mcp.json:

{
  "tree-sitter": {
    "command": "python3",
    "args": ["-m", "mcp_server_tree_sitter.server"],
    "cwd": "/Users/alice/mcp-server-tree-sitter"
  }
}

Usage Pattern

1. Register a Project First

register_project_tool(path="/path/to/project", name="my-project")

2. Explore Files

list_files(project="my-project", pattern="**/*.py")
get_file(project="my-project", path="src/main.py")

3. Analyze Structure

get_ast(project="my-project", path="src/main.py", max_depth=3)
get_symbols(project="my-project", path="src/main.py")

4. Search with Queries

find_text(project="my-project", pattern="function", file_pattern="**/*.py")
run_query(
  project="my-project",
  query='(function_definition name: (identifier) @function.name)',
  language="python"
)

5. Complexity Analysis

analyze_complexity(project="my-project", path="src/main.py")

Available Tools

Project: register_project_tool, list_projects_tool, remove_project_tool
Language: list_languages, check_language_available
Files: list_files, get_file, get_file_metadata
AST: get_ast, get_node_at_position
Search: find_text, run_query
Symbols: get_symbols, find_usage
Analysis: analyze_project, get_dependencies, analyze_complexity
Queries: get_query_template_tool, build_query, adapt_query
Similar Code: find_similar_code

Supported Languages

Python, JavaScript, TypeScript, Go, Rust, C, C++, Swift, Java, Kotlin, Julia, APL, and many more via tree-sitter-language-pack.

Scientific Skill Interleaving

This skill connects to the K-Dense-AI/claude-scientific-skills ecosystem:

Tree Structures

etetoolkit [○] via bicomodule
- Tree parsing and traversal

Bibliography References

graph-theory: 38 citations in bib.duckdb

Cat# Integration

This skill maps to Cat# = Comod(P) as a bicomodule in the equipment structure:

Trit: 0 (ERGODIC)
Home: Prof
Poly Op: ⊗
Kan Role: Adj
Color: #26D826

GF(3) Naturality

The skill participates in triads satisfying:

(-1) + (0) + (+1) ≡ 0 (mod 3)

This ensures compositional coherence in the Cat# equipment structure.