code-review-graph

Name: code-review-graph
Availability: InStock
Author: nnkienn

Compute blast radii of AST graph changes for token-efficient code review.

1|Updated May 29, 2026

Search Tags:#code review #token efficiency #MCP integration #Tree-sitter #AST graph

Ready to run

npx skills add https://github.com/nnkienn/Nyxara-core --skill code-review-graph-nnkienn

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: code-review-graph
Source: https://github.com/nnkienn/Nyxara-core/tree/main/.skills/skills/code-review-graph
Command: npx skills add https://github.com/nnkienn/Nyxara-core --skill code-review-graph-nnkienn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tree-sitter, sqlite, pymysql, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Code-review-graph solves the problem of inefficient code reviews by providing AI assistants with context maps of codebase structures, reducing the amount of token usage significantly.

Core Features & Use Cases

Token-Efficient Code Reviews: By computing blast radii of changes instead of reading entire codebases, the Skill reduces AI assistant token usage by 6.8x to 49x on average.
Tree-sitter AST Graphs: Parses codebases into an AST graph using Tree-sitter, storing the results in a SQLite database for efficient structural analysis.
Use Case: For instance, in a large monorepo, if you modify a function in the 'auth' module, code-review-graph will provide only the files impacted by that change, significantly reducing the number of tokens used.

Quick Start

Use the code-review-graph command to build the graph for your project, and let your AI assistant review changes in context with minimal token usage.

Frequently Asked Questions about code-review-graph

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I reduce token usage for AI code review in a large monorepo?▼

Reduce AI code review token usage by computing blast radii of changes in an AST graph instead of reading entire codebases, cutting token consumption by 6.8x to 49x on average. This approach provides only impacted files to the AI assistant.

How does Tree-sitter AST graph analysis work for code review context?▼

Tree-sitter AST graph analysis parses your codebase structure into a SQLite database, enabling efficient structural queries. When you modify a function, it maps the blast radius to identify exactly which files are impacted by that specific change.

Can I use code-review-graph for codebases with less than 500 files?▼

Code-review-graph is optimized for codebases over 500 files, especially for multi-file changes in monorepos or complex modules. Smaller projects may not see significant token reduction benefits from blast radius analysis.

What dependencies do I need to run AST-based code review with SQLite?▼

You need Tree-sitter for parsing, SQLite for the graph database, and pymysql for database connectivity. The Skill uses minimal Python and MCP dependencies to maintain efficiency during structural analysis.

When should I use blast radius analysis instead of full codebase context for AI review?▼

Use blast radius analysis when reviewing multi-file changes in monorepos or complex modules where providing full codebase context would exceed token limits. It identifies only impacted files, making it ideal for large-scale codebases over 500 files.