agentsclimarketplace

Code review graph

Skill SamyakJhaveri/loam/cultivation/marketplace/code-review-graph/skills/code-review-graph

Copier template that bootstraps AI-agent-optimized project setups: layered context routing, curated skills, and an enforced validation gate — synced across projects.

Install
npx -y skills add SamyakJhaveri/loam --skill code-review-graph

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

GraphRAG-powered code review with blast-radius analysis via Tree-sitter AST. MCP server. Recommended for 500+ file codebases.

SKILL.md

1.3 KB, 274 tokens by cl100k_base, as published. Nobody here has run it

code-review-graph

GraphRAG-powered code review that uses Tree-sitter AST analysis to scope blast radius for diffs and detect architectural hotspots. 24-language support.

Upstream: https://github.com/tirth8205/code-review-graph

Install

pip install code-review-graph

MCP Server Setup

Add to your project's .mcp.json:

{
  "code-review-graph": {
    "type": "stdio",
    "command": "uvx",
    "args": ["code-review-graph", "--stdio"],
    "env": {}
  }
}

The MCP server exposes tools for graph-based code analysis.

How It Complements Loam

  • code-review-graph decides WHICH code to look at (blast-radius scoping)
  • /multi-review decides WHAT to say about it (quality analysis)

Use code-review-graph first to identify affected files, then feed those into /multi-review for focused critique.

Requirements

  • Python 3.10+
  • Tree-sitter (auto-installed)
  • Optional: sentence-transformers, igraph

Notes

  • MIT license, actively maintained
  • No benefit below ~200 files — graph overhead exceeds savings
  • Windows has known deadlock issues
  • Still Beta with many open issues

Gives 0 of the 12 instructions most mcp tooling skills give in 274 tokens

Counted across 638 of the 750 authors here whose files we hold, read 2026-08-06

  • create ten complex read-only evaluation questionsin 71 of 638, across 17 files
  • test servers using MCP Inspectorin 60 of 638, across 18 files
  • provide actionable error messagesin 56 of 638, across 14 files
  • prioritize comprehensive API coverage over specific workflowsin 54 of 638, across 12 files
  • use TypeScript and Streamable HTTP for remote serversin 53 of 638, across 7 files
  • define structured output schemas where possiblein 51 of 638, across 9 files
  • use Zod or Pydantic for input schemasin 48 of 638, across 6 files
  • fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
  • load framework documentation using WebFetchin 45 of 638, across 3 files
  • verify each evaluation answer independentlyin 45 of 638, across 3 files
  • implement API client with authentication and paginationin 45 of 638, across 3 files
  • Define input schemas with validationin 28 of 638, across 10 files

Said here and by no other author read

  • install code-review-graph
  • use code-review-graph before multi-review
  • identify affected files with graph analysis
  • feed affected files into multi-review

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.