code-graph-context CLAUDE.md

code-graph-context CLAUDE.md is an instructions file for coding agents from andrew-hernandez-paragon/code-graph-context. It costs 2,416 tokens per session, scanned A, original, MIT.

An MCP server that turns a TypeScript codebase into a searchable graph of files, code elements, and their relationships. MCP is a standard way for tools to provide context to an AI assistant.

In plain words
What is it for?
Use it to search a TypeScript project, follow connections between code elements, inspect the effects of changes, and provide structured code context to an AI assistant.
Why use it?
It helps an AI assistant understand how code is connected instead of searching files as unrelated text. The graph can support semantic search, relationship tracing, and impact analysis.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/andrew-hernandez-paragon/code-graph-context/claude-md
Clone the repo
git clone --depth 1 https://github.com/andrew-hernandez-paragon/code-graph-context

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-graph-context CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/andrew-hernandez-paragon/code-graph-context/claude-md.svg)](https://agentmods.dev/instructions/andrew-hernandez-paragon/code-graph-context/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/andrew-hernandez-paragon/code-graph-context/claude-md"><img src="https://agentmods.dev/badge/instructions/andrew-hernandez-paragon/code-graph-context/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,416 This file is loaded in full into every session.
When invoked 2,416 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02416 $0.02416
Opus 5 $0.01208 $0.01208
Sonnet 5 $0.00483 $0.00483
Haiku 4.5 $0.00242 $0.00242

Measured 5d ago against content hash f1a978de4f27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-graph-context CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Code Graph Context is an MCP (Model Context Protocol) server that builds code graphs to provide rich context to LLMs. It parses TypeScript codebases using AST analysis (ts-morph), stores the graph in Neo4j with vector embeddings, and provides semantic search and graph traversal tools.

Build & Development Commands

npm run build          # Compile TypeScript to dist/
npm run dev            # Watch mode compilation
npm run mcp            # Run MCP server: node dist/mcp/mcp.server.js
npm run lint           # ESLint with auto-fix
npm run format         # Prettier formatting

Architecture

Data Flow

TypeScript Project → AST Parser (ts-morph) → Graph Nodes/Edges → Neo4j + Vector Embeddings → MCP Tools

Key Directories

  • src/mcp/ - MCP server entry point and tools
    • mcp.server.ts - Server initialization
    • tools/ - 7 MCP tools (search_codebase, traverse_from_node, impact_analysis, etc.)
    • handlers/ - Business logic for graph generation and traversal
  • src/core/ - Core business logic
    • parsers/typescript-parser.ts - Main AST parser (~1000 lines)
    • config/schema.ts - Core graph schema definitions
    • config/nestjs-framework-schema.ts - NestJS semantic patterns
    • embeddings/ - OpenAI embeddings and NL-to-Cypher services
  • src/storage/neo4j/ - Neo4j driver and queries

Dual-Schema System

The parser uses two schema layers:

  1. Core Schema (AST-level): ClassDeclaration, MethodDeclaration, PropertyDeclaration, ImportDeclaration, etc.
  2. Framework Schema (Semantic): Controller, Service, Module, Guard, Repository, etc. (NestJS patterns)

Nodes have both coreType (AST) and semanticType (framework interpretation).

Multi-Project Support

The system supports multiple projects in a single Neo4j database through project isolation:

  • Project ID Format: proj_<12-hex-chars> (e.g., proj_a1b2c3d4e5f6)
  • Auto-generation: If not provided, projectId is generated deterministically from the project path
  • Explicit Override: Pass projectId to parse_typescript_project to use a custom ID
  • Isolation: All queries are automatically scoped to the project - nodes from different projects never interfere

Read the full file on GitHub · 216 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 216 lines · 2,416 tokens per session scan A f1a978de4f27

Subscribe to this mod's changes

code-graph-context CLAUDE.md is an instructions file published in the GitHub repository andrew-hernandez-paragon/code-graph-context (17 stars, last pushed 3mo ago), licensed MIT. It adds 2,416 tokens to every session, about $0.0121 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.