repo-graphrag-mcp: Instructions file for Codex

AGENTS.md

repo-graphrag-mcp AGENTS.md is an instructions file for Codex, OpenCode from yumeiriowl/repo-graphrag-mcp. It costs 1,315 tokens per session, scanned A, original, MIT.

A repository analysis tool that maps code and documentation into a searchable knowledge base. It combines relationships between code elements with text search.

In plain words
What is it for?
Use it to analyze a repository, ask questions about its code and documentation, and create implementation plans that fit the existing structure.
Why use it?
It helps answer questions about an unfamiliar codebase without relying only on filenames or isolated text matches. It can also account for how parts of the code are connected when planning changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is yumeiriowl/repo-graphrag-mcp's own configuration. It tells Codex and OpenCode how to work on repo-graphrag-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything repo-graphrag-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/myproject.

Reuse

Borrowing it

Nothing to install: this file belongs to yumeiriowl/repo-graphrag-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yumeiriowl/repo-graphrag-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/yumeiriowl/repo-graphrag-mcp

Made for: Codex, OpenCode.

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 repo-graphrag-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yumeiriowl/repo-graphrag-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/yumeiriowl/repo-graphrag-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/yumeiriowl/repo-graphrag-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yumeiriowl/repo-graphrag-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for repo-graphrag-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yumeiriowl/repo-graphrag-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yumeiriowl/repo-graphrag-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,315 This file is loaded in full into every session.
When invoked 1,315 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01315 $0.01315
Opus 5.5 $0.00526 $0.00526
Sonnet 5.5 $0.00263 $0.00263
Haiku 4.5 $0.00131 $0.00131

Measured 2mo ago against content hash 2cf2e0519caa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-graphrag-mcp AGENTS.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 2mo 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.

AGENTS.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo GraphRAG MCP Usage Guide

"Repo GraphRAG MCP" extracts entities (classes, functions, etc.) and relationships from repository code and documentation to build a knowledge graph. Vectorizes and indexes all text. Combines graph search and vector search to answer questions and generate implementation plans with understanding of code structure.

Prerequisites

  • Python 3.11 or higher
  • uv package manager
  1. Install dependencies:
cd repo-graphrag-mcp
uv sync
  1. Configure environment variables: Copy .env.example to create a .env file

Note: Assumes users have already set up their environment. Refer to repo-graphrag-mcp/.env.example only when MCP startup or operation errors occur.

Three Tools

  1. graph_create - Analyze repository to build/update knowledge graph and vector index
  2. graph_query - Answer questions about the repository using the knowledge graph
  3. graph_plan - Generate implementation plans with understanding of existing code structure

All tools are invoked with the graph: prefix in user requests.

Tool 1: graph_create

Purpose: Analyze a directory to build a knowledge graph and vector index.

Parameters:

  • read_dir_path (required): Absolute path to the directory to analyze
  • storage_name (optional): Name of the storage (default: "storage")

Usage Examples:

graph: /home/user/myproject my_project
graph: C:\projects\webapp webapp_storage
graph: /path/to/repo  # Uses default storage name "storage"

Behavior:

  • First run: Processes all files and creates storage
  • Subsequent runs: Processes only changed/new/deleted files (incremental update)
  • Storage is created relative to the MCP server directory

Processed File Types: Code files are fixed. Other types can be modified in .env.

  • Code: .py, .cpp, .h, .java, .rs, .c, .cs, .go, .rb, .js, .jsx, .kt, .kts, .ts, .tsx, .html, .htm, .css
  • Documents (default): .txt, .md, .rst, and special files: readme, changelog (case insensitive)
  • Excluded (default): pycache, .git, .github, .venv, node_modules, .DS_Store, Thumbs.db, robots.txt, bac, backup, temp, tmp

Read the full file on GitHub · 163 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. 2mo ago First seen · 163 lines · 1,315 tokens per session scan A 2cf2e0519caa

Subscribe to this mod's changes

repo-graphrag-mcp AGENTS.md is an instructions file published in the GitHub repository yumeiriowl/repo-graphrag-mcp (7 stars, last pushed 9mo ago), licensed MIT. It adds 1,315 tokens to every session, about $0.0053 per session on Opus 5.5. 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 2026-08-31.

Related

repo-graphrag-mcp AGENTS.md compared with instructions from other repositories

repo-graphrag-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
repo-graphrag-mcp AGENTS.mdyumeiriowl/repo-graphrag-mcpInstructions file79mo agoMITA1,315Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode