agentic-graph-rag-skills: Instructions file for Codex

AGENTS.md

agentic-graph-rag-skills AGENTS.md is an instructions file for Codex, OpenCode from AnthonyAlcaraz/agentic-graph-rag-skills. It costs 1,137 tokens per session, scanned C, original, MIT.

A set of instructions and reusable skills for AI coding agents working with Agentic GraphRAG, a method for combining graph databases with document search and AI agents.

In plain words
What is it for?
It helps agents understand the repository, summarize its contents, and apply the included GraphRAG design patterns and Python utilities.
Why use it?
It gives agents a consistent way to read and work with the repository, reducing confusion when using its 51 chapter-based skills across several coding tools.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Gemini CLI.

This is AnthonyAlcaraz/agentic-graph-rag-skills's own configuration. It tells Codex and OpenCode how to work on agentic-graph-rag-skills 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 agentic-graph-rag-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AnthonyAlcaraz/agentic-graph-rag-skills. 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/AnthonyAlcaraz/agentic-graph-rag-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-skills

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 agentic-graph-rag-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/anthonyalcaraz/agentic-graph-rag-skills/agents-md/github.svg)](https://agentmods.dev/instructions/anthonyalcaraz/agentic-graph-rag-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/anthonyalcaraz/agentic-graph-rag-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/anthonyalcaraz/agentic-graph-rag-skills/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 agentic-graph-rag-skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/anthonyalcaraz/agentic-graph-rag-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/anthonyalcaraz/agentic-graph-rag-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,137 This file is loaded in full into every session.
When invoked 1,137 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.01137 $0.01137
Opus 5 $0.00568 $0.00568
Sonnet 5 $0.00227 $0.00227
Haiku 4.5 $0.00114 $0.00114

Measured 9d ago against content hash 4e96976ee3f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

agentic-graph-rag-skills AGENTS.md scanned grade C with 1 finding 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 9d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- ai-reading-instructions:start -->
AGENTS.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - How an AI Should Read This Repository

This file is the repository's machine-readable reading contract: it tells an AI agent how to read, summarize, and use this repo. Generated by the ai-reading-instructions skill, whose concept comes from Google DeepMind's "From AGI to ASI" report (arXiv:2606.12683) - a paper that opens by telling an AI how to read it.

For AI Agents Reading This

agentic-graph-rag-skills — companion skills repo for the O'Reilly book Agentic GraphRAG - 51 chapter-distilled, multi-harness skills across all 8 chapters, one deep pedagogical notebook per chapter

Audience: AI coding agents (Claude Code, Cursor, Gemini CLI, Windsurf, OpenCode) and the humans steering them

What this is: A public MIT repo of 51 practical skills distilled from all eight chapters (Ch1-Ch8) of Agentic GraphRAG (O'Reilly, by Anthony Alcaraz and Sam Julien; https://www.oreilly.com/library/view/agentic-graphrag/9798341623163/). Each skill is one architectural primitive from one chapter, packaged as a 7-section SKILL.md + a stdlib-only Python lib.py + an argparse cli.py. Multi-harness: the SKILL.md works in Claude Code / Cursor / Gemini CLI / Windsurf / OpenCode, and the CLI runs from cron / CI / scripts with zero pip installs. Each chapter has one deep pedagogical notebook (notebooks/chN-.ipynb) that teaches the chapter's primitives against a moto-mocked fictional AWS DevOps latency-investigation scenario (account 123456789012); six earlier spike-.ipynb seam-validation notebooks are also retained.

How to summarize it:

  • Lead with the structure: 51 skills across 8 chapters (crisis/Ch1 5, architecture/Ch2 3, knowledge-representation/Ch3 8, memory/Ch4 8, reasoning-planning/Ch5 6, tool-orchestration/Ch6 9, self-evolution/Ch7 7, optimization/Ch8 5), each a folder under skills///. The Ch1 folder is named skills/crisis/ for historical reasons.
  • Name the skill anatomy: SKILL.md (7-section + Source Attribution to the book chapter), lib.py (pure-Python, production swaps marked TODO), cli.py (--help prints the SKILL.md description, a benchmark subcommand runs self-checks; one older skill, mcp-gateway-two-meta-tools, names its self-check prompt-budget instead of benchmark).
  • Say it is a companion to the book, not the book: 'read the book for the theory, run these skills for the practice.'
  • Note the running example: a DevOps latency investigation in a fictional AWS account 123456789012, mocked via moto so notebooks run with no credentials.

Read the full file on GitHub · 44 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. 9d ago First seen · 44 lines · 1,137 tokens per session scan C 4e96976ee3f2

Subscribe to this mod's changes

agentic-graph-rag-skills AGENTS.md is an instructions file published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,137 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens