graph-engineering-crash-course AGENTS.md

graph-engineering-crash-course AGENTS.md is an instructions file for Codex, OpenCode from ayeshakhalid192007-dev/graph-engineering-crash-course. It costs 981 tokens per session, scanned A, original, MIT.

Repository instructions for a graph-engineering course, including its master plan, source records, page structure, and commit rules. Graph engineering concerns systems that model relationships as connected nodes and links.

In plain words
What is it for?
They guide agents working on course documentation, checking the master plan and sources, following the required page format, and making small focused commits.
Why use it?
They protect important project specifications and attribution records while keeping course pages original, consistent, and manageable.

Instructions file for CodexOpenCode

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/ayeshakhalid192007-dev/graph-engineering-crash-course/agents-md
Clone the repo
git clone --depth 1 https://github.com/ayeshakhalid192007-dev/graph-engineering-crash-course

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 graph-engineering-crash-course AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ayeshakhalid192007-dev/graph-engineering-crash-course/agents-md.svg)](https://agentmods.dev/instructions/ayeshakhalid192007-dev/graph-engineering-crash-course/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ayeshakhalid192007-dev/graph-engineering-crash-course/agents-md"><img src="https://agentmods.dev/badge/instructions/ayeshakhalid192007-dev/graph-engineering-crash-course/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 981 This file is loaded in full into every session.
When invoked 981 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 5.1 $0.00981 $0.00981
Opus 5 $0.00491 $0.00491
Sonnet 5 $0.00196 $0.00196
Haiku 4.5 $0.00098 $0.00098

Measured 5d ago against content hash 01168e8f8c8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

graph-engineering-crash-course 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 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.

AGENTS.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Operating rules for any agent — human-directed or autonomous, Claude Code, OpenCode, or anything else — that touches this repository. These rules apply regardless of which tool is doing the work. If you are looking for tool-specific notes, see CLAUDE.md; the rules below sit underneath it and take priority whenever the two seem to disagree.

1. graph-plan.md is the master spec, and it is human-only

graph-plan.md is the single source of truth for what this course is and how it is built. No agent, loop, or automated process may edit it. It changes only by direct action of the human owner of this repository. If a plan, a page, or a piece of tooling seems to conflict with graph-plan.md, the plan wins and the conflict gets flagged for the human to resolve — the fix is never to quietly bring the spec in line with whatever the agent already did.

The same protection covers the source table in resources/sources.md: the ten entries there (see below) are load-bearing attribution records, not editorial copy, and no automated process may add to, remove from, or reword that table.

2. The originality policy is not optional

Every docs/ page in this course is written from a contributor's own understanding of an idea, never with a source page open next to the editor and never as a light rewording of someone else's sentences. This isn't a style preference — it's mechanically enforced. Before any docs/ change is committed, scripts/originality-check.mjs must run clean. The full policy, including the quoting exception for the one attributed statement in this course, lives in graph-plan.md §2.1; the record of exactly which idea came from which of the ten sources, and why it earned a place here, lives in resources/sources.md. An agent that cannot make a page pass the originality check should stop and rewrite from a blank page, not fight the checker with synonym substitution — synonym-swapped plagiarism is still plagiarism, and the checker is not the only line of defense; a human reviewer reads for it too.

Read the full file on GitHub · 77 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 · 77 lines · 981 tokens per session scan A 01168e8f8c8c

Subscribe to this mod's changes

graph-engineering-crash-course AGENTS.md is an instructions file published in the GitHub repository ayeshakhalid192007-dev/graph-engineering-crash-course (5 stars, last pushed 10d ago), licensed MIT. It adds 981 tokens to every session, about $0.0049 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 2026-08-31.

Related

Other instructions, from other repositories

crystal AGENTS.md

Instructions for stravu/crystal, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

stravu/crystal · 702 tokens

Warden-AI GEMINI.md

Gemini CLI instructions for rynald0cst0ltziam/Warden-AI, covering warden — context governance and verification layer, session start (important — do this first), layer 1: before starting work — context selection, layer 2: during work — tool output pruning and enforcement hooks (automatic).

rynald0cst0ltziam/Warden-AI · 4,292 tokens

agents-chat copilot-instructions.md

Copilot instructions for huanyingtianhe/agents-chat, covering copilot instructions, build & run, tests (playwright e2e), architecture and key components.

huanyingtianhe/agents-chat · 1,522 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 · 5,182 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens