What is seo-graph AGENTS.md?

Project instructions for seo-graph, a toolkit that helps websites describe their content to search engines and AI agents. It creates linked Schema.org data, Markdown versions of pages, route information, and related delivery files.

Use them when building or changing seo-graph or its Astro integration, including schema graphs, page Markdown, llms.txt, route manifests, and content negotiation.

They reduce mistakes when adding structured website data or agent-readable content and clarify which entities to use for different site types.

How iannuttall/seo-graph configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to iannuttall/seo-graph. 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/iannuttall/seo-graph/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/iannuttall/seo-graph

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/iannuttall/seo-graph/agents-md/github.svg)](https://agentmods.dev/instructions/iannuttall/seo-graph/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/iannuttall/seo-graph/agents-md"><img src="https://agentmods.dev/badge/instructions/iannuttall/seo-graph/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/iannuttall/seo-graph/agents-md"><img src="https://agentmods.dev/badge/instructions/iannuttall/seo-graph/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21,733 This file is loaded in full into every session.

When invoked 21,733 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 89% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.21733	$0.21733
Opus 5.5	$0.08693	$0.08693
Sonnet 5.5	$0.04347	$0.04347
Haiku 4.5	$0.02173	$0.02173

Measured 16d ago against content hash 7aea988302d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

seo-graph 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 16d 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.

Origin

This is a copy

89% identical to seo-graph AGENTS.md — 1,190 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 2,714 lines

How it starts

The opening of the file, as written. The whole thing — 2,714 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — seo-graph

This file is for AI coding agents (Claude Code, Cursor, Copilot, etc.) building sites that use @iannuttall/seo-graph-core and/or @iannuttall/seo-graph-astro. It explains what the library does, how the pieces fit together, and which schema.org entities to use for every common site type.

What this library does

seo-graph makes a site legible to AI agents and search engines from one toolkit, in two layers:

Schema graphs. Valid, linked schema.org JSON-LD @graph arrays from typed inputs. Instead of hand-writing JSON-LD (error-prone) or copying snippets from schema.org docs (inconsistent), you call piece builders that return strongly-typed entities, then wrap them in a @graph envelope.
Agent markdown. Deterministic Markdown representations of every page — rendered from the built HTML for arbitrary pages (with a strict exclusion contract so decorative markup never leaks) and straight from the source entry for content-collection pages — plus llms.txt, a route manifest, IndexNow, and an HTTP content-negotiation handler so agents can request Accept: text/markdown at the canonical URL.

Two packages:

@iannuttall/seo-graph-core — Pure TypeScript, no framework dependency. Piece builders, ID factory, graph assembler, deduplication, the built-HTML → Markdown renderer, collection markdown renderer, route mapping, manifests, llms.txt, git-based lastmod, IndexNow manifest hashing. Use this from any runtime.
@iannuttall/seo-graph-astro — Astro layer. agentMarkdown() build integration, collection markdown endpoints, schema endpoints and schema map, IndexNow key route, RFC 9727 api-catalog, Zod content helpers, and a Cloudflare Worker content-negotiation handler (./cloudflare subpath).

Portions of the schema layer derive from jdevalk/seo-graph (MIT, see NOTICE). The agent-markdown pipeline is original work first built for seoskill.dev.

Read the full file on GitHub · 2,714 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.

16d ago Changed · +5 lines · +66 tokens per session 7aea988302d4
1mo ago Changed · +19 lines · +262 tokens per session bccfcb0d95a5
2mo ago First seen · 2,690 lines · 21,405 tokens per session scan A 6674cea5825f

Subscribe to this mod's changes

seo-graph AGENTS.md is an instructions file published in the GitHub repository iannuttall/seo-graph (26 stars, last pushed 4d ago), licensed MIT. It adds 21,733 tokens to every session, about $0.0869 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to seo-graph AGENTS.md, differing in 1,190 lines, and is treated as a copy.

Marketing and SEO agent-ready ai-agents astro astro-integration cloudflare-workers content-negotiation

seo-graph AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
seo-graph AGENTS.mdiannuttall/seo-graph	Instructions file	26	4d ago	MIT	A	21,733	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

seo-graph: Instructions file for Codex