A command that reviews structured data: extra machine-readable information in a website’s code that search engines use to understand pages. It checks JSON-LD and related markup for valid types, required fields and possible rich search-result displays.

Use it to inspect or generate structured data for websites, articles, products and other page types, and to identify rich-result opportunities.

It helps find missing or invalid search metadata that can prevent search engines from understanding a page correctly. It can work from a supplied URL or the current project files.

seo-schema — Command for Claude Code by bestdeejay-design

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.

Clone the repo

git clone --depth 1 https://github.com/bestdeejay-design/agent-skills

Made for: Claude Code.

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/commands/bestdeejay-design/agent-skills/seo-schema.svg)](https://agentmods.dev/commands/bestdeejay-design/agent-skills/seo-schema)

Your own site

<a href="https://agentmods.dev/commands/bestdeejay-design/agent-skills/seo-schema"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-schema.svg" alt="Measured on agentmods" height="20"></a>

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 880 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.00880
Opus 5	$0.00028	$0.00440
Sonnet 5	$0.00011	$0.00176
Haiku 4.5	$0.00006	$0.00088

Measured 8d ago against content hash 95a550dbab1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

seo-schema 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 8d 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.

skills/seo-schema/commands/seo-schema.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Schema.org and structured data specialist. Analyze the project to audit the existing JSON-LD and identify rich snippet opportunities that improve CTR in search results.

Operating mode

If the user provides a URL (e.g. /seo-schema https://example.com):

Fetch the URL and extract all <script type="application/ld+json"> blocks
Also extract Microdata attributes (itemscope, itemtype, itemprop) if present
Apply the same validation analysis and generate corrected JSON-LD

Without a URL → analyze files of the current project in the file system.

1. Find existing structured data

Search in all files:

<script type="application/ld+json"> blocks
itemscope, itemtype, itemprop attributes (Microdata — deprecated)
Configuration files that generate schema dynamically

2. Schema types by page type

Identify the type of each page and verify it has the correct schema:

Website / Home

{
  "@type": "WebSite",
  "name": "...",
  "url": "...",
  "potentialAction": { "@type": "SearchAction" }
}

Article / Blog

Required fields: headline, author, datePublished, image Recommended fields: dateModified, publisher, description

Organization / Local Business

Required fields: name, address, telephone Recommended fields: openingHours, geo, priceRange, image

Product / E-commerce

Required fields: name, offers (with price, priceCurrency, availability) Recommended fields: image, description, brand, aggregateRating

FAQ

Format: FAQPage with mainEntity → array of Question + acceptedAnswer

HowTo

Fields: name, step (array of HowToStep with text)

Review / AggregateRating

Fields: ratingValue, reviewCount, bestRating

Breadcrumb

Format: BreadcrumbList with itemListElement → ListItem with position, name, item

3. Validation

For each schema found, verify:

Are all fields required by Google present?
Are the data types correct (string vs URL vs date)?
Are the URLs absolute (not relative)?
Are dates in ISO 8601 format?
Do images have an absolute URL and minimum dimensions (1200x630)?

Read the full file on GitHub · 114 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.

8d ago First seen · 114 lines · 57 tokens per session scan A 95a550dbab1c

Subscribe to this mod's changes

seo-schema is a command published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 880 once invoked, about $0.0003 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.

Marketing and SEO Productivity Python ai-agents automation opencode presentation-generator

seo-schema