schema-graph

schema-graph is a skill for Claude Code from PavloSEO/seohead-seotools. It costs 173 tokens per session (1,086 once invoked), scanned A, original, MIT.

A tool for checking and recommending Schema.org structured data, which is information added to a page to help search engines understand it. It works with JSON-LD and connected data graphs.

In plain words
What is it for?
Use it to recommend structured data for articles, products, services, local businesses, events, recipes, and FAQ pages, then check the markup already on the page.
Why use it?
It helps identify the right page type and find missing information that may prevent enhanced search results, such as article or product details.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to recommend structured data for articles, products, services, local businesses, events, recipes, and FAQ pages, then check the markup already on the page.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pavloseo/seohead-seotools/schema-graph
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.

Any agent
npx skills add PavloSEO/seohead-seotools --skill schema-graph
Clone the repo
git clone --depth 1 https://github.com/PavloSEO/seohead-seotools

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.

agentmods badge for schema-graph

README.md
[![agentmods](https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/schema-graph/github.svg)](https://agentmods.dev/skills/pavloseo/seohead-seotools/schema-graph)
Your own site
<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/schema-graph"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/schema-graph/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 schema-graph

Your own site · 80×15
<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/schema-graph"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/schema-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,086 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00173 $0.01086
Opus 5 $0.00086 $0.00543
Sonnet 5 $0.00035 $0.00217
Haiku 4.5 $0.00017 $0.00109

Measured 8d ago against content hash 8f36590ae21e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

schema-graph 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.

.claude/skills/schema-graph/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Schema Graph — Check Page Structured Data and Recommend a Graph

Two tools work as a pair: schema-build identifies the page type and recommends a connected @graph (what to add), while schema-check validates the markup that is already present. The first builds; the second checks—not the other way around.

When to use it

  • The user asks to check or create markup, JSON-LD, Schema.org, or rich results.
  • A general audit (seo-deep-audit) has reached the structured-data section.
  • A page does not produce a rich result even though it contains qualifying content—find out what is missing.

Workflow (default: build → check → compare)

Step 1. Recommend a graph. One command provides the type classifier, a ready-to-use @graph, and a diff:

seohead schema-build --url https://example.com/page

Read these fields carefully: inferred_type, confidence, signals[] (the basis for the decision), alternatives[], and note. If confidence: low and a note is present, the classifier is uncertain; do not present the type as a fact. Either inspect the page visually or have a person specify the type with --type Product (or Service, Article, LocalBusiness, and so on).

Step 2. Validate what is already on the page.

seohead schema-check --url https://example.com/page

These are two different layers: entities[].errors/warnings covers the Schema.org vocabulary (inheritance, deprecated/pending terms, and dangling @id references), while rich_results[] covers rich-result eligibility and missing_required. graph covers connectivity: islands and is_graph.

Step 3. Compare what the site promises with what its markup declares. Compare page facts (facts: price, rating, article date, H1, OG, and sameAs) with existing_jsonld. Any mismatch is a finding: for example, a price is visible but offers is absent from the JSON-LD, or datePublished in the markup does not match article:published_time. diff_vs_existing.addable_now lists fields that can be populated immediately from visible facts.

Read the full file on GitHub · 83 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 83 lines · 173 tokens per session scan A 8f36590ae21e

Subscribe to this mod's changes

schema-graph is a skill published in the GitHub repository PavloSEO/seohead-seotools (0 stars, last pushed 5d ago), licensed MIT. It adds 173 tokens to every session and 1,086 once invoked, about $0.0009 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 skills, from other repositories