Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/techhorizonlabs/thl-opennpx agentmods add skills/techhorizonlabs/thl-open/geo-schemaWrote 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.
[](https://agentmods.dev/skills/techhorizonlabs/thl-open/geo-schema)<a href="https://agentmods.dev/skills/techhorizonlabs/thl-open/geo-schema"><img src="https://agentmods.dev/badge/skills/techhorizonlabs/thl-open/geo-schema/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.
<a href="https://agentmods.dev/skills/techhorizonlabs/thl-open/geo-schema"><img src="https://agentmods.dev/badge/skills/techhorizonlabs/thl-open/geo-schema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00026 | $0.03736 |
| Opus 5 | $0.00013 | $0.01868 |
| Sonnet 5 | $0.00005 | $0.00747 |
| Haiku 4.5 | $0.00003 | $0.00374 |
Grade A, and why
geo-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 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.
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.
This is a copy
94% identical to geo-schema — 6 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.
How it starts
The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Schema & Structured Data
Purpose
Structured data is the primary machine-readable signal that tells AI systems what an entity IS, what it does, and how it connects to other entities. While schema markup has traditionally been about earning Google rich results, its role in GEO is fundamentally different: structured data is how AI models understand and trust your entity. A complete entity graph in structured data dramatically increases citation probability across all AI search platforms.
How to Use This Skill
- Fetch the target page HTML using
fetch_page.py(see note below) - Detect all existing structured data (JSON-LD, Microdata, RDFa)
- Validate detected schemas against Schema.org specifications
- Identify missing recommended schemas based on business type
- Generate ready-to-use JSON-LD code blocks
- Output GEO-SCHEMA-REPORT.md
Step 1: Detection
IMPORTANT: WebFetch converts HTML to markdown and strips <head> content, which removes JSON-LD blocks. Use fetch_page.py instead:
python3 scripts/fetch_page.py <url> page
The output includes a structured_data array with all parsed JSON-LD blocks from the page.
Scan for JSON-LD
Look for <script type="application/ld+json"> blocks in the HTML. Parse each block as JSON. A page may contain multiple JSON-LD blocks — collect all of them.
Scan for Microdata
Look for elements with itemscope, itemtype, and itemprop attributes. Map the hierarchy of nested items. Note: Microdata is harder for AI crawlers to parse than JSON-LD. Flag a recommendation to migrate to JSON-LD if Microdata is the only format found.
Scan for RDFa
Look for elements with typeof, property, and vocab attributes. Similar to Microdata — recommend migration to JSON-LD.
Priority Order
JSON-LD is the strongly recommended format for GEO. Google, Bing, and AI platforms all process JSON-LD most reliably. If the site uses Microdata or RDFa exclusively, flag this as a high-priority migration.
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.
- 9d ago First seen · 373 lines · 26 tokens per session scan A 520e55962f47
geo-schema is a skill published in the GitHub repository techhorizonlabs/thl-open (15 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 3,736 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to geo-schema, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
geo-schema
Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup.
geo-schema
Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup.
geo-schema
Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup.
geo-visibility
Get cited and recommended by AI engines (ChatGPT, AI Overviews and AI Mode, Perplexity, Claude, Gemini). Input: a page or piece of content. Output: passage-level citability fixes (answer-first H2 blocks, self-contained chunks, definitions, sourced stats, comparison tables), a 5-pillar GEO score (0-100), an AI-crawler…
seo-content-collection-page
Optimize e-commerce collection, category, and product listing pages (PLPs) for Google and AI assistants. Input: a collection or category page (Shopify, WooCommerce, Magento, BigCommerce, PrestaShop, or custom). Output: a bottom-of-page SEO text block, faceted-navigation and filter URL control, pagination canonicals…
geo-tracking
Measure AI visibility without paid tools or API keys. Input: your site (GA4 and server logs) and a buyer prompt panel. Output: GA4 AI-traffic reporting (custom channel group plus referrer regex above Referral), monthly brand mention rate, citation rate, and share of voice versus competitors across ChatGPT, Perplexity…