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-auditWrote 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-audit)<a href="https://agentmods.dev/skills/techhorizonlabs/thl-open/geo-audit"><img src="https://agentmods.dev/badge/skills/techhorizonlabs/thl-open/geo-audit/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-audit"><img src="https://agentmods.dev/badge/skills/techhorizonlabs/thl-open/geo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.03912 |
| Opus 5 | $0.00030 | $0.01956 |
| Sonnet 5 | $0.00012 | $0.00782 |
| Haiku 4.5 | $0.00006 | $0.00391 |
Grade A, and why
geo-audit 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.
How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Audit Orchestration Skill
Purpose
This skill performs a comprehensive Generative Engine Optimization (GEO) audit of any website. GEO is the practice of optimizing web content so that AI systems (ChatGPT, Claude, Perplexity, Gemini, etc.) can discover, understand, cite, and recommend it. This audit measures how well a site performs across all GEO dimensions and produces an actionable improvement plan.
What this composite is — and isn't. This score is a readiness measure: it reads public signals (content, schema, crawler access, off-page authority) and infers how citable and recommendable the site is. It does not query the AI engines to confirm the business is actually named in their answers. Read it as "how well-built for AI is this site," not "is this site in the answer right now." For the live outcome, run the free scan at areyoufoundbyai.com: two buyer questions on ChatGPT and Gemini, once, no signup; the trial and paid tiers ask up to 12 buyer questions across all seven engines, multi-sampled (the two are complementary: readiness here, visibility there; see
docs/THL-GEO-METHOD.md). Every dimension below carries a provenance tag; a[heuristic]tag means model judgement from signals, not a measured fact.
Key Insight
Traditional SEO optimizes for search engine rankings. GEO optimizes for AI citation and recommendation. Sites that score high on GEO metrics see 30-115% more visibility in AI-generated responses (Georgia Tech / Princeton / IIT Delhi 2024 study). The two disciplines overlap but have distinct requirements.
THL enhancements (this fork)
Tech Horizon Labs runs this audit as part of a three-layer method (see docs/THL-GEO-METHOD.md):
- External benchmark. Alongside the dimensional composite below, run the
agent-readiness-scanskill (THL-original) for Cloudflare's independentisitagentready.com0–100 score. Record both; on a re-audit, track the delta on each — the movement is the proof, not the first number. - Checklist. Work through
references/thl-audit-checklist.mdso no dimension is silently skipped and the same facts/scores stay consistent across every section. - Deliverable. Assemble the audit data and run
tools/audit-report-kit(THL-original) to produce a branded client PDF + compile-checked JSON-LD for the schema fixes — instead of leaving a raw markdown file.
What ships with it
1 file 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.
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 · 367 lines · 60 tokens per session scan A 92f99888df93
geo-audit is a skill published in the GitHub repository techhorizonlabs/thl-open (15 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 3,912 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 2026-08-30.
Other skills, from other repositories
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…
seo-content-product-page
Optimize e-commerce product pages (PDPs) for Google and for AI assistants that now recommend products directly. Input: a product page or description (Shopify, WooCommerce, Magento, BigCommerce, PrestaShop, Wix, Webflow, or custom). Output: a rewritten PDP with unique copy, FAQ and definition blocks, review and…
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…
seo-content-blog
Write blog articles that rank on Google and get cited by AI engines (ChatGPT, Perplexity, AI Overviews). Input: a keyword, topic, or existing draft. Output: a publish-ready article, outline, or brief built on a 12-element answer-first skeleton (question H2s, expert quotes, stats, FAQ, internal links, SERP-benchmarked…
seo-internal-linking
Design internal linking so authority flows to the pages that sell and every page stays crawlable. Input: a sitemap, an article, or a set of posts. Output: money-page mapping, orphan-page fixes, content silos and hub-and-spoke clusters, anchor-text variation, breadcrumb/menu/footer roles, and keyword cannibalization…