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 | $0.03966 |
| Opus 5.5 | $0.00024 | $0.01586 |
| Sonnet 5.5 | $0.00012 | $0.00793 |
| Haiku 4.5 | $0.00006 | $0.00397 |
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 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.
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 what it 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, no signup; Pro asks up to 25 buyer questions across seven engines on the schedule you choose, from a shared token balance, and its headline measure is the named share of saved answers (the two are complementary: readiness here, visibility there; see
docs/THL-GEO-METHOD.md). This composite is the open audit's own formula. It is not the product's AI Readiness score, which is built differently (five site signals, with the off-site Footprint scored separately). 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):
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.
- 16d ago Changed 4450a1a7590e
- 1mo 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 (18 stars, last pushed 16d ago), licensed MIT. It adds 60 tokens to every session and 3,966 once invoked, about $0.0002 per session on Opus 5.5. 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
seo-content-blog
Spec, audit, competitor benchmark and build for blog articles and the blog template, so a post ranks on Google and gets cited by AI engines (ChatGPT, Perplexity, AI Overviews). Input: a keyword, topic, draft or post URL. Phase 1 spec: BLOG rows on top of the common page spec, covering the 12-element answer-first…
seo-content-collection-page
Spec, audit, competitor benchmark and build for e-commerce collection, category and product listing pages (PLPs) on Shopify, WooCommerce, Magento, BigCommerce, PrestaShop or a custom store. Runs four phases: the collection spec (COL-01 to COL-24 plus the common rows), an audit of the live page with the bundled…
seo-content-product-page
Spec, audit, competitor benchmark and build for e-commerce product pages (PDPs), so they rank in Google and get recommended by the AI assistants that now link products directly. Input: a product page URL or a product brief (Shopify, WooCommerce, Magento, BigCommerce, PrestaShop, Wix, Webflow or custom). Runs four…
seo-content-service-page
Spec, audit, competitor benchmark and build for service pages and service landing pages (agencies, consultants, coaches, trades, clinics, law firms, SaaS), plus region and city pages. Input: a service, the business, a target area, the page URL if any. Runs four phases: the spec (SVC-01 to SVC-24 on top of the common C…
seo-local
Run spec, audit, competitor benchmark and build for local visibility, on the two assets a local business owns: the location page and the Google Business Profile, plus reviews and NAP citations. Spec: LOC, GBP, REV and CIT requirements with IDs. Audit: seoaudit.py and sectionaudit.py --type location on the page, a…
seo-content-comparison-page
Spec, audit, competitor benchmark and build for the bottom-funnel pages that capture buyers at the decision moment: 'X vs Y', 'alternatives to X', 'best X for Y', the comparison hub, and audience or segment pages ('for agencies', 'for freelancers'). Runs four phases: the CMP spec with stable IDs on top of the common…