GEO Optimizer is a toolkit that checks whether AI answer services such as ChatGPT, Perplexity, Gemini, Claude, and Google AI Overviews can find, interpret, and cite a website. It helps people audit and improve a site's visibility in AI-generated answers through a command-line tool, Python library, MCP server, GitHub Action, or Astro integration.
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/Auriti-Labs/geo-optimizer-skillnpx agentmods add rules/auriti-labs/geo-optimizer-skill/cursorWrote 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/rules/auriti-labs/geo-optimizer-skill/cursor)<a href="https://agentmods.dev/rules/auriti-labs/geo-optimizer-skill/cursor"><img src="https://agentmods.dev/badge/rules/auriti-labs/geo-optimizer-skill/cursor/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/rules/auriti-labs/geo-optimizer-skill/cursor"><img src="https://agentmods.dev/badge/rules/auriti-labs/geo-optimizer-skill/cursor.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 | $0.00000 | $0.01140 |
| Opus 5.5 | $0.00000 | $0.00456 |
| Sonnet 5.5 | $0.00000 | $0.00228 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
cursor 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 13d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
robots.txt
Always include these user-agents with Allow: /:
- Critical citation bots:
OAI-SearchBot,PerplexityBot,ClaudeBot,Google-Extended - Also include:
GPTBot,ChatGPT-User,anthropic-ai,claude-web,Googlebot,Bingbot,Applebot,Applebot-Extended,meta-externalagent,Bytespider,cohere-ai,DuckAssistBot
Never block critical citation bots even if blocking training bots.
Use Disallow: / for GPTBot and anthropic-ai to block training while keeping citations.
Always keep OAI-SearchBot, ClaudeBot, PerplexityBot at Allow: / for citation access.
llms.txt
Always include these elements in /llms.txt:
- H1: site name (required)
- Blockquote immediately after H1: one-sentence site description (required)
- Sections matching site structure:
## Tools,## Articles,## Docs, etc. - Every link must have a colon + brief description:
- [Title](URL): Description
Never create an llms.txt without the H1 + blockquote pair.
Never list URLs without descriptions.
Always place llms.txt at the site root (/llms.txt), not in a subdirectory.
Keep llms.txt under 200 lines — AI crawlers prefer concise files.
Generate llms.txt with: geo llms --base-url URL --site-name NAME --description DESC --output ./public/llms.txt
JSON-LD Schema
Always add WebSite schema to every page's <head>.
Always add WebApplication schema to tool and calculator pages.
Always add FAQPage schema to any page with Q&A content.
Never omit the "url" field in any schema type.
Never use schema without the "@context": "https://schema.org" field.
Use WebSite for: all pages (global schema).
Use WebApplication for: tools, calculators, apps, generators.
Use FAQPage for: FAQ sections, how-to pages, question-based content.
Use Article for: blog posts, guides, tutorials.
Inject schema automatically: geo schema --type TYPE --url URL
Types available: website, webapp, faq, article, organization, breadcrumb
Content (Princeton GEO Methods)
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.
- 13d ago Changed · +2 lines 7c70c722742b
- 1mo ago First seen · 93 lines · 0 tokens per session scan A c0fa1d7b5f31
cursor is a cursor rule published in the GitHub repository Auriti-Labs/geo-optimizer-skill (1,151 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,140 tokens. 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
as-contract-cast-smell
// ❌ WRONG — bypasses the family ContractSerializer seam const contract = JSON.parse(raw) as Contract; const contract = JSON.parse(raw) as Contract .