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.
npx skills add PavloSEO/seohead-seotools --skill geo-aeo-auditgit clone --depth 1 https://github.com/PavloSEO/seohead-seotoolsWrote 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/pavloseo/seohead-seotools/geo-aeo-audit)<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/geo-aeo-audit"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/geo-aeo-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/pavloseo/seohead-seotools/geo-aeo-audit"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/geo-aeo-audit.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 | $0.00147 | $0.01059 |
| Opus 5 | $0.00073 | $0.00530 |
| Sonnet 5 | $0.00029 | $0.00212 |
| Haiku 4.5 | $0.00015 | $0.00106 |
Grade A, and why
geo-aeo-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 11d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO / AEO Audit — Website Visibility in AI Answers
Classic SEO concerns search results. GEO/AEO concerns whether a website appears in an answer when a user asks ChatGPT, Perplexity, or Gemini, and whether the AI provides a link. There are three levers:
- AI crawler access — which crawlers robots.txt allows or blocks, intentionally or accidentally.
- llms.txt — whether the website has a manifest for models and how useful it is.
- Content citability — whether the content is written so that an AI can answer with a link.
When to Use It
- A website is losing traffic from conventional search and wants a channel from AI answers.
- To check whether GPTBot was blocked accidentally.
- To launch llms.txt as a new entry point for models.
Workflow
Step 1. AI crawler access. One command reports the status of 18+ known bots:
seohead ai-bots-check --url https://example.com
Read summary.by_type: training (model training — Google-Extended, CCBot,
Bytespider), retrieval (answer retrieval — PerplexityBot, Claude-Web), and user
(a request on behalf of a user — ChatGPT-User). The usual decision is to allow
retrieval for visibility in answers and make a considered choice about training
because providing data for training may be undesirable. Bots with status: allowed_default were neither explicitly allowed nor explicitly blocked by the website;
they are allowed by default unless a general Disallow rule applies.
Step 2. llms.txt.
seohead llms-txt-check --url https://example.com --brand "SiteName"
There are 9 checkpoints: an H1, ≥3 sections, ≥3 links, a brand/category mention,
product/proof/docs pages, and a size of ≤60 KB. The result is a 0–10 score plus a letter
grade. A missing file produces ok: False and the finding “the website does not provide
AI with ready-to-use context.” --brand checks whether the brand name is mentioned.
Step 3. Content citability. The formal scorer uses 4 dimensions worth 25 points each:
seohead citability-check --url https://example.com/page # use the page text
seohead citability-check --input '{"text":"...excerpt..."}' # analyze an excerpt offline
The dimensions are answer blocks (self-contained paragraphs of 20–200 words that do not begin with context-dependent language), self-containment (no phrases such as “as mentioned above” that make an extracted passage meaningless), statistical density (numbers, percentages, and dates plus evidence markers per 100 words), and structure quality (headings, lists, TL;DR, and paragraph length). The result is a 0–100 score plus a letter grade.
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.
- 11d ago First seen · 82 lines · 147 tokens per session scan A 65e56efd00bf
geo-aeo-audit is a skill published in the GitHub repository PavloSEO/seohead-seotools (0 stars, last pushed 8d ago), licensed MIT. It adds 147 tokens to every session and 1,059 once invoked, about $0.0007 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.
Other skills, from other repositories
fire-your-seo-agency
A procedure for improving how a website appears in search engines and how AI answer systems find and cite it. It covers search, answer-engine, generative-AI, and Naver visibility.
geo-loop
Run one bounded eGEOagents loop iteration over a workspace domain - read the charter and fresh collector data, do ONE unit of work, write substrate artifacts, append one Timeline entry and one LOG line. Use for loop mode, /geo:loop, scheduled GEO runs, or continuous monitoring.
content-scoring
Score content against the 10 GEO criteria with evidence and prioritized fixes. Use when users ask to score, rate, evaluate, or estimate ranking strength.
competitive-analysis
Analyze AI-search competitors for a query and recommend ranking strategy. Use when users ask competitor analysis, who ranks, or competitive landscape.
validation-doctor
Check Brave Search and Chrome DevTools MCP availability and provide exact setup snippets. Use when validation dependencies are missing or uncertain.
geo-content-research
Researches what prompts people ask AI engines (ChatGPT, Gemini, Perplexity, Claude) about a product category and produces a prompts.csv artifact — a prioritized, strictly-schema'd list of the queries where the brand should be cited. Feeds the monitor workflow.