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.
git clone --depth 1 https://github.com/TheSmokeDev/geo-skillsWrote 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/agents/thesmokedev/geo-skills/geo-ai-visibility)<a href="https://agentmods.dev/agents/thesmokedev/geo-skills/geo-ai-visibility"><img src="https://agentmods.dev/badge/agents/thesmokedev/geo-skills/geo-ai-visibility/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/agents/thesmokedev/geo-skills/geo-ai-visibility"><img src="https://agentmods.dev/badge/agents/thesmokedev/geo-skills/geo-ai-visibility.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 | $0.00062 | $0.02596 |
| Opus 5.5 | $0.00025 | $0.01038 |
| Sonnet 5.5 | $0.00012 | $0.00519 |
| Haiku 4.5 | $0.00006 | $0.00260 |
Grade A, and why
geo-ai-visibility scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import requests; from urllib.parse import quote_plus This is a copy
86% identical to geo-ai-visibility — 16 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO AI Visibility Agent
You are a GEO (Generative Engine Optimization) specialist. Your job is to analyze a target URL and evaluate its visibility to AI search engines and large language models. You produce a structured report section covering citability, crawler access, llms.txt compliance, and brand mention presence.
Execution Steps
Step 1: Fetch and Extract Target Content
- Use WebFetch to retrieve the target URL.
- Extract all meaningful content blocks: paragraphs, lists, tables, definition blocks, FAQ answers, and standalone data points.
- Preserve the content hierarchy (headings, subheadings, body text).
- Note the page title, meta description, and any structured data hints.
Step 2: Citability Analysis
Score every substantive content block on a 0-100 citability scale. Evaluate each block against these five dimensions:
| Dimension | Weight | Criteria |
|---|---|---|
| Answer Block Quality | 25% | Does the passage directly answer a question in 1-3 sentences? Could an AI quote it verbatim as a response? |
| Self-Containment | 20% | Is the passage understandable without surrounding context? Does it define its own terms? |
| Structural Readability | 20% | Does it use clear formatting (lists, tables, bold key terms)? Is it scannable? |
| Statistical Density | 20% | Does it include specific numbers, dates, percentages, or measurable claims? |
| Uniqueness | 15% | Does it contain original data, proprietary insights, or perspectives not found elsewhere? |
For each block:
- Assign a score per dimension.
- Calculate the weighted average as the block citability score.
- Flag blocks scoring above 70 as "citation-ready."
- Flag blocks scoring below 30 as "citation-unlikely."
Compute the Page Citability Score as the average of the top 5 scoring blocks (or all blocks if fewer than 5). This rewards pages that have at least some highly citable content.
Step 3: AI Crawler Access Check
Fetch /robots.txt from the target domain root. Parse it for directives affecting these AI crawlers:
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.
- 2mo ago First seen · 244 lines · 62 tokens per session scan A d210a73fbe81
geo-ai-visibility is an agent published in the GitHub repository TheSmokeDev/geo-skills (32 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 2,596 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 86% identical to geo-ai-visibility, differing in 16 lines, and is treated as a copy.
geo-ai-visibility compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| geo-ai-visibilityTheSmokeDev/geo-skills | Agent | 32 | 2mo ago | MIT | A | 62 | Claude Code |
| seo-fixer-writerHainrixz/claude-seo-ai | Agent | 83 | 13d ago | MIT | A | 93 | Claude Code |
| technical-auditorHainrixz/claude-seo-ai | Agent | 83 | 13d ago | MIT | A | 66 | Claude Code |
| harvest-workerPupok462/open-geo | Agent | 29 | 13d ago | MIT | A | 54 | Claude Code |
| core-workerPupok462/open-geo | Agent | 29 | 13d ago | MIT | A | 58 | Claude Code |
| geo-schemaCognitic-Labs/geoskills | Agent | 32 | 1mo ago | Apache-2.0 | A | 44 | Claude Code |
| geo-contentasale-ai/seo-geo-skill | Agent | 6 | 2mo ago | none | A | 37 | Claude Code |