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 TheSmokeDev/geo-skills --skill geo-fanoutgit 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/skills/thesmokedev/geo-skills/geo-fanout)<a href="https://agentmods.dev/skills/thesmokedev/geo-skills/geo-fanout"><img src="https://agentmods.dev/badge/skills/thesmokedev/geo-skills/geo-fanout/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/thesmokedev/geo-skills/geo-fanout"><img src="https://agentmods.dev/badge/skills/thesmokedev/geo-skills/geo-fanout.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 | $0.00078 | $0.02268 |
| Opus 5 | $0.00039 | $0.01134 |
| Sonnet 5 | $0.00016 | $0.00454 |
| Haiku 4.5 | $0.00008 | $0.00227 |
Grade A, and why
geo-fanout 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 12d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query Fan-Out / Topic-Cluster Optimization Skill
Purpose
This skill optimizes a site for query fan-out -- the mechanism by which AI search engines rewrite a single user prompt into a cluster of sub-queries and retrieve sources per sub-query. Fan-out coverage is the 2026 meta-factor for AI citation: pages win citations by matching the sub-queries engines generate, not by ranking #1 for the head term. This skill maps a topic's sub-query space, audits how much of it the site covers, and engineers titles and URL slugs so pages survive the pre-read gatekeeping step.
Core Insight
Fan-out is the top-scoring citation factor in Zyppy's 23-factor meta-analysis: 9.3/10 (DigitalApplied synthesis of 54 studies, Jun 2026). Engines like Gemini 3 (Jan 2026) and ChatGPT decompose one prompt into multiple sub-queries, run each against their index, and cite the pages that best match each sub-query. The consequence is a collapsed dependence on organic rank:
- Only 38% of AIO-cited URLs rank in the organic top 10 -- down from 76% (Ahrefs, 863K SERPs / 4M URLs, Mar 2026).
- 31% of AIO citations come from positions 11-100, and 31% from beyond position 100 (same study).
Page-3 organic is NOT disqualifying. The fan-out is the small-site opening: a low-authority page that precisely answers one sub-query can be cited over a high-authority page that only covers the head term.
Win the cluster, not the head term.
How Fan-Out Works (Mechanism)
- User submits one prompt (e.g., "how much does SR-22 insurance cost in California?").
- The engine classifies whether to search at all (ChatGPT: only ~18-24% of prompts trigger search).
- The prompt is rewritten into a cluster of sub-queries -- eligibility, cost, process, location, and language variants of the underlying intent.
- Each sub-query is run against the engine's retrieval index (ChatGPT: Bing; Gemini/AIO: Google).
- Retrieved pages pass a pre-read gate on title, snippet, and URL before content is ever opened.
- The engine cites the best-matching pages across the cluster (~15-50% of retrieved URLs get cited; ⚠️ single source, SubscribePR Jul 2026).
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.
- 12d ago First seen · 155 lines · 78 tokens per session scan A d3746ee74d01
geo-fanout is a skill published in the GitHub repository TheSmokeDev/geo-skills (22 stars, last pushed 9d ago), licensed MIT. It adds 78 tokens to every session and 2,268 once invoked, about $0.0004 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
orangeo-ai-visibility-skill
Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans. Use when asked for a Claude Code skill, Codex skill, GEO skill, generative engine optimization skill, answer engine optimization skill, AI visibility audit, AI search visibility checker, llms.txt…
ganhuo-geo-engineer
Use this Skill when the user provides an existing article, product page, tutorial, FAQ, or knowledge note and wants to rebuild it into a GEO or AI-search-friendly content asset. Use it for old-content refresh, citation-readiness improvement, answer-first restructuring, GEO upgrades, and Ganhuo AI content workflows. Do…
ai-answer-trace
Ask Claude, ChatGPT, and Gemini a question and capture the full evidence trail behind each answer: the search queries each engine ran, the pages it retrieved, and the sources it cited. The raw material of GEO measurement. Needs AI engine API keys, not an Xpoz account.
geo-visibility-check
One-shot GEO audit: does your brand appear in Claude, ChatGPT, and Gemini answers for the buyer questions that matter? Runs a prompt panel through the engines with citation tracing and reports per-prompt verdicts, who wins instead, and which sources the answers come from.
crazyseo
Measure and fix whether AI assistants (ChatGPT, Gemini, Perplexity) recommend a website. Use when someone asks "am I visible in AI search", "does ChatGPT recommend us", "why doesn't AI mention my brand", "GEO/AEO audit", "AI SEO", "llms.txt", "is my site readable by AI crawlers", or wants to know which sources AI…
xerj-code
Reference-coding with XERJ. Clone the libraries that already solved your problem, index them locally, and retrieve the exact implementation before writing code — so the agent reads passages instead of re-deriving algorithms across retry loops. Use when starting a task in an unfamiliar API, porting an algorithm, or…