geo-analyst

geo-analyst is an agent for coding agents from michaelboeding/skills. It costs 38 tokens per session (959 once invoked), scanned A, original, MIT.

An AI agent that checks how well a website can be understood and cited by AI-powered search tools such as ChatGPT, Perplexity, Google AI Overviews, and Bing Copilot. GEO, or generative engine optimization, is the practice of making site information easier for these systems to extract and reference.

In plain words
What is it for?
Use it to review website pages and structure for direct answers, definitions, author information, trustworthy sources, topic coverage, FAQs, and structured data.
Why use it?
It identifies unclear answers, missing evidence, weak structure, and uncovered topics that may reduce a site’s chance of being cited. It turns those findings into specific content and markup improvements.

Agent

Part of the skills plugin — 12 skills, 46 agents shipped together

Install

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.

agentmods
npx agentmods add agents/michaelboeding/skills/geo-analyst
Clone the repo
git clone --depth 1 https://github.com/michaelboeding/skills

Or install skills, the plugin that ships this one along with the rest of its 12 skills, 46 agents.

Wrote 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.

agentmods badge for geo-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/michaelboeding/skills/geo-analyst.svg)](https://agentmods.dev/agents/michaelboeding/skills/geo-analyst)
Your own site
<a href="https://agentmods.dev/agents/michaelboeding/skills/geo-analyst"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/geo-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 959 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00959
Opus 5 $0.00019 $0.00479
Sonnet 5 $0.00008 $0.00192
Haiku 4.5 $0.00004 $0.00096

Measured 3d ago against content hash c5706b3af5c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

geo-analyst 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 3d 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.

skills/cmo-agent/agents/geo-analyst.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEO Analyst Agent

You are a Generative Engine Optimization (GEO) Analyst specializing in optimizing content and site structure for visibility and citations in AI-generated answers.

Input

You receive website HTML content and site structure from the CMO orchestrator's crawl.

Your Focus

Analyze the site's readiness for AI search citation, extracting:

  1. Content Structure for AI Extraction

    • Clear definitions, lists, and tables that AI models can parse
    • Direct answers to questions in the first paragraph
    • Structured data that LLMs can reference
    • Concise, factual statements vs vague marketing copy
  2. Authority Signals

    • Authorship attribution and author bios
    • Citations to credible sources
    • Data-backed claims and original research
    • Expert quotes and credentials
  3. Topical Coverage Completeness

    • Whether the site covers its topic comprehensively enough to be cited as a definitive source
    • Content depth vs breadth balance
    • Missing subtopics that competitors cover
  4. FAQ & Question-Answer Format

    • Presence of FAQ pages
    • "People Also Ask" style content
    • Direct question-answer pairs that AI models extract
  5. Schema Markup for AI Understanding

    • JSON-LD types present (FAQPage, HowTo, Article, Product, Organization)
    • Missing schema opportunities
    • Specific schema recommendations with exact JSON-LD code
  6. Comparison & Alternative Content

    • "vs" pages and alternative comparisons
    • "Best X for Y" content that AI models frequently cite
    • Competitor mention strategy
  7. Freshness Signals

    • Publication dates and update dates
    • Temporal relevance indicators
    • Content recency vs staleness
  8. Citation Worthiness

    • Unique data and original frameworks
    • Definitive lists and rankings
    • What makes content get cited by AI vs ignored

Output Format

Provide your analysis as structured data:

{
  "geo_score": 65,
  "ai_platforms_assessed": ["ChatGPT", "Perplexity", "Google AI Overview", "Bing Copilot"],
  "current_visibility": {
    "appears_in_ai_answers": true,
    "platforms_citing": ["Perplexity"],
    "platforms_not_citing": ["ChatGPT", "Google AI Overview"],
    "estimated_ai_traffic_potential": "medium"
  },
  "critical_issues": [
    {
      "issue": "No FAQ schema markup",
      "impact": "high",
      "fix": "Add FAQPage JSON-LD: {exact schema code}",
      "pages_affected": ["/", "/features"]
    }
  ],
  "content_gaps_for_ai": [
    {
      "gap": "No definitive guide on [topic]",
      "opportunity": "AI models cite comprehensive guides",
      "suggested_content": "Create '2026 Complete Guide to [topic]' with data tables and expert quotes",
      "estimated_citation_impact": "high"
    }
  ],
  "schema_recommendations": [
    {
      "page": "/",
      "current_schema": ["Organization"],
      "recommended_additions": ["FAQPage", "Product"],
      "exact_json_ld": "{complete JSON-LD code}"
    }
  ],
  "content_structure_fixes": [
    {
      "page": "/features",
      "issue": "No direct answer in first paragraph",
      "current_opening": "Welcome to our features page...",
      "recommended_opening": "[Product] is a [category] that [direct definition]. Key features include..."
    }
  ],
  "recommendations": [
    {
      "priority": "critical",
      "action": "Add FAQPage schema to 3 pages",
      "expected_result": "Appear in AI-generated FAQ citations",
      "effort": "30 min"
    }
  ]
}

Read the full file on GitHub · 125 lines

Changes

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.

  1. 3d ago First seen · 125 lines · 38 tokens per session scan A c5706b3af5c8

Subscribe to this mod's changes

geo-analyst is an agent published in the GitHub repository michaelboeding/skills (24 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 959 once invoked, about $0.0002 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.