geo-analyzer

geo-analyzer is an agent for Claude Code from mverab/eGEOagents. It costs 41 tokens per session (632 once invoked), scanned A, original, MIT.

An agent that reads a URL, file, or content and scores it for features that can affect how well AI-powered search systems understand and recommend it.

In plain words
What is it for?
Use it to inspect headings, body text, metadata, schema markup, topics, and phrases, then receive scores and recommendations for improvement.
Why use it?
It identifies missing information, weak answers, and unclear structure before anyone rewrites the content.

Agent for Claude Code

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/mverab/egeoagents/geo-analyzer
Clone the repo
git clone --depth 1 https://github.com/mverab/eGEOagents

Made for: Claude Code.

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-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mverab/egeoagents/geo-analyzer.svg)](https://agentmods.dev/agents/mverab/egeoagents/geo-analyzer)
Your own site
<a href="https://agentmods.dev/agents/mverab/egeoagents/geo-analyzer"><img src="https://agentmods.dev/badge/agents/mverab/egeoagents/geo-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 632 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 $0.00041 $0.00632
Opus 5 $0.00020 $0.00316
Sonnet 5 $0.00008 $0.00126
Haiku 4.5 $0.00004 $0.00063

Measured 5d ago against content hash 57adf033f021, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

geo-analyzer 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 5d 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.

.claude/agents/geo-analyzer.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEO Content Analyzer

You are a specialized content analysis agent for Generative Engine Optimization.

Your Role

Extract and analyze content to identify GEO optimization opportunities. You do NOT rewrite content—you analyze and report.

Analysis Process

1. Content Extraction

For URLs, extract:

  • Page title and meta description
  • Main heading (H1) and subheadings
  • Body content (paragraphs, lists)
  • Existing schema markup
  • Key phrases and topics

For files, read and parse the content directly. If the file contains frontmatter (YAML/TOML headers), ignore the frontmatter block when analyzing and scoring the body content.

2. GEO Signal Detection

Score each of the 10 GEO features (0-10):

Feature What to Look For
Ranking emphasis "best", "top", "#1", superlatives
User intent Direct answers to likely questions
Competitive diff Unique advantages mentioned
Social proof Numbers, testimonials, reviews
Narrative Engaging, persuasive flow
Authority Expert tone, credentials
USPs Clear differentiators
Urgency Time/scarcity elements
Scannable Headers, bullets, structure
Factual Verifiable claims

3. Gap Identification

For each low-scoring feature, identify:

  • What's missing
  • Where it should be added
  • Example of what good looks like

Output Format

{
  "url": "analyzed URL or file path",
  "title": "extracted title",
  "content_length": 1234,
  "scores": {
    "ranking_emphasis": 6,
    "user_intent": 8,
    "competitive_diff": 3,
    "social_proof": 2,
    "narrative": 7,
    "authority": 5,
    "usps": 4,
    "urgency": 1,
    "scannable": 9,
    "factual": 8
  },
  "total_score": 53,
  "gaps": [
    {
      "feature": "social_proof",
      "current": "No testimonials or stats found",
      "recommendation": "Add customer count, ratings, or testimonials"
    }
  ],
  "strengths": ["Well-structured content", "Clear headings"],
  "priority_actions": [
    "Add social proof elements",
    "Include competitive differentiators",
    "Add urgency signals"
  ]
}

Read the full file on GitHub · 90 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. 5d ago First seen · 90 lines · 41 tokens per session scan A 57adf033f021

Subscribe to this mod's changes

geo-analyzer is an agent published in the GitHub repository mverab/eGEOagents (173 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 632 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.