rank-geo

rank-geo is a skill for Claude Code from Houseofmvps/claude-rank. It costs 24 tokens per session (655 once invoked), scanned A, original, MIT.

A checker and fixer for how website content can be found and understood by AI search tools such as ChatGPT, Perplexity, and Google AI Overviews.

In plain words
What is it for?
It helps audit robots.txt, JSON-LD data, question headings, summaries, definitions, llms.txt, sitemaps, and breadcrumbs, then verify changes.
Why use it?
It identifies barriers such as blocked AI crawlers, weak structured data, unclear content, and missing discovery files, then suggests or applies supported fixes.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-rank plugin — 6 skills, 12 commands, 9 agents, 1 hook shipped together

Good fit It helps audit robots.txt, JSON-LD data, question headings, summaries, definitions, llms.txt, sitemaps, and breadcrumbs, then verify changes.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Houseofmvps/claude-rank
Claude Code
/plugin install claude-rank

Made for: Claude Code.

Or install claude-rank, the plugin that ships this one along with the rest of its 6 skills, 12 commands, 9 agents, 1 hook.

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 rank-geo

README.md
[![agentmods](https://agentmods.dev/badge/skills/houseofmvps/claude-rank/rank-geo/github.svg)](https://agentmods.dev/skills/houseofmvps/claude-rank/rank-geo)
Your own site
<a href="https://agentmods.dev/skills/houseofmvps/claude-rank/rank-geo"><img src="https://agentmods.dev/badge/skills/houseofmvps/claude-rank/rank-geo/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.

agentmods 80×15 button for rank-geo

Your own site · 80×15
<a href="https://agentmods.dev/skills/houseofmvps/claude-rank/rank-geo"><img src="https://agentmods.dev/badge/skills/houseofmvps/claude-rank/rank-geo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 655 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00024 $0.00655
Opus 5 $0.00012 $0.00328
Sonnet 5 $0.00005 $0.00131
Haiku 4.5 $0.00002 $0.00065

Measured 12d ago against content hash d37cec51c90f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

rank-geo 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.

skills/rank-geo/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEO Audit — AI Search Optimization

Phase 1: Scan

node ${CLAUDE_PLUGIN_ROOT}/tools/geo-scanner.mjs <project-directory>

Phase 2: Report

Present GEO findings grouped by:

  • AI Bot Access — which bots are allowed/blocked in robots.txt
  • Structured Data — JSON-LD quality for AI extraction
  • Content Structure — question headers, definitions, citation-ready passages
  • Discoverability — llms.txt, sitemap, breadcrumbs

Phase 3: Fix

  • Blocked AI bots → update robots.txt: node ${CLAUDE_PLUGIN_ROOT}/tools/robots-analyzer.mjs generate <dir> <url>
  • Missing llms.txt → generate: node ${CLAUDE_PLUGIN_ROOT}/tools/llms-txt-generator.mjs <dir>
  • Missing Organization schema → generate: node ${CLAUDE_PLUGIN_ROOT}/tools/schema-engine.mjs generate Organization --name="..." --url="..."
  • Missing Author schema → generate Person schema with credentials
  • No question H2s → rewrite key H2 headers as "What is...", "How does...", "Why..."
  • No TL;DR patterns → add 1-2 sentence summaries under important H2 sections
  • No definition patterns → add "[Product] is [clear definition]" in opening paragraphs

Phase 4: Verify

Re-run geo-scanner. Show before/after GEO score.

Phase 5: Search Console Submission

After deploying GEO fixes, submit to search engines so AI crawlers pick up the changes:

Google Search Console

  1. Resubmit sitemap — Sitemaps → Resubmit sitemap.xml (triggers recrawl)
  2. Request indexing for pages where you unblocked AI bots or added schema — URL Inspection → Request Indexing
  3. Check robots.txt — Settings → Crawling → verify your updated robots.txt is live (AI bots unblocked)

Bing Webmaster Tools

  1. Submit URLs — URL Submission → submit pages with new schema/content structure
  2. Verify robots.txt — Bingbot feeds Microsoft Copilot and ChatGPT Browse — keeping it unblocked is essential
  3. Enable IndexNow — Near-instant indexing for Bing, Yandex, Seznam. Generate key at indexnow.org

AI Search Verification (wait 2-4 weeks)

  1. Search your brand name + top 3 keywords in ChatGPT, Perplexity, Google AI Overviews, Gemini
  2. Screenshot results as a baseline
  3. Note which competitors are cited — create citation-ready content for each gap (134-167 word passages per Semrush "State of AI Search" study, 2025)
  4. Add comparison tables and statistics — multimedia increases AI citation rates by ~156% (Source: Search Engine Journal, "Multimedia & AI Citation Rates," Jan 2026)
  5. Set up weekly monitoring — track your AI citation rate vs competitors

Read the full file on GitHub · 56 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. 12d ago First seen · 56 lines · 24 tokens per session scan A d37cec51c90f

Subscribe to this mod's changes

rank-geo is a skill published in the GitHub repository Houseofmvps/claude-rank (143 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 655 once invoked, about $0.0001 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.