geo-seo

geo-seo is a skill for Claude Code, Codex from humanerd-drew/opencode-drewgent. It costs 57 tokens per session (4,020 once invoked), scanned A, original, MIT.

A guide to traditional SEO and GEO, which means preparing content to be found, understood, and cited by AI search systems. It applies these checks to WordPress sites, Cloudflare Workers, and an Obsidian vault.

In plain words
What is it for?
Use it to review crawlers, metadata, sitemaps, answer-focused headings, structured data, and other signals that affect search and AI visibility.
Why use it?
It addresses the gap between ranking in ordinary search results and being mentioned or cited in AI-generated answers.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Good fit Use it to review crawlers, metadata, sitemaps, answer-focused headings, structured data, and other signals that affect search and AI visibility.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/humanerd-drew/opencode-drewgent/geo-seo
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.

Any agent
npx skills add humanerd-drew/opencode-drewgent --skill geo-seo
Clone the repo
git clone --depth 1 https://github.com/humanerd-drew/opencode-drewgent

Made for: Claude Code, Codex.

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-seo

README.md
[![agentmods](https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/geo-seo.svg)](https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/geo-seo)
Your own site
<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/geo-seo"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/geo-seo.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,020 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 $0.00057 $0.04020
Opus 5 $0.00028 $0.02010
Sonnet 5 $0.00011 $0.00804
Haiku 4.5 $0.00006 $0.00402

Measured 3d ago against content hash e7acf26a09aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

geo-seo 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/seo/geo-seo/SKILL.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEO-first SEO — Generative Engine Optimization for {{AGENT_NAME}}

GEO(Generative Engine Optimization) + 전통 SEO를 동시에 다룬다. AI 검색 엔진(ChatGPT, Claude, Gemini, Perplexity, Google AI Overviews)이 콘텐츠를 발견·인용·요약하기 좋게 만드는 것이 목표다.

이 스킬은 {{AGENT_NAME}}의 WordPress 사이트(YOUR_DOMAIN), Cloudflare Workers, Obsidian vault를 대상으로 GEO 원칙을 적용한다.

1. GEO Fundamentals for {{AGENT_NAME}}

1.1 What changed in AI search

  • Query → Answer: 사용자가 링크 목록을 받는 대신 AI가 직접 답변을 생성한다.
  • Citation as currency: AI가 브랜드를 언급/인용하는 빈도가 새로운 가치 척도다.
  • Entity-first: 키워드 매칭보다 브랜드/인물/조직의 entity 인식이 중요하다.
  • Passage retrieval: 전체 페이지가 아닌 특정 문단/정의 블록이 인용된다.

1.2 GEO vs SEO

구분 SEO GEO
최적화 대상 Googlebot, Bingbot GPTBot, ClaudeBot, PerplexityBot, Google-Extended
성공 지표 Ranking, CTR, impressions AI mention, citation count, brand recall
핵심 자산 Backlinks Brand mentions, entity signals, citability
콘텐츠 단위 Page Passage / answer block
구조 자산 Sitemap, meta tags llms.txt, schema, answerable headings

1.3 {{AGENT_NAME}}-specific GEO surface

자산 GEO 활용
WordPress (YOUR_DOMAIN) 공개 블로그/랜딩 페이지 — AI 크롤러 대상
Cloudflare Workers llms.txt 서빙, 검증용 micro audit endpoint
Obsidian vault (P2/P4/P5) 날짜/통계/인용 출처가 풍부한 지식 원천
seo-article-harvester Google/AI 검색 알고리즘 변화를 실시간 감지

2. AI Crawler Access — robots.txt + llms.txt

2.1 robots.txt

WordPress 루트의 robots.txt 또는 Cloudflare Workers rewrite 응답에 다음을 포함한다.

User-agent: GPTBot
Disallow: /wp-admin/
Allow: /

User-agent: ClaudeBot
User-agent: Claude-Web
Disallow: /wp-admin/
Allow: /

User-agent: PerplexityBot
Disallow: /wp-admin/
Allow: /

User-agent: Google-Extended
Disallow: /wp-admin/
Allow: /

User-agent: *
Disallow: /wp-admin/
Allow: /

2.2 llms.txt

https://YOUR_DOMAIN/llms.txt에 사이트의 정체성과 중요 경로를 요약한다.

# llms.txt for YOUR_DOMAIN

## About
YOUR_DOMAIN is {{AGENT_NAME}}'s public lab and blog on AI-native workflows,
Cloudflare Workers, and agentic systems. Primary language: Korean.

## Key pages
- /about — organization and author background
- /blog — latest essays on AI engineering
- /lab — open experiments and tools
- /skills — {{AGENT_NAME}} skill catalog

## Crawl policy
- Allowed for all AI crawlers.
- Do not train on private member-only content under /member/.

## Contact
Your Name — [email protected]

Read the full file on GitHub · 384 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 · 384 lines · 57 tokens per session scan A e7acf26a09aa

Subscribe to this mod's changes

geo-seo is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 4,020 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

ultimate-seo-geo-skill

Use this skill when running SEO audits, optimizing for AI search engines (AI Overviews, ChatGPT, Perplexity), generating schema markup, diagnosing traffic drops, fixing Core Web Vitals, managing site migrations, or building keyword strategies. Runs scored full-site audits (0-100 Health Score) across 21 modules…

curiositech/some_claude_skills · 118 tokens

dataforseo-brain

Scaffold and operate DataForSEO Brain, a source-cited Obsidian brain for DataForSEO v3 API mastery - 12 modules and 200+ endpoints (SERP, Keywords Data, AI Optimization, Domain Analytics, DataForSEO Labs, OnPage, Backlinks, Content Analysis, Merchant, App Data, Business Data, Databases), the task/live queue execution…

AgriciDaniel/dataforseo-brain · 273 tokens

content-thicken

Evidence-driven blog driver. Takes ONE target from the fused search plus AI-answer content library, pulls the real questions it has to answer, drafts a thick long-form guide against a template contract, validates it deterministically, and stops at preview. Two modes, thicken an already-earning post IN PLACE (never…

Jasper0122/agent-seo-kit · 126 tokens

backlink-outreach

Find, evaluate, pitch and track natural backlink and content partnerships. Prospects come from the GEO citation data rather than a generic blog search: the targets are the pages an AI already cites when answering your category questions. Research runs on the Monid tool layer (web search and scrape, authority metrics…

Jasper0122/agent-seo-kit · 133 tokens

geo-monitor

Run and read the GEO pipeline, which measures whether AI answer engines mention, recommend and cite your site. Puts a fixed registry of real user questions to an answer engine through the Monid tool layer, detects the three signals plus competitors, and turns "a rival is named and we are not" into a tracked work…

Jasper0122/agent-seo-kit · 159 tokens

seo-intake

Run and read the SEO intake pipeline. Pulls the organic keyword set for your domain and for each competitor through the Monid tool layer, computes the gap locally, and routes every keyword to the one action that can help it (write-new / striking / build-depth / defend / noise). Use when asked to refresh the SEO queue…

Jasper0122/agent-seo-kit · 117 tokens