What is a-geo-optimizer?

A web-project guide for improving how AI assistants find, understand, and cite a site’s content. It covers site structure and technical settings used by AI crawlers.

Use it when creating or auditing pages, restructuring content, or reviewing robots.txt, sitemaps, schema markup, and other structured site data for AI visibility.

It helps address the problem of a site being overlooked or misunderstood by AI search tools. It also provides checks for common visibility gaps.

a-geo-optimizer — Skill for Claude Code and Codex by imisic

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 imisic/claude-marketplace --skill a-geo-optimizer

Clone the repo

git clone --depth 1 https://github.com/imisic/claude-marketplace

Made for: Claude Code, Codex.

Or install search-visibility, the plugin that ships this one along with the rest of its 2 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-geo-optimizer/github.svg)](https://agentmods.dev/skills/imisic/claude-marketplace/a-geo-optimizer)

Your own site

<a href="https://agentmods.dev/skills/imisic/claude-marketplace/a-geo-optimizer"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-geo-optimizer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/imisic/claude-marketplace/a-geo-optimizer"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-geo-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,798 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00155	$0.02798
Opus 5.5	$0.00062	$0.01119
Sonnet 5.5	$0.00031	$0.00560
Haiku 4.5	$0.00015	$0.00280

Measured 5d ago against content hash 43d0a40e432d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

a-geo-optimizer scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/geo_probe.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **Technical foundation**: Start with `python3 "${CLAUDE_SKILL_DIR}/scripts/geo_probe.py" <url> [more page URLs] --json`. It fetches robots.txt (per-crawler allow/disallow/unmentioned, Sitemap and Content-Signal lines)

plugins/search-visibility/skills/a-geo-optimizer/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEO Optimizer: AI Search Visibility Skill

Make any web project discoverable and citable by AI assistants (ChatGPT, Claude, Gemini, Perplexity, Copilot). This skill covers technical implementation, content structure, and ongoing monitoring.

When to use this skill

New site/page creation: Bake GEO in from the start
Existing site audit: Diagnose and fix AI visibility gaps
Content writing/restructuring: Format content for AI citation
Template development: Build PHP/HTML templates with GEO built-in
robots.txt / schema / sitemap work: Ensure AI crawler compatibility
Competitive analysis: Compare AI citation performance

How to use this skill

Step 1: Determine the task type

Ask yourself which mode applies:

Mode	When	What to do
Full audit	User wants the full review	Run all checklists from `references/technical-checklist.md`
New build	Creating a site/page from scratch	Follow the build-time integration guide below
Content optimization	Writing or restructuring content	Follow `references/content-strategy.md`
Quick fix	Specific technical task (robots.txt, schema, etc.)	Jump to relevant section in `references/technical-checklist.md`

Step 2: For full audits, follow this sequence

Technical foundation: Start with python3 "${CLAUDE_SKILL_DIR}/scripts/geo_probe.py" <url> [more page URLs] --json. It fetches robots.txt (per-crawler allow/disallow/unmentioned, Sitemap and Content-Signal lines), /llms.txt and /llms-full.txt (presence, size, first heading, format), and every page's JSON-LD blocks (@type values, parse errors, missing template fields) plus <title>, meta description, canonical, <html lang> and a no-JS body-text heuristic. Its findings are evidence with a severity, never recommendations: judge that candidate set, then read references/technical-checklist.md and the pages themselves only for what the probe cannot see (wording quality, whether the content is worth citing, CDN-level bot blocking via curl -A "GPTBot", page speed, Lighthouse). Verify:
- robots.txt allows the AI search/index bots (exact user-agents in references/crawler-reference.md), and named groups repeat the * group's Disallow lines (named groups don't inherit them; probe check robots-named-group-skips-wildcard). Allowing training bots is the owner's decision; ask
- Google Search Console > Settings > Search generative AI is on Include (Exclude drops the site from AI Overviews and AI Mode)
- Server-side rendering (critical: the OpenAI, Anthropic and Perplexity crawlers don't execute JS)
- Schema.org JSON-LD for entities on key pages (Organization, Person, Product, LocalBusiness, Article); FAQ/HowTo markup optional
- Page speed (TTFB < 200ms, LCP < 2.5s)
- XML sitemap + RSS/Atom feed
- HTTPS, mobile-friendly
- llms.txt file: if present, it should pass Lighthouse's llms-txt audit, which checks three things: an H1 header, at least one markdown [text](url) link, and at least 50 characters (checklist section 5)
- Agentic Browsing readiness (checklist section 13): run PageSpeed Insights and read the Agentic Browsing category; agent-critical a11y (programmatic names, valid ARIA, touch targets) and CLS now double as agent-readiness signals. WebMCP only matters for interactive sites (search, cart, booking)
- If behind Cloudflare: fetch the LIVE robots.txt and check for injected Content-Signal directives (ai-train=no is the managed default; ai-input=no would hurt AI citation, see crawler-reference section 12)

Read the full file on GitHub · 145 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

5d ago Changed · +9 lines 43d0a40e432d
1mo ago Changed · +1 lines 7516930655fc
1mo ago Changed · -7 lines · -1 tokens per session 71b0b956ae2b
2mo ago First seen · 142 lines · 156 tokens per session scan A 5bbf07035735

Subscribe to this mod's changes

a-geo-optimizer is a skill published in the GitHub repository imisic/claude-marketplace (1 stars, last pushed 5d ago), licensed MIT. It adds 155 tokens to every session and 2,798 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Code review Marketing and SEO Research ai-tools claude developer-tools plugin-marketplace

a-geo-optimizer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
a-geo-optimizerimisic/claude-marketplace	Skill	1	5d ago	MIT	A	155	Claude Code, Codex
tuicragavra/tuicr	Skill	3.6k	today	MIT	A	52	Claude Code, Codex
liveagent-code-reviewStack-Cairn/LiveAgent	Skill	2.3k	today	MIT	A	54	Claude Code, Codex
codex-adversarial-reviewWrongStack/WrongStack	Skill	409	today	MIT	A	113	Claude Code, Codex
generic-fullstack-code-reviewertravisjneuman/.claude	Skill	112	4d ago	MIT	A	64	Claude Code
agent-architecture-analysttravisjneuman/.claude	Skill	112	4d ago	MIT	A	13	Claude Code
eg-precommit-reviewvshvedov/elephant-goldfish	Skill	98	10d ago	MIT	A	24	Codex

a-geo-optimizer