A report that compares two GEO audits, where GEO means improving a website's visibility in AI-generated answers. It calculates score changes, category progress, platform progress, crawler status, and completed actions.

Use it for monthly client reports, comparing dated audit files, tracking completed recommendations, and identifying remaining issues.

It shows what changed since a baseline audit and makes progress easier to measure over time.

geo-compare — Skill for Claude Code and Codex by bytefer

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 bytefer/geo-seo-codex --skill geo-compare

Clone the repo

git clone --depth 1 https://github.com/bytefer/geo-seo-codex

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bytefer/geo-seo-codex/geo-compare.svg)](https://agentmods.dev/skills/bytefer/geo-seo-codex/geo-compare)

Your own site

<a href="https://agentmods.dev/skills/bytefer/geo-seo-codex/geo-compare"><img src="https://agentmods.dev/badge/skills/bytefer/geo-seo-codex/geo-compare.svg" alt="Measured on agentmods" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,714 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 88% copy Near-identical to another mod 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	$0.00089	$0.02714
Opus 5	$0.00044	$0.01357
Sonnet 5	$0.00018	$0.00543
Haiku 4.5	$0.00009	$0.00271

Measured 8d ago against content hash 7a81940db38c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

geo-compare 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 8d 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.

Origin

This is a copy

88% identical to geo-compare — 26 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/geo-compare/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEO Monthly Delta Report Generator

Purpose

The single most powerful retention tool for a GEO agency: show clients exactly what improved since they started working with you. Every point gained on the GEO score is proof of value. This skill generates the "here's your progress" report.

Invocations

$geo-compare <domain>
$geo-compare <baseline-file> <current-file>
$geo-compare electron-srl.com --month march-2026

Examples:

$geo-compare electron-srl.com
$geo-compare ~/.geo-prospects/audits/electron-srl.com-2026-01-15.md ~/.geo-prospects/audits/electron-srl.com-2026-03-12.md

Workflow

Step 1: Find Audit Files

If only domain is provided:

Look in ~/.geo-prospects/audits/ for files matching <domain>-*.md
Sort by date
Use oldest as baseline, newest as current
If only one file exists: use it as baseline, run a fresh quick audit as current
If no files exist: suggest running $geo-prospect audit <domain> first

Step 2: Parse Both Audits

Extract from each audit file:

Overall GEO Score
Per-category scores (6 categories)
Per-platform scores (5 platforms)
AI crawler status (14 crawlers)
Critical issues list
Action items list with status

Step 3: Calculate Deltas

For each metric:

Delta = Current - Baseline
Trend = ▲ (improved), ▼ (declined), ── (unchanged)
Color coding in report: green (+), red (-), gray (=)

Step 4: Generate Monthly Report

Output to ~/.geo-prospects/reports/<domain>-monthly-<date>.md

Report Template

Generate the following document:

# GEO Monthly Progress Report
## [COMPANY NAME] — [MONTH YEAR]

**Reporting period:** [BASELINE DATE] → [CURRENT DATE]
**Prepared by:** [AGENCY NAME]
**Report reference:** GEO-MONTHLY-[DOMAIN]-[YYMMDD]

---

## Executive Summary

[2-3 sentences: What improved, what's the trend, what to focus on next month.]

Example: "Electron Srl's GEO Score improved from 32 to 44 this month (+12 points),
placing the site firmly in the 'Below Average' tier and on track to reach 'Moderate'
by May. The biggest wins were AI crawler access (+3 crawlers now allowed) and schema
implementation (+Organization and LocalBusiness schemas live). Next month's focus is
content citability — the highest-weighted remaining gap."

---

## GEO Score Progress

OVERALL GEO SCORE

Read the full file on GitHub · 300 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.

8d ago First seen · 300 lines · 89 tokens per session scan A 7a81940db38c

Subscribe to this mod's changes

geo-compare is a skill published in the GitHub repository bytefer/geo-seo-codex (11 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 2,714 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to geo-compare, differing in 26 lines, and is treated as a copy.

Analytics and metrics Marketing and SEO ai ai-agents codex codex-plugin codex-skill codex-skills

building-edgespark-apps

Build and modify EdgeSpark apps. Use when a project has edgespark.toml, the user mentions EdgeSpark, or work involves the edgespark CLI, server SDK types, storage/auth/database workflows, deployment, or @edgespark/web.

edgesparkhq/codex-plugins · 55 tokens

edgespark-frontend-design

Design and redesign EdgeSpark frontends with distinctive, production-grade visual direction instead of generic AI-looking UI. Use when building or polishing landing pages, marketing sites, dashboards, auth flows, portfolios, product surfaces, or reusable frontend sections in EdgeSpark, especially when the task…

edgesparkhq/codex-plugins · 87 tokens

geo-compare