seo-audit

seo-audit is a command for coding agents from minosdevs/seo-geo-kit. It costs 23 tokens per session (487 once invoked), scanned A, original, MIT.

A command for performing a complete search-engine and generative-engine optimization audit of a website. It examines both the project code and the live site without applying fixes.

In plain words
What is it for?
Use it to audit site context, routes, metadata, headers, HTML, content intent, and production pages, then produce a scored, prioritized report in the `seo/` folder.
Why use it?
It exposes technical and content problems using evidence from files and fetched pages. This avoids treating code metadata as proof of what visitors and search systems actually receive.

Command

Part of the seo-geo-kit plugin — 1 skill, 3 commands shipped together

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 commands/minosdevs/seo-geo-kit/seo-audit
Clone the repo
git clone --depth 1 https://github.com/minosdevs/seo-geo-kit

Or install seo-geo-kit, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

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 seo-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/minosdevs/seo-geo-kit/seo-audit.svg)](https://agentmods.dev/commands/minosdevs/seo-geo-kit/seo-audit)
Your own site
<a href="https://agentmods.dev/commands/minosdevs/seo-geo-kit/seo-audit"><img src="https://agentmods.dev/badge/commands/minosdevs/seo-geo-kit/seo-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 487 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 $0.00023 $0.00487
Opus 5 $0.00012 $0.00244
Sonnet 5 $0.00005 $0.00097
Haiku 4.5 $0.00002 $0.00049

Measured 5d ago against content hash 21f4d68f71b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seo-audit 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.

commands/seo-audit.md · 33 lines

What it actually says

Lance un audit SEO + GEO complet en mode ANALYSE.

Cible : $ARGUMENTS Si vide, audite le projet du repertoire courant et son URL de production detectee.

Utilise le skill seo-geo-audit (mode ANALYSE) et suis-le a la lettre.

Rappels critiques pour ce mode :

  1. Ne modifie aucun fichier du projet. Le seul fichier ecrit est le rapport dans seo/. Meme si un correctif est trivial, tu le notes, tu ne l'appliques pas.
  2. Etablis le contexte d'abord (framework, URL de prod, langues, inventaire des routes, business). Si tu ne trouves pas l'URL de production, demande-la, ne l'invente pas.
  3. Audite le code ET le live. Un metadata parfait dans le code ne prouve rien sur ce qui est reellement servi. Fetch les pages, verifie les headers, lis le HTML source.
  4. Chaque finding cite une preuve : un fichier:ligne ou un extrait du HTML recupere. Pas de "il semblerait que", pas de recommandation generique non verifiee.
  5. Sois severe. Un score complaisant ne sert a personne. Si le contenu ne repond a aucune intention reelle, ecris-le noir sur blanc, meme si la technique est propre.
  6. Dis ce que tu n'as pas pu verifier dans la section "Non verifie" du rapport.

Passes a couvrir, sans en sauter : fichiers racine, crawl live, technique on-page, GEO/AEO, contenu et intentions, performance, autorite. Charge references/audit-checklist.md et references/geo-playbook.md pour le detail, references/report-template.md pour le format.

Livrable : seo/AUDIT-<YYYY-MM-DD>.md, puis dans le chat le score global, les 5 items P0, et la commande a lancer ensuite (/seo-fix).

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 · 33 lines · 23 tokens per session scan A 21f4d68f71b8

Subscribe to this mod's changes

seo-audit is a command published in the GitHub repository minosdevs/seo-geo-kit (1 stars, last pushed 19d ago), licensed MIT. It adds 23 tokens to every session and 487 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 2026-08-31.