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.
npx skills add minosdevs/seo-geo-kit --skill seo-geo-auditgit clone --depth 1 https://github.com/minosdevs/seo-geo-kitWrote 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.
[](https://agentmods.dev/skills/minosdevs/seo-geo-kit/seo-geo-audit)<a href="https://agentmods.dev/skills/minosdevs/seo-geo-kit/seo-geo-audit"><img src="https://agentmods.dev/badge/skills/minosdevs/seo-geo-kit/seo-geo-audit/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.
<a href="https://agentmods.dev/skills/minosdevs/seo-geo-kit/seo-geo-audit"><img src="https://agentmods.dev/badge/skills/minosdevs/seo-geo-kit/seo-geo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00166 | $0.03573 |
| Opus 5 | $0.00083 | $0.01786 |
| Sonnet 5 | $0.00033 | $0.00715 |
| Haiku 4.5 | $0.00017 | $0.00357 |
Grade A, and why
seo-geo-audit 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Utilise `WebFetch` ou `curl -sSL -o - -w '\n%{http_code} %{time_total}s'`. How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO / GEO Kit
Trois modes. L'utilisateur en choisit un via une slash command, ou tu deduis le mode de sa demande.
| Commande | Mode | Ce que ca fait |
|---|---|---|
/seo-audit |
ANALYSE | Audite tout, ne touche a rien, produit un rapport note et priorise |
/seo-fix |
CORRECTION | Lit le dernier rapport, applique les correctifs, verifie, commit |
/seo-blog |
CONTENU | Ecrit un article de blog aligne sur le site, optimise SEO + GEO, et le cable |
Regle absolue : ANALYSE ne modifie aucun fichier du projet (a part le rapport dans seo/).
Si l'utilisateur lance /seo-audit, tu n'edites pas son code, meme si le fix est trivial. Tu le notes.
0. Contexte a etablir (tous les modes, ~2 min)
Avant tout, etablis ces faits. Ne les devine pas, verifie-les.
- Framework et version :
package.json,next.config.*,astro.config.*,nuxt.config.*,gatsby-config.*,_config.yml,index.html. Next.js App Router et Pages Router n'ont pas la meme API de metadata, ne confonds pas. - URL de production : dans l'ordre,
NEXT_PUBLIC_SITE_URL/SITE_URLde.env*, unlib/site.*ouconfig/site.*,package.json#homepage, le README,vercel.json, la remote git. Si rien, demande l'URL : sans elle tu ne peux auditer que le code, pas le rendu. - Langues : mono ou multilingue ? Ou vivent les traductions ? Quelle langue par defaut ?
Quelle strategie d'URL (
/fr,/en, sous-domaine, domaine par langue) ? - Inventaire des routes : liste tous les fichiers de page (
app/**/page.tsx,pages/**,src/pages/**,content/**). Compte les pages statiques, les routes dynamiques, les articles. - Business : que vend le site, a qui, dans quel pays ? Sans ca tu ne peux pas juger la pertinence des mots-cles ni la qualite du contenu. Lis la landing, le README, le CLAUDE.md.
Ecris ces 5 points en tete de rapport. Ils conditionnent toutes les recommandations.
1. Mode ANALYSE (/seo-audit)
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.
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.
- 10d ago First seen · 223 lines · 166 tokens per session scan A c7c1eb5e3243
seo-geo-audit is a skill published in the GitHub repository minosdevs/seo-geo-kit (2 stars, last pushed 24d ago), licensed MIT. It adds 166 tokens to every session and 3,573 once invoked, about $0.0008 per session on Opus 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.
Other skills, from other repositories
build-backlinks
Finds free backlink and brand mention opportunities across Hacker News, Quora, GitHub, directories, and niche communities. Outputs a prioritized action plan with draft responses ready to post. Use after brand research and content creation to amplify reach and AI engine citations.
geo-content-research
Researches what prompts people ask AI engines (ChatGPT, Gemini, Perplexity, Claude) about a product category and produces a prompts.csv artifact — a prioritized, strictly-schema'd list of the queries where the brand should be cited. Feeds the monitor workflow.
improve-aeo-geo
Audits a website codebase and makes code changes so AI engines (ChatGPT, Claude, Perplexity, Google AI Overviews) can better discover, parse, quote, and cite the site. Covers structured data, content structure, technical signals, and freshness.
create-geo-charts
Creates data visualizations (charts, graphs, tables) optimized for AI engine parsing and citation. Produces inline SVG/HTML with text summaries, data tables, and JSON-LD so AI engines can quote the data.
research-keywords
Finds high-value SEO and GEO keywords using web search, AI analysis, and optionally paid tools like Ahrefs or Semrush. Produces a validated keywords.csv file with a fixed schema for downstream pipeline consumption.
write-seo-geo-content
Writes product-led content pages optimized for both search engines and AI engine citations. Produces markdown files with frontmatter, following page-type frameworks (comparison, guide, use case, learn, trust) with verified sources and no fabricated data.