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 jgoullet/seo-geo-audit --skill seo-collectorgit clone --depth 1 https://github.com/jgoullet/seo-geo-auditWrote 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/jgoullet/seo-geo-audit/seo-collector)<a href="https://agentmods.dev/skills/jgoullet/seo-geo-audit/seo-collector"><img src="https://agentmods.dev/badge/skills/jgoullet/seo-geo-audit/seo-collector/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/jgoullet/seo-geo-audit/seo-collector"><img src="https://agentmods.dev/badge/skills/jgoullet/seo-geo-audit/seo-collector.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 | $0.00227 | $0.04776 |
| Opus 5.5 | $0.00091 | $0.01910 |
| Sonnet 5.5 | $0.00045 | $0.00955 |
| Haiku 4.5 | $0.00023 | $0.00478 |
Grade A, and why
seo-collector 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: SEO Collector — Automated technical data collection
All responses and logs are produced in English by default. Switch to the user's language if they explicitly request it.
Overview
This skill automatically crawls a website and produces a structured site-data.json file, ready to be consumed by the seo-geo-audit skill. It replaces manual information gathering (Step 0 of the audit).
Position in the pipeline
[seo-shared-context] → client-profile.md
↓
┌─────────────────────────┐
│ SEO COLLECTOR (this) │
└─────────────────────────┘
↓
site-data.json
↓
┌─────────────────────────┐
│ SEO-GEO AUDIT │
└─────────────────────────┘
Step 0: Prerequisites
Required inputs
- Site URL (required)
client-profile.md(optional — if available, load it for mode, competitors, CMS info)
Optional MCP integrations
Ahrefs MCP (recommended — replaces estimates with real data)
Ahrefs MCP is available on Lite, Standard, Advanced, and Enterprise plans (from $29/month Starter). It provides real backlink data, domain rating, organic keywords, and competitor identification — all data that the collector would otherwise estimate.
If Ahrefs MCP is connected, the collector will use it to pull:
| Ahrefs endpoint | What it provides | Replaces |
|---|---|---|
domain-rating |
Real DR score (0-100) + Ahrefs Rank | Estimated authority |
backlinks-stats |
Total backlinks, referring domains, dofollow/nofollow | "Estimated from web search" |
broken-backlinks |
Broken inbound links list | Not available without Ahrefs |
organic-keywords |
Keywords the site ranks for + positions + volumes | Manual keyword search |
organic-competitors |
Top organic competitors identified by Ahrefs | "Identify via web_search" |
top-pages |
Pages driving the most organic traffic | Sample crawl guesswork |
batch-url-analysis |
SEO metrics for multiple URLs at once | One-by-one page crawl |
brand-radar |
Brand mentions across AI agents (ChatGPT, Perplexity...) | Manual GEO visibility test |
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.
- 2mo ago First seen · 478 lines · 227 tokens per session scan A 282103e29428
seo-collector is a skill published in the GitHub repository jgoullet/seo-geo-audit (5 stars, last pushed 7mo ago), licensed MIT. It adds 227 tokens to every session and 4,776 once invoked, about $0.0009 per session on Opus 5.5. 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.
seo-collector compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| seo-collectorjgoullet/seo-geo-audit | Skill | 5 | 7mo ago | MIT | A | 227 | Claude Code, Codex |
| geo-audittechhorizonlabs/thl-open | Skill | 19 | 28d ago | MIT | A | 60 | Claude Code |
| geotechhorizonlabs/thl-open | Skill | 19 | 28d ago | MIT | A | 139 | Claude Code |
| found-by-aitechhorizonlabs/thl-open | Skill | 19 | 28d ago | MIT | A | 67 | Claude Code |
| geo-brand-mentionstechhorizonlabs/thl-open | Skill | 19 | 28d ago | MIT | A | 49 | Claude Code |
| geo-llmstxttechhorizonlabs/thl-open | Skill | 19 | 28d ago | MIT | A | 46 | Claude Code |
| agent-readiness-scantechhorizonlabs/thl-open | Skill | 19 | 28d ago | MIT | A | 79 | Claude Code |