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 marcusquinn/aidevops --skill seo-auditgit clone --depth 1 https://github.com/marcusquinn/aidevopsWrote 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/marcusquinn/aidevops/seo-audit)<a href="https://agentmods.dev/skills/marcusquinn/aidevops/seo-audit"><img src="https://agentmods.dev/badge/skills/marcusquinn/aidevops/seo-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/marcusquinn/aidevops/seo-audit"><img src="https://agentmods.dev/badge/skills/marcusquinn/aidevops/seo-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 | $0.00087 | $0.01616 |
| Opus 5.5 | $0.00035 | $0.00646 |
| Sonnet 5.5 | $0.00017 | $0.00323 |
| Haiku 4.5 | $0.00009 | $0.00162 |
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 today.
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Audit
Before auditing: Read .claude/product-marketing-context.md if it exists. Clarify: site type (SaaS, e-commerce, blog), primary goal, priority keywords, known issues, traffic baseline, recent changes/migrations, scope (full site vs. specific pages), Search Console access.
Audit Priority Order
- Crawlability & Indexation — can Google find and index it?
- Technical Foundations — fast and functional?
- On-Page Optimization — content optimized?
- Content Quality — deserves to rank?
- Authority & Links — credible?
Technical SEO Audit
Crawlability
Robots.txt: No unintentional blocks; important pages allowed; sitemap referenced.
XML Sitemap: Exists, accessible, submitted to Search Console; canonical indexable URLs only; updated regularly.
Site Architecture: Important pages ≤3 clicks from homepage; logical hierarchy; no orphan pages; internal linking intact.
Crawl Budget (large sites): Parameterized URLs controlled; faceted nav handled; no session IDs in URLs; infinite scroll has pagination fallback.
Indexation
Index Status: Run site:domain.com; check Search Console coverage; compare indexed vs. expected count.
Indexation Issues: Noindex on important pages; canonicals pointing wrong; redirect chains/loops; soft 404s; duplicate content without canonicals.
Canonicalization: All pages have canonical tags; self-referencing on unique pages; HTTP→HTTPS; www/non-www consistent; trailing slash consistent.
Site Speed & Core Web Vitals
| Metric | Target |
|---|---|
| LCP (Largest Contentful Paint) | < 2.5s |
| INP (Interaction to Next Paint) | < 200ms |
| CLS (Cumulative Layout Shift) | < 0.1 |
Speed factors: TTFB, image optimization, JS/CSS delivery, caching, CDN, font loading.
Tools: PageSpeed Insights (tools/browser/pagespeed.md), Search Console Core Web Vitals report.
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.
- today Changed · +2 lines cf333ad9da95
- 1mo ago First seen · 169 lines · 87 tokens per session scan A f945cb1c6f67
seo-audit is a skill published in the GitHub repository marcusquinn/aidevops (423 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 1,616 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
ad-creative-paid-ads
Skill "ad-creative-paid-ads" from ItamarZand88/awesome-agent-conventions, covering ad creative, before starting, 1. product & offer, 2. audience and 3. platform & stage.
tradermonty-technical-analyst
Skill "tradermonty-technical-analyst" from ItamarZand88/awesome-agent-conventions, covering technical analyst, when to use, prerequisites, output and core principles.
geo-content-optimizer
Skill "geo-content-optimizer" from ItamarZand88/awesome-agent-conventions, covering geo content optimizer, what this skill does, quick start, skill contract and handoff summary.
seo-keyword-research
Skill "seo-keyword-research" from ItamarZand88/awesome-agent-conventions, covering keyword research, quick start, skill contract, handoff summary and data sources.
omicverse-single-cell-clustering
Skill "omicverse-single-cell-clustering" from ItamarZand88/awesome-agent-conventions, covering single-cell clustering and batch correction with omicverse, instructions, examples and references.
remove-ai-flavor
A writing guide for making text sound more natural and less like an AI-generated draft. It identifies template-like wording, empty claims, translation-like phrasing, and overused formatting while preserving the author’s meaning and tone.