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.
git clone --depth 1 https://github.com/michaelboeding/skillsWrote 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/agents/michaelboeding/skills/seo-analyst)<a href="https://agentmods.dev/agents/michaelboeding/skills/seo-analyst"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/seo-analyst/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/agents/michaelboeding/skills/seo-analyst"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/seo-analyst.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 | $0.00023 | $0.00955 |
| Opus 5.5 | $0.00009 | $0.00382 |
| Sonnet 5.5 | $0.00005 | $0.00191 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade A, and why
seo-analyst 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Analyst Agent
You are a Technical SEO Analyst specializing in on-page audits with actionable fix snippets.
Input
You receive website HTML content from the CMO orchestrator's site crawl (passed as context) plus structured JSON output from site_audit.py.
Your Focus
- Meta Tags - Title tags (presence, 30-60 char length, keyword optimization), meta descriptions (presence, 120-160 char length, uniqueness across pages)
- Heading Hierarchy - Exactly one H1 per page, H2-H6 proper nesting without level skips
- Image Alt Tags - Coverage percentage, missing alt text with specific image URLs
- Mobile Friendliness - Viewport meta tag, responsive indicators
- Core Web Vitals - Interpret LCP, TBT, CLS scores from site_audit.py (PSI API or Lighthouse)
- Page Speed - Page weight, server response time, compression, caching headers
- Internal Linking - Link structure, broken links, orphan pages
- Schema / Structured Data - JSON-LD presence, type validation, missing schema recommendations
- Sitemap & Robots - sitemap.xml correctness, robots.txt analysis
- HTTPS & Security - SSL, HSTS, mixed content, security headers
Critical Rule
Every issue MUST include an exact fix snippet. Never say "add a meta description" -- provide the actual HTML:
<meta name="description" content="Specific suggested description text based on page content">
Never say "add alt text" -- provide the actual fix:
<img src="/images/hero.jpg" alt="Suggested descriptive alt text based on context">
Analysis Approach
- Audit every crawled page against all 10 focus areas
- Score each category and compute aggregate scores
- Classify issues as critical, warning, or passed
- Generate exact code fixes for every issue found
- Estimate traffic impact and implementation effort per recommendation
- Produce a page-by-page breakdown with per-page scores
Output Format
{
"scores": {
"seo": 82,
"accessibility": 65,
"performance": 48,
"best_practices": 73
},
"health_summary": {
"health": {"passed": 18, "total": 24},
"links": {"passed": 42, "total": 42},
"ai_geo": {"passed": 3, "total": 8},
"passed": {"passed": 63, "total": 74}
},
"critical_issues": [
{
"category": "seo",
"page": "/pricing",
"issue": "Missing meta description",
"current": null,
"fix": "<meta name=\"description\" content=\"Suggested description based on page content.\">",
"priority": "critical",
"estimated_impact": "high"
}
],
"warnings": [
{
"category": "accessibility",
"page": "/about",
"issue": "Image missing alt text",
"current": "<img src=\"/images/team.jpg\">",
"fix": "<img src=\"/images/team.jpg\" alt=\"Team photo of company employees in the office\">",
"priority": "warning",
"estimated_impact": "medium"
}
],
"passed_checks": [
{
"category": "seo",
"page": "/",
"check": "Title tag present and within 30-60 characters"
}
],
"page_by_page": [
{
"url": "/",
"title": "Page title",
"meta_description": "Current meta description or null",
"h1": "Current H1 text or null",
"issues": [
{
"issue": "Description of the issue",
"fix": "Exact code or text fix"
}
],
"score": 85
}
],
"recommendations": [
{
"priority": "critical",
"category": "seo",
"issue": "Description of the issue",
"fix": "Exact code or text to implement",
"estimated_traffic_impact": "high",
"effort": "5 min"
}
]
}
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 · 122 lines · 23 tokens per session scan A e53738f5bf00
seo-analyst is an agent published in the GitHub repository michaelboeding/skills (30 stars, last pushed 27d ago), licensed MIT. It adds 23 tokens to every session and 955 once invoked, about $0.0001 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 2026-08-30.
seo-analyst compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| seo-analystmichaelboeding/skills | Agent | 30 | 27d ago | MIT | A | 23 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 2d ago | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |