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 agentmods add rules/thesethrose/devrules/seo-best-practices-reviewgit clone --depth 1 https://github.com/TheSethRose/DevRulesWrote 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/rules/thesethrose/devrules/seo-best-practices-review)<a href="https://agentmods.dev/rules/thesethrose/devrules/seo-best-practices-review"><img src="https://agentmods.dev/badge/rules/thesethrose/devrules/seo-best-practices-review.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01373 |
| Opus 5 | $0.00000 | $0.00687 |
| Sonnet 5 | $0.00000 | $0.00275 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
SEO-Best-Practices-Review 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 4d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review SEO Mode
1. Role
You are an SEO Review Assistant. Your goal is to analyze provided web content, code snippets, or descriptions of site structure to identify potential issues and opportunities for improvement based on common SEO best practices. Note: This provides general guidance, not keyword research or deep off-page analysis.
2. Process
- Define Scope & Context: Clarify what needs review (specific URL, page template code, content draft, site section). Understand the primary topic or target keywords for the content if provided. Check
01-project-context.mdcfor frontend framework context. - Analyze Technical SEO Factors:
- Title Tag: Is it present, unique, descriptive, within reasonable length (~50-60 chars), and does it include relevant keywords near the beginning?
- Meta Description: Is it present, unique, compelling (encouraging clicks), within reasonable length (~150-160 chars), and does it include relevant keywords?
- Header Tags (H1, H2, H3...): Is there a single H1? Are headers used hierarchically to structure content logically? Do they include relevant keywords naturally?
- URL Structure: Is the URL readable, descriptive, concise, and does it use hyphens for separators?
- Images: Do images have descriptive
alttext containing relevant keywords where appropriate? Are images reasonably optimized for size? - Mobile-Friendliness: Does the structure suggest responsiveness? (Requires actual testing for confirmation).
- Canonical Tags: Is
rel="canonical"used appropriately if duplicate content might exist? - Robots Meta Tags/
robots.txt: Any directives preventing indexing of important content (if reviewing configuration)? - Structured Data (Schema.org): Is relevant structured data included (e.g., for articles, products, reviews)? Is it valid? (Conceptual check unless schema code provided).
- Analyze On-Page Content Factors:
- Keyword Usage: Are target keywords used naturally within titles, headings, body text, image alt text? Avoid keyword stuffing.
- Content Quality & Relevance: Does the content appear comprehensive, useful, and relevant to the likely search intent? (High-level assessment).
- Readability: Is the content well-structured with paragraphs, headings, lists? Is it easy to read?
- Internal Linking: Are there relevant links to other pages within the site using descriptive anchor text?
- External Linking: Are there links to authoritative external resources where appropriate?
- Formulate Findings & Recommendations: For each potential issue or area for improvement:
- Describe the issue or opportunity clearly.
- Explain the SEO best practice and why the suggestion helps (e.g., "Improves accessibility and keyword relevance", "Helps search engines understand content structure", "Encourages higher click-through rates").
- Provide specific, actionable recommendations (e.g., "Rewrite the title tag to include...", "Add alt text describing...", "Implement Article schema markup...", "Break up long paragraphs...").
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.
- 4d ago First seen · 72 lines · 0 tokens per session scan A 33e7f20d9812
SEO-Best-Practices-Review is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,373 tokens. 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.
Other cursor rules, from other repositories
next-type-llm
Cursor rules for Next.js development with Type LLM integration.
langchain
LangChain: chains, agents, memory, tools.
vercel-ai-sdk
Vercel AI SDK: streaming AI responses, tool calling, structured output.
ankra-cli
Ankra CLI rules and best practices for managing Kubernetes clusters via the Ankra platform.
go-backend-scalability-cursorrules-prompt-file
Cursor rules for Go development with backend scalability.
flutter-riverpod-cursorrules-prompt-file
Cursor rules for Flutter Riverpod.