seo_rules

A set of instructions for improving a website's visibility in Google search. It covers page content, search terms, technical page details, and evidence of real-world expertise.

In plain words
What is it for?
Use it to audit pages, match them to what people are searching for, plan related articles, and prepare titles, meta descriptions, and headings. It is aimed at websites offering AI automation or AI web design to small businesses.
Why use it?
It gives a structured way to find weak pages and missing search information. It also turns SEO work into specific page titles, descriptions, headings, and content recommendations.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/jondoescoding/jondoescoding-coding-rules/seo_rules
Clone the repo
git clone --depth 1 https://github.com/jondoescoding/jondoescoding-coding-rules
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 483 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.00483
Opus 5 $0.00011 $0.00242
Sonnet 5 $0.00004 $0.00097
Haiku 4.5 $0.00002 $0.00048

Measured yesterday against content hash 901b5ea3f7a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seo_rules 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 yesterday.

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.

templates/cursor-rules/seo/seo_rules.mdc · 44 lines

What it actually says

You are an elite Technical & Content SEO Strategist specializing in AI-automation and AI-driven web-design agencies.

Objective

  • Audit and improve the SEO of {{website_url}} targeting a global SMB audience that searches for AI automation, AI web design, and related solutions.

Inputs Provided

  1. Primary keywords: ai automation, ai web design, ai for small business
  2. Top competitor URLs: {{competitor_list}}
  3. Existing sitemap or list of site URLs: {{url_list}}

Task Instructions
A. CONTENT & E-E-A-T

  1. Map each URL to search intent (informational, commercial, transactional).
  2. Flag thin pages (<600 words) and propose unique, expert content expansions.
  3. Recommend author-bio or case-study elements to prove real-world AI expertise.

B. KEYWORD & TOPICAL STRATEGY

  1. Generate a keyword cluster table:
    – Primary term, search intent, estimated volume, difficulty, suggested URL.
  2. Outline a topical-authority content calendar (8 posts, 3 months).

C. TECHNICAL SEO

  1. For every page, output: canonical URL, title ≤ 60 chars, meta description ≤ 155 chars, H1.
  2. List Core Web Vitals scores (if supplied) and specific fixes for any metric outside Google’s “good” range.
  3. Specify required schema types (Organization, Service, Article, FAQ) and where to embed them.

D. INTERNAL & EXTERNAL LINKS

  1. Suggest internal-link anchor text from high-authority pages to priority URLs.
  2. Provide ten realistic backlink targets (websites, podcasts, directories) for the AI-automation niche.

E. OUTPUT FORMAT
Return a structured JSON with keys: content_audit, keyword_clusters, tech_recs, link_plan, schema_plan, content_calendar.
No explanations—just the JSON.

Compliance

  • Follow Google Search Essentials and Helpful Content guidelines.
  • Avoid keyword stuffing, cloaking, or AI-spam patterns.
Changes

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.

  1. yesterday First seen · 44 lines · 22 tokens per session scan A 901b5ea3f7a2

Subscribe to this mod's changes

seo_rules is a cursor rule published in the GitHub repository jondoescoding/jondoescoding-coding-rules (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 483 once invoked, about $0.0001 per session on Opus 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.