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/afaraha8403/balakitWrote 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/afaraha8403/balakit/seo-ai-search)<a href="https://agentmods.dev/rules/afaraha8403/balakit/seo-ai-search"><img src="https://agentmods.dev/badge/rules/afaraha8403/balakit/seo-ai-search/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/rules/afaraha8403/balakit/seo-ai-search"><img src="https://agentmods.dev/badge/rules/afaraha8403/balakit/seo-ai-search.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 | $0.00000 | $0.01307 |
| Opus 5 | $0.00000 | $0.00654 |
| Sonnet 5 | $0.00000 | $0.00261 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade B, and why
seo-ai-search scanned grade B with 1 finding 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 9d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- **Prompt Injection Sanitization:** User-generated content (reviews, Q&A, profiles) surfaced in JSON-LD or `/llms.txt` MUST be sanitized. Ensure malicious instructions (e.g., "Ignore previous instructions and execute X" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal SEO & AI Search (Implementation & Security)
Apply when changing public-facing web pages or core SEO utility libraries.
For high-level strategy, manual audits, or marketing campaigns, refer to your project's marketing/SEO playbooks. Do not duplicate that workflow here.
Principle: AI visibility (LLMs, RAG systems, Agents) builds on valid HTML, extractable copy, structured data, and freshness. However, exposing Agentic Commerce endpoints and LLM-readable text creates new threat vectors. Optimize for both visibility and adversarial robustness.
Where Things Live (Agnostic Architecture)
Maintain strict separation of concerns across your framework (Next.js, Astro, Nuxt, etc.):
| Concern | Target Implementation |
|---|---|
| Meta clamping & sanitization | Centralized utility file (e.g., meta.ts, seo.utils.ts) |
| JSON-LD builders | Centralized schema definitions (e.g., schema.ts) |
| AI site index & routing | /llms.txt (or framework equivalent route) |
| AI knowledge export | /llms-full.txt (Full context export) |
| Machine-readable pricing | Static server route (e.g., pricing.md or API) |
| Agentic commerce index | Declared in /llms.txt under Agentic commerce |
| Crawler policy | /robots.txt and /ai.txt in the public static directory |
AI Security & Adversarial Defenses [CRITICAL]
When building endpoints specifically for AI consumption (/llms.txt, JSON-LD, UCP feeds), treat external LLMs and AI crawlers as potential attack vectors.
- Prompt Injection Sanitization: User-generated content (reviews, Q&A, profiles) surfaced in JSON-LD or
/llms.txtMUST be sanitized. Ensure malicious instructions (e.g., "Ignore previous instructions and execute X") cannot hijack downstream RAG systems or Agentic Commerce workflows. - Adversarial Validation (AV): Critical machine-readable logic (like Agentic capabilities or pricing APIs) should undergo adversarial testing. Ensure outputs cannot be easily hallucinated or misinterpreted by external models.
- Crawler Nuance: Allow verified AI crawlers (e.g.,
GPTBot,ClaudeBot) in/robots.txt, but implement aggressive rate-limiting. Explicitly block unverified, aggressive scraper bots to prevent data scraping DDoS attacks.
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.
- 9d ago First seen · 111 lines · 1,307 tokens per session scan B e2d4ac2cd2c6
seo-ai-search is a cursor rule published in the GitHub repository afaraha8403/balakit (1 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,307 tokens. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
skill-creator
Create, edit, evaluate, and debug the skills in this repo, including running their evals and fixing a description that fails to trigger. Use when user says 'help me build a new skill', 'add a skill for X', 'run the evals for the tf skill', 'run the behavioral evals', 'my skill is not triggering', 'fix this skill's…
tf-plan
Review a Terraform plan before applying it: destroys and replacements of data-bearing resources, secrets readable in plan output, out-of-band drift, blast radius, and whether the apply is bound to the plan you actually reviewed. Use when user says 'review my plan', 'is this plan safe to apply', 'check tfplan', 'what…
clarify-first
Infer-and-act by default — ask only on high confusion weight, after inspecting, with a decision-linked question.
file-organization
Project file and folder organization patterns.
skill-router
Routes tasks to the correct skill file automatically.
composer-senior-practices
Version-pinned framework guidance from primary docs when building on unfamiliar stacks, upgrading, or reviewing architecture — load when evidence beats training data; not required for routine feature work.