seomachine: Command for Claude Code

.claude/commands/research-ai-citations.md

research-ai-citations is a command for Claude Code from TheCraigHewitt/seomachine. It costs 0 tokens per session (1,555 once invoked), scanned A, original, MIT.

A command for researching the questions people ask AI tools about a topic and the sources those tools cite in their answers. It groups commercially focused prompts and creates a source-tracking template.

In plain words
What is it for?
Use it to research topics such as project-management software, email platforms, or small-business CRMs, then track which websites AI answers cite.
Why use it?
It helps reveal opportunities that ordinary keyword research may miss, since search engines and AI tools may use different questions and sources.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is TheCraigHewitt/seomachine's own configuration. It tells Claude Code how to work on seomachine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything seomachine configures →

About the project

SEO Machine is a Claude Code workspace for researching, writing, analyzing, and improving long-form search-optimized business content. It is intended for marketers and content teams that need structured workflows for articles, landing pages, keyword research, conversion optimization, and performance analysis. Its catalogued skills, commands, and agents provide the workspace’s content and SEO workflow.

TheCraigHewitt/seomachine · 7,427 stars · on GitHub · seomachine.io

Reuse

Borrowing it

Nothing to install: this file belongs to TheCraigHewitt/seomachine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TheCraigHewitt/seomachine/main/.claude/commands/research-ai-citations.md
Clone the repo
git clone --depth 1 https://github.com/TheCraigHewitt/seomachine

Made for: Claude Code.

Wrote 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.

agentmods badge for research-ai-citations

README.md
[![agentmods](https://agentmods.dev/badge/commands/thecraighewitt/seomachine/research-ai-citations/github.svg)](https://agentmods.dev/commands/thecraighewitt/seomachine/research-ai-citations)
Your own site
<a href="https://agentmods.dev/commands/thecraighewitt/seomachine/research-ai-citations"><img src="https://agentmods.dev/badge/commands/thecraighewitt/seomachine/research-ai-citations/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.

agentmods 80×15 button for research-ai-citations

Your own site · 80×15
<a href="https://agentmods.dev/commands/thecraighewitt/seomachine/research-ai-citations"><img src="https://agentmods.dev/badge/commands/thecraighewitt/seomachine/research-ai-citations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01555
Opus 5 $0.00000 $0.00777
Sonnet 5 $0.00000 $0.00311
Haiku 4.5 $0.00000 $0.00155

Measured 11d ago against content hash 48b3e06a8f36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-ai-citations 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 11d 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.

.claude/commands/research-ai-citations.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research AI Citations Command

Generate high-commercial-intent prompts for a topic, cluster them, and create an audit template for tracking which sources AI tools cite. This is the prompt-driven research counterpart to traditional keyword research.

Usage

/research-ai-citations [topic or keyword]

Examples:

  • /research-ai-citations "project management tools"
  • /research-ai-citations "email marketing platform"
  • /research-ai-citations "CRM for small businesses"

Why This Matters

Traditional SEO research asks: "What keywords do people search on Google?" AI citation research asks: "What prompts do people type into ChatGPT/Perplexity, and which sources get cited in the answers?"

These are different questions with different answers. A page can rank #1 on Google but never get cited by ChatGPT if the content isn't structured for AI consumption, or if competitors dominate the directories and listicles that AI tools actually pull from.

This command bridges that gap.

Process

Step 1: Generate Prompt List (100+ prompts)

Generate a comprehensive list of high-commercial-intent prompts that a potential customer might ask AI tools about this topic.

Prompt Categories

A. Direct Recommendation Prompts (Highest Priority) These trigger AI to search the web and cite sources:

  • "What is the best [topic]?"
  • "Top [topic] for [use case]"
  • "Best [topic] for [audience]"
  • "Recommend a [topic] for [specific need]"

B. Comparison Prompts

  • "[Product A] vs [Product B] for [topic]"
  • "Compare [options] for [topic]"
  • "Which [topic] is better for [use case]?"
  • "Alternatives to [competitor] for [topic]"

C. Feature-Specific Prompts

  • "Best [topic] with [feature]"
  • "[Topic] that supports [capability]"
  • "Which [topic] has [specific feature]?"

D. Use-Case Prompts

  • "Best [topic] for [industry/niche]"
  • "[Topic] for [specific scenario]"
  • "How to [achieve goal] with [topic]"

E. Pricing/Value Prompts

  • "Cheapest [topic]"
  • "Free [topic] options"
  • "[Topic] pricing comparison"
  • "Is [product] worth it for [topic]?"

Read the full file on GitHub · 184 lines

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. 11d ago First seen · 184 lines · 0 tokens per session scan A 48b3e06a8f36

Subscribe to this mod's changes

research-ai-citations is a command published in the GitHub repository TheCraigHewitt/seomachine (7,427 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,555 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.