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.
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.
curl -O https://raw.githubusercontent.com/TheCraigHewitt/seomachine/main/.claude/commands/research-ai-citations.mdgit clone --depth 1 https://github.com/TheCraigHewitt/seomachineWrote 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/commands/thecraighewitt/seomachine/research-ai-citations)<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.
<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>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 | $0.01555 |
| Opus 5 | $0.00000 | $0.00777 |
| Sonnet 5 | $0.00000 | $0.00311 |
| Haiku 4.5 | $0.00000 | $0.00155 |
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.
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]?"
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.
- 11d ago First seen · 184 lines · 0 tokens per session scan A 48b3e06a8f36
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.