seomachine: Command for Claude Code

.claude/commands/research-topics.md

research-topics is a command for Claude Code from TheCraigHewitt/seomachine. It costs 0 tokens per session (812 once invoked), scanned A, original, MIT.

A command that groups a site’s ranking keywords into related topics and measures how completely each topic is covered. It uses Google Search Console, which reports a site’s search impressions, clicks, and positions, plus other SEO data.

In plain words
What is it for?
Use it to find content gaps, compare topic coverage, prioritize areas to improve, and create a topic-cluster report.
Why use it?
It reveals topics where the site is strong, weak, or missing useful related content.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

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 · 7,434 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-topics.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-topics

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/thecraighewitt/seomachine/research-topics"><img src="https://agentmods.dev/badge/commands/thecraighewitt/seomachine/research-topics.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 812 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 $0.00812
Opus 5 $0.00000 $0.00406
Sonnet 5 $0.00000 $0.00162
Haiku 4.5 $0.00000 $0.00081

Measured 13d ago against content hash b8f5e3a000d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

research-topics 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 13d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/research-topics.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Topics Command

Analyze topical authority by clustering keywords into related topics.

Usage

/research-topics

What This Command Does

Groups all your ranking keywords into topic clusters and identifies:

  • Strong Authority Topics: Where you dominate (maintain & expand)
  • Moderate Authority Topics: Partial coverage (strengthen)
  • Weak Authority Topics: BIGGEST OPPORTUNITY (build comprehensive clusters)
  • Coverage Gaps: Related keywords within each topic you don't rank for

For each topic:

  • Authority score (0-100) based on coverage, position, demand
  • Number of keywords ranking
  • Average position
  • Total impressions and clicks
  • Coverage gaps to fill

Process

Execute topic cluster analysis:

python3 research_topic_clusters.py

This will:

  1. Fetch all ranking keywords from GSC (90 days)
  2. Cluster keywords into topics using:
    • ML clustering (TF-IDF + K-means) if sklearn available
    • Pattern-based clustering as fallback
  3. Calculate authority score for each cluster
  4. Identify coverage gaps using DataForSEO
  5. Prioritize weak clusters with high demand
  6. Generate report: research/topic-clusters-YYYY-MM-DD.md

Output

The report includes:

Authority Distribution

  • Strong Authority: Topics you dominate
  • Moderate Authority: Partial coverage
  • Weak Authority: OPPORTUNITIES
  • Minimal Authority: Major gaps

Weak Authority Topics (FOCUS HERE!)

For each weak cluster:

  • Authority score and level
  • Current keyword count
  • Average position
  • Total impressions
  • Top 5 current keywords
  • 8-10 coverage gaps with search volume
  • Recommended action (build 8-12 article cluster)

Strong Authority Topics (MAINTAIN)

For each strong cluster:

  • Performance metrics
  • Top performing keywords
  • Expansion opportunities
  • Maintenance recommendations

Key Insight

Weak clusters with high demand = Your biggest opportunity

Example: "Content Marketing"

  • Only 3 keywords ranking
  • Average position 28
  • 5,000 impressions/month (HIGH DEMAND!)
  • 15+ related keywords you don't rank for
  • Action: Build comprehensive 10-article cluster

Read the full file on GitHub · 132 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. 13d ago First seen · 132 lines · 0 tokens per session scan A b8f5e3a000d6

Subscribe to this mod's changes

research-topics is a command published in the GitHub repository TheCraigHewitt/seomachine (7,434 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 812 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.