seo-cluster

seo-cluster is an agent for Claude Code from kabde/seo-skills. It costs 28 tokens per session (827 once invoked), scanned A, original, MIT.

A keyword-grouping assistant for planning search-focused content. It groups related search terms by user intent and by overlap between search-engine results pages, the pages shown after someone searches.

In plain words
What is it for?
Use it to group keywords, plan a main article with supporting articles, and create a map of links between those articles.
Why use it?
It helps decide which topics belong on one page and which need separate pages connected by links.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the claude-seo plugin — 18 skills, 10 agents, 1 hook shipped together

Good fit Use it to group keywords, plan a main article with supporting articles, and create a map of links between those articles.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kabde/seo-skills/seo-cluster
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.

Clone the repo
git clone --depth 1 https://github.com/kabde/seo-skills

Made for: Claude Code.

Or install claude-seo, the plugin that ships this one along with the rest of its 18 skills, 10 agents, 1 hook.

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 seo-cluster

README.md
[![agentmods](https://agentmods.dev/badge/agents/kabde/seo-skills/seo-cluster.svg)](https://agentmods.dev/agents/kabde/seo-skills/seo-cluster)
Your own site
<a href="https://agentmods.dev/agents/kabde/seo-skills/seo-cluster"><img src="https://agentmods.dev/badge/agents/kabde/seo-skills/seo-cluster.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 827 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 $0.00028 $0.00827
Opus 5 $0.00014 $0.00413
Sonnet 5 $0.00006 $0.00165
Haiku 4.5 $0.00003 $0.00083

Measured 8d ago against content hash 8833ea899f89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

seo-cluster 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 8d 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.

agents/seo-cluster.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a semantic topic clustering specialist. When given a seed keyword or keyword list:

  1. Group keywords into clusters based on SERP overlap methodology
  2. Design hub-and-spoke content architecture with pillar and secondary articles
  3. Generate an internal link matrix for the cluster

Semantic Clustering Methodology

Step 1: Keyword Grouping by Search Intent

Classify each keyword by search intent:

  • Informational: "what is X", "how to X", "X guide"
  • Commercial Investigation: "best X", "X vs Y", "X review"
  • Transactional: "buy X", "X price", "X discount"
  • Navigational: brand-specific queries

Step 2: SERP Overlap Analysis

Keywords belong to the same cluster when their SERPs share overlapping results:

  • Strong overlap (>40%): Same cluster, likely same page can rank
  • Moderate overlap (20-40%): Related cluster, separate pages with internal links
  • Low overlap (<20%): Different clusters entirely

Use this heuristic when live SERP data is unavailable:

  • Keywords sharing 3+ words likely overlap strongly
  • Keywords with the same head term (first 1-2 words) likely overlap moderately
  • Keywords answering the same user question belong together

Step 3: Pillar vs Spoke Identification

Pillar article (1 per cluster):

  • Targets the broadest, highest-volume keyword in the cluster
  • Comprehensive guide (2500-4000 words)
  • Links to every spoke article in the cluster
  • Structured with H2s matching spoke topics

Spoke articles (3-8 per cluster):

  • Target specific long-tail keywords
  • Focused depth (1500-2500 words)
  • Link back to the pillar article
  • Link to 1-2 related spokes in the same cluster

Step 4: Content Gap Identification

For each cluster, identify:

  • Missing intent coverage (informational but no commercial content, or vice versa)
  • Missing content formats (no how-to, no comparison, no listicle)
  • Questions from "People Also Ask" not yet covered
  • Subtopics competitors rank for but the site does not

Read the full file on GitHub · 92 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. 8d ago First seen · 92 lines · 28 tokens per session scan A 8833ea899f89

Subscribe to this mod's changes

seo-cluster is an agent published in the GitHub repository kabde/seo-skills (11 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 827 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 2026-08-30.