cluster

A command that plans a topic cluster: a main pillar page supported by related articles connected through internal links. Internal links are links between pages on the same website.

In plain words
What is it for?
Use it to define the pillar page, plan 8–12 supporting articles, map their links, research keywords, and set a creation sequence.
Why use it?
It helps organise coverage of a subject and identify which related pages should be created and connected.

Command for Claude Code

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.

agentmods
npx agentmods add commands/seite-sh/seite/cluster
Clone the repo
git clone --depth 1 https://github.com/seite-sh/seite

Made for: Claude Code.

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 2,915 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.02915
Opus 5 $0.00000 $0.01458
Sonnet 5 $0.00000 $0.00583
Haiku 4.5 $0.00000 $0.00292

Measured 2d ago against content hash 2352542f8877, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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

This is a copy

100% identical to cluster — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

seite-sh/.claude/commands/cluster.md · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cluster Command

Build a complete topic cluster strategy with pillar page definition, 8-12 supporting articles, internal linking map, and creation sequence.

Usage

/cluster [topic]

Examples:

  • /cluster "content marketing"
  • /cluster "podcast monetization"
  • /cluster "remote team management"

Process

Step 1: Gather Existing Data

Check for existing research that informs this cluster:

  1. Search research/ for any existing /research-topics output:
    Glob: research/topic-clusters-*.md
    
  2. Search for any existing research on this topic:
    Glob: research/*[topic-slug]*.md
    
  3. If found, extract:
    • Authority score for this topic area
    • Keywords already ranking
    • Coverage gaps identified
    • Any SERP analysis already done

Document what exists vs. what needs fresh research.

Step 2: Keyword Research

Build the complete keyword landscape for this topic.

  1. DataForSEO Keyword Ideas

    python3 -c "
    import sys; sys.path.insert(0, 'data_sources/modules')
    from dataforseo import DataForSEOClient
    client = DataForSEOClient()
    results = client.get_keyword_ideas('$ARGUMENTS')
    for kw in sorted(results, key=lambda x: x.get('search_volume', 0), reverse=True)[:30]:
        print(f\"{kw.get('keyword', 'N/A')} | Vol: {kw.get('search_volume', 'N/A')} | Diff: {kw.get('keyword_difficulty', 'N/A')} | CPC: {kw.get('cpc', 'N/A')}\")
    "
    
  2. DataForSEO Questions

    python3 -c "
    import sys; sys.path.insert(0, 'data_sources/modules')
    from dataforseo import DataForSEOClient
    client = DataForSEOClient()
    results = client.get_questions('$ARGUMENTS')
    for q in results[:15]:
        print(f\"{q.get('keyword', 'N/A')} | Vol: {q.get('search_volume', 'N/A')}\")
    "
    
  3. WebSearch for Additional Keywords

    WebSearch: "[topic] guide" site:ahrefs.com OR site:semrush.com OR site:moz.com
    WebSearch: "[topic] related keywords" OR "[topic] subtopics"
    
  4. Group Keywords into Tiers

    • Pillar-level: Broad, high-volume (1000+ searches/mo), competitive
    • Supporting-level: Specific subtopics, medium volume (100-1000/mo)
    • Long-tail: Very specific queries, low volume (<100/mo), low competition

Read the full file on GitHub · 362 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. 2d ago First seen · 362 lines · 0 tokens per session scan A 2352542f8877

Subscribe to this mod's changes

cluster is a command published in the GitHub repository seite-sh/seite (19 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,915 tokens. A static security scan graded it A with 0 findings. It is 100% identical to cluster, differing in 0 lines, and is treated as a copy.