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.
npx agentmods add commands/seite-sh/seite/clustergit clone --depth 1 https://github.com/seite-sh/seiteWhat 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 | $0.00000 | $0.02915 |
| Opus 5 | $0.00000 | $0.01458 |
| Sonnet 5 | $0.00000 | $0.00583 |
| Haiku 4.5 | $0.00000 | $0.00292 |
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.
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.
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:
- Search
research/for any existing/research-topicsoutput:Glob: research/topic-clusters-*.md - Search for any existing research on this topic:
Glob: research/*[topic-slug]*.md - 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.
-
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')}\") " -
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')}\") " -
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" -
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
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.
- 2d ago First seen · 362 lines · 0 tokens per session scan A 2352542f8877
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.
Other commands, from other repositories
fieldtheory
Explain and drive the Field Theory CLI — bookmark-sourced seeds, repo-aware possibility runs that score ideas onto a 2x2 grid, and the interconnected .md files they leave behind. Trigger when the user asks about ft, bookmarks, seeds, ft possible (or the older name ft ideas), grids, dots/nodes, or how to turn saved…
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.
wiki-digest
Generate a daily or weekly digest of wiki changes — new sources, pages, insights, and gaps.
prd-triage
Triage pending findings on the active PRD.
issue-amend
Re-snapshot the active issue's scope from the spec, clear verified and reviewed receipts, and record the change as a permanent amendment.
q-research
Read the research-mode skill's SKILL.md for the full ruleset before proceeding. Follow all constraints, the source lookup cascade, the token budget, and the "what counts as cited" rules exactly.