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 skills add amirjahfar1/automate-seo-with-claude --skill seo-keyword-clustergit clone --depth 1 https://github.com/amirjahfar1/automate-seo-with-claudeWrote 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/skills/amirjahfar1/automate-seo-with-claude/seo-keyword-cluster)<a href="https://agentmods.dev/skills/amirjahfar1/automate-seo-with-claude/seo-keyword-cluster"><img src="https://agentmods.dev/badge/skills/amirjahfar1/automate-seo-with-claude/seo-keyword-cluster/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/skills/amirjahfar1/automate-seo-with-claude/seo-keyword-cluster"><img src="https://agentmods.dev/badge/skills/amirjahfar1/automate-seo-with-claude/seo-keyword-cluster.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 | $0.00109 | $0.02491 |
| Opus 5 | $0.00055 | $0.01246 |
| Sonnet 5 | $0.00022 | $0.00498 |
| Haiku 4.5 | $0.00011 | $0.00249 |
Grade A, and why
seo-keyword-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 12d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Example output: examples/seo-keyword-cluster-headless-cms-20260514/PLAN.md
Keyword Cluster
Transform seed keywords into a prioritised cluster plan: each cluster grouped by search intent and theme, with volume totals, a pillar concept, spoke articles, and suggested H1/H2 for each spoke.
Prerequisites
- DataForSEO MCP server connected.
- User provides: (a) 3 to 20 seed keywords, (b) target market country (default:
us), and optionally (c) minimum volume threshold (default: 100/mo), (d) maximum KD (default: 60).
Process
-
Expand seeds
mcp__dataforseo__dataforseo_labs_google_related_keywords,mcp__dataforseo__dataforseo_labs_google_keyword_suggestions,mcp__dataforseo__dataforseo_labs_google_keyword_ideas- For each seed, pull related + similar + long-tail variants in the target country.
- Target at least 100 candidate keywords per seed; de-duplicate across seeds.
-
Question-based expansion
mcp__dataforseo__dataforseo_labs_google_keyword_ideas(filter to interrogatives: who/what/why/how/can/does/is/are…)- Pull question-intent keywords for the top 5 seeds.
- These usually become spoke articles with PAA/featured-snippet potential.
-
Clean and filter
- Remove keywords below min volume and above max KD.
- Strip branded terms the target does not own.
- Tag each keyword with detected intent: informational, commercial, transactional, navigational.
-
Cluster by SERP overlap
mcp__dataforseo__serp_organic_live_advanced- Group keywords by how Google actually ranks them — shared top-10 organic URLs — not by text similarity. Token-overlap clustering manufactures cannibalisation; see
references/serp-overlap-methodology.mdfor the full algorithm and anti-pattern callouts. - Cost note. DataForSEO bills per call; this pass issues one
serp_organic_live_advancedcall per unique candidate keyword. Use the documenteddepth/limitparams to cap result size. For a large candidate set, trim it by raising the min-volume / lowering the max-KD thresholds in step 3 and re-running so fewer SERP calls are issued. - Fetch SERPs (one call per unique candidate keyword, cached for the session) — see
references/serp-overlap-methodology.md§ "Caching". Total SERP fetches = number of keywords, not number of pairs. - Pairwise overlap scoring. For each pair within an intent pre-group (see
references/serp-overlap-methodology.md§ "Pre-Grouping" for the optimisation that avoids full O(N²)), count shared URLs in the top 10 organic. Apply thresholds: 7-10 shared = same post (merge keywords), 4-6 = same cluster, 2-3 = interlink across clusters, 0-1 = separate clusters or exclude. - Form clusters from the connected components in the 4-6+ overlap graph. Target 5 to 12 clusters. Each cluster gets a name, primary keyword, secondary keywords, total volume, weighted KD.
- Classify each cluster as pillar-worthy (broad, high volume, informational) or spoke-only (narrow, specific).
- Group keywords by how Google actually ranks them — shared top-10 organic URLs — not by text similarity. Token-overlap clustering manufactures cannibalisation; see
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 142 lines · 109 tokens per session scan A abce2047eab7
seo-keyword-cluster is a skill published in the GitHub repository amirjahfar1/automate-seo-with-claude (2 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 2,491 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
seo-site-audit-pro
Flagship comprehensive SEO audit combining Ahrefs and GSC data in sequential waves with checkpoint saves. Use when user says "site audit pro", "full audit", "comprehensive audit", "audit with live data", "deep audit", "pro audit", "complete SEO audit", "run a full site audit", or "audit everything for this domain".…
seo-content
Content quality and E-E-A-T analysis with AI citation readiness assessment. Enhanced with live Ahrefs (actual keyword rankings, positions) and GSC (search query performance) data to validate static E-E-A-T analysis with real user behavior. Use when user says "content quality", "E-E-A-T", "content analysis"…
seo-core-web-vitals
Dedicated Core Web Vitals deep-dive: pull field data (CrUX / PageSpeed Insights), fall back to Lighthouse lab data, score LCP, INP, and CLS against Google's thresholds at the 75th percentile, and run per-metric diagnosis playbooks with concrete fixes. Use when user says "core web vitals", "CWV", "LCP", "INP", "CLS"…
seo-geo
Optimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences. GEO analysis enriched with Ahrefs Brand Radar AI visibility data when available. Includes brand mention signals, AI crawler accessibility, llms.txt compliance, passage-level citability scoring…
seo-lighthouse-audit
Run a Lighthouse audit against any URL via the local Lighthouse CLI or the PageSpeed Insights API fallback, parse category scores and failed audits, and map every failed audit ID to its official Chrome docs page plus a one-line fix. Use when user says "lighthouse", "lighthouse audit", "run lighthouse", "lighthouse…
seo-llms-txt
Generate, validate, or audit llms.txt files for AI search visibility. Crawls site structure, generates spec-compliant Markdown index for LLMs. Use when user says "llms.txt", "llm txt", "AI crawlers", "generate llms", "LLM file", "AI readability file".