agentmods.dev

keyword-cluster

keyword-cluster is a command for Claude Code from indranilbanerjee/digital-marketing-pro. It costs 34 tokens per session (791 once invoked), scanned A, original, MIT.

A keyword planning tool that groups related search phrases into a main topic page and supporting pages. Search intent means what a person is trying to accomplish with a search.

In plain words
What is it for?
Use it to build topic hubs, group keywords by intent, prioritise pages, plan internal links, detect keyword cannibalisation, and prepare programmatic SEO projects.
Why use it?
It turns a raw keyword list into an organised content plan and helps identify overlapping pages or topics that could compete with each other.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is If you see unfamiliar placeholders or need to check which keyword data sources are connected, see [CONNECTORS.md](../CONNECTORS.md)..

Part of the digital-marketing-pro plugin — 154 skills, 18 commands, 24 agents shipped together

not rated 806repo +14 4d ago A scan 34 tokens original MIT

Good fit Use it to build topic hubs, group keywords by intent, prioritise pages, plan internal links, detect keyword cannibalisation, and prepare programmatic SEO projects.

Compare 6 commands from other repositories ↓
View source ↗ indranilbanerjee/digital-marketing-pro indranil.in
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-pro
agentmods
npx agentmods add commands/indranilbanerjee/digital-marketing-pro/keyword-cluster

Made for: Claude Code.

Or install digital-marketing-pro, the plugin that ships this one along with the rest of its 154 skills, 18 commands, 24 agents.

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 keyword-cluster

README.md
[![agentmods](https://agentmods.dev/badge/commands/indranilbanerjee/digital-marketing-pro/keyword-cluster/github.svg)](https://agentmods.dev/commands/indranilbanerjee/digital-marketing-pro/keyword-cluster)
Your own site
<a href="https://agentmods.dev/commands/indranilbanerjee/digital-marketing-pro/keyword-cluster"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/digital-marketing-pro/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.

agentmods 80×15 button for keyword-cluster

Your own site · 80×15
<a href="https://agentmods.dev/commands/indranilbanerjee/digital-marketing-pro/keyword-cluster"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/digital-marketing-pro/keyword-cluster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 791 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 $0.00034 $0.00791
Opus 5 $0.00017 $0.00396
Sonnet 5 $0.00007 $0.00158
Haiku 4.5 $0.00003 $0.00079

Measured 12d ago against content hash 18f6d7003fa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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.

commands/keyword-cluster.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Keyword Cluster

If you see unfamiliar placeholders or need to check which keyword data sources are connected, see CONNECTORS.md.

Takes a set of seed keywords and produces a publication-ready cluster plan: pillar pages with their spokes, intent-grouped, prioritised by an opinionated scoring formula, with an internal-link map and a four-gate quality scorecard. Routes to skills/keyword-cluster/SKILL.md.

Trigger

User runs /digital-marketing-pro:keyword-cluster or asks for:

  • "Cluster these keywords into a content plan"
  • "Build a pillar/spokes architecture for this topic"
  • "Design a topic hub for X"
  • "Dedupe my cannibalising pages"
  • "Plan a programmatic SEO rollout"

Inputs

  1. Seeds — either a list of 3–20 seed keywords inline, or a path to a CSV with at least a keyword column (plus optional volume, kd, intent)
  2. Target country / language (optional — uses brand profile default)
  3. SERP data (strongly recommended) — JSON map of keyword → top-N result URLs from connected rank-tracker MCP. Without this, falls back to lower-confidence lexical clustering.
  4. Filter thresholds (optional) — minimum search volume, maximum keyword difficulty

Process

  1. Load brand context + auto-apply industry / compliance rules
  2. Optionally expand seeds via brand's keyword-research MCP (/digital-marketing-pro:keyword-research) if input is < 20 keywords
  3. Filter seeds by min-volume / max-KD / banned-word lists
  4. Fetch top-10 SERPs per keyword via connected rank-tracker (with budget guard at 500-credit threshold)
  5. Run scripts/keyword_cluster.py with SERP mode (or lexical fallback)
  6. Validate the four quality gates (cannibalisation / orphan / coverage / anchor_diversity) — surface needs_review diagnostics if any fail
  7. Draft pillar-page briefs for clusters with priority_score >= 0.5
  8. Build internal-link map
  9. Sort by priority for build-order recommendation
  10. Write PLAN.md to ${CLAUDE_PLUGIN_DATA}/{brand}/seo/keyword-cluster/{date}/

Read the full file on GitHub · 59 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. 12d ago First seen · 59 lines · 34 tokens per session scan A 18f6d7003fa0

Subscribe to this mod's changes

keyword-cluster is a command published in the GitHub repository indranilbanerjee/digital-marketing-pro (806 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 791 once invoked, about $0.0002 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.

Claude CodeMarketing and SEOaeoclaude-plugincontent-marketingmarketing-automationseo
Related

Other commands, from other repositories

brand-setup

Configure brand voice, terminology, compliance guardrails, and style guide for content production.

indranilbanerjee/contentforge · 16 tokens

output-folder

Print the absolute path to the user-visible ContentForge output folder and open it in the OS file manager.

indranilbanerjee/contentforge · 20 tokens

create-content

Run the full 10-phase content production pipeline — research, draft, fact-check, humanize, and publish.

indranilbanerjee/contentforge · 22 tokens

audit-content

Audit your content library for freshness decay, coverage gaps, and optimization opportunities.

indranilbanerjee/contentforge · 14 tokens

content-brief

Generate a research-backed content brief with keyword data, competitor analysis, search intent, and SEO strategy.

indranilbanerjee/contentforge · 19 tokens

publish

Publish finished content to Webflow or WordPress with preview, verification, and HTML export fallback.

indranilbanerjee/contentforge · 18 tokens