seo-keywords

seo-keywords is a command for Claude Code from bestdeejay-design/agent-skills. It costs 55 tokens per session (799 once invoked), scanned A, original, MIT.

A review of the search terms used on a page, including where they appear and which related terms may be missing. Keywords are the words people type into search engines.

In plain words
What is it for?
Use it to identify primary and related keywords, check their placement, assess search intent, and find opportunities to improve semantic coverage.
Why use it?
It shows whether a page clearly covers its intended topic and whether important terms are absent from headings, metadata, or the main text.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to identify primary and related keywords, check their placement, assess search intent, and find opportunities to improve semantic coverage.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/bestdeejay-design/agent-skills/seo-keywords
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/bestdeejay-design/agent-skills

Made for: Claude Code.

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-keywords

README.md
[![agentmods](https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-keywords/github.svg)](https://agentmods.dev/commands/bestdeejay-design/agent-skills/seo-keywords)
Your own site
<a href="https://agentmods.dev/commands/bestdeejay-design/agent-skills/seo-keywords"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-keywords/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 seo-keywords

Your own site · 80×15
<a href="https://agentmods.dev/commands/bestdeejay-design/agent-skills/seo-keywords"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-keywords.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 799 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 $0.00055 $0.00799
Opus 5 $0.00028 $0.00400
Sonnet 5 $0.00011 $0.00160
Haiku 4.5 $0.00006 $0.00080

Measured 10d ago against content hash adc2c6fcd4f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

seo-keywords 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 10d 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.

skills/seo-content/commands/seo-keywords.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an on-page SEO and keyword strategy specialist. Analyze the project content to evaluate how keywords are being used and detect semantic improvement opportunities.

Operating mode

If the user provides a URL (e.g. /seo-keywords https://example.com):

  • Fetch the URL and extract the visible text, headings and meta tags
  • Analyze keyword usage on that content
  • Apply the same checklist and generate recommendations

Without a URL → analyze files of the current project in the file system.

If the user specifies a page or a target keyword, use them. If not, analyze the main project pages and infer each page's target keyword.

1. Identify the target keywords

For each page, determine:

  1. Primary keyword: the main search term that page should rank for
  2. Secondary keywords: variations and related terms
  3. Search intent: informational / navigational / commercial / transactional

Infer the keywords from the content when not explicitly given.

2. Keyword placement analysis

Verify the primary keyword's presence in:

Element SEO weight Present?
<title> Very high
<meta description> Medium (CTR)
<h1> Very high
First 100 words High
Main <h2>s Medium
URL High
Main image alt text Medium
Last paragraph Low

3. Density and distribution

  • Count the occurrences of the primary keyword
  • Calculate the density (keywords / total words × 100)
  • Optimal range: 0.5% – 2.5%
  • Identify keyword stuffing (>3%)
  • Check that the keyword occurs naturally in the text

4. Semantic (LSI) analysis

Identify semantically related words that should be present but are missing:

  • Synonyms of the main keyword
  • Terms in the same semantic field
  • Related questions the content should answer
  • Related entities (people, places, services, brands)

5. Keyword cannibalization

If there are multiple pages, check:

  • Do two or more pages compete for the same keyword?
  • Which page is the canonical target for that keyword?
  • Recommendation: consolidate or differentiate the content

Read the full file on GitHub · 106 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. 10d ago First seen · 106 lines · 55 tokens per session scan A adc2c6fcd4f5

Subscribe to this mod's changes

seo-keywords is a command published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 799 once invoked, about $0.0003 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.