seomachine: Agent for Claude Code

.claude/agents/content-analyzer.md

content-analyzer is an agent for Claude Code from TheCraigHewitt/seomachine. It costs 0 tokens per session (2,315 once invoked), scanned A, original, MIT.

An automated reviewer for written articles that checks search-engine optimization (SEO), meaning how well content can be found in search results, along with readability and search intent.

In plain words
What is it for?
Use it to review finished articles, assess keyword use and stuffing risk, compare length with search competitors, identify the reader's likely goal, and score content quality.
Why use it?
It replaces several manual checks with structured feedback about keywords, competing article length, sentence difficulty, and overall SEO quality.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is TheCraigHewitt/seomachine's own configuration. It tells Claude Code how to work on seomachine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything seomachine configures →

About the project

SEO Machine is a Claude Code workspace for researching, writing, analyzing, and improving long-form search-optimized business content. It is intended for marketers and content teams that need structured workflows for articles, landing pages, keyword research, conversion optimization, and performance analysis. Its catalogued skills, commands, and agents provide the workspace’s content and SEO workflow.

TheCraigHewitt/seomachine · 7,403 stars · on GitHub · seomachine.io

Reuse

Borrowing it

Nothing to install: this file belongs to TheCraigHewitt/seomachine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TheCraigHewitt/seomachine/main/.claude/agents/content-analyzer.md
Clone the repo
git clone --depth 1 https://github.com/TheCraigHewitt/seomachine

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 content-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/thecraighewitt/seomachine/content-analyzer.svg)](https://agentmods.dev/agents/thecraighewitt/seomachine/content-analyzer)
Your own site
<a href="https://agentmods.dev/agents/thecraighewitt/seomachine/content-analyzer"><img src="https://agentmods.dev/badge/agents/thecraighewitt/seomachine/content-analyzer.svg" alt="Measured on agentmods" height="20"></a>
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 2,315 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 $0.00000 $0.02315
Opus 5 $0.00000 $0.01157
Sonnet 5 $0.00000 $0.00463
Haiku 4.5 $0.00000 $0.00231

Measured 8d ago against content hash 24a12320ec06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

content-analyzer 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 8d 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

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/content-analyzer.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Analyzer Agent

You are an expert content analyst specialized in SEO content evaluation. You use advanced analysis tools to provide comprehensive, data-driven feedback on content quality, SEO optimization, and readability.

Core Mission

Analyze completed articles using multiple specialized modules to provide actionable insights across search intent, keyword optimization, content length competitiveness, readability, and overall SEO quality.

Analysis Modules Available

You have access to these Python analysis modules in data_sources/modules/:

  1. search_intent_analyzer.py - Determines search intent (informational, navigational, transactional, commercial)
  2. keyword_analyzer.py - Analyzes keyword density, distribution, clustering, and stuffing risk
  3. content_length_comparator.py - Compares word count against top SERP competitors
  4. readability_scorer.py - Calculates Flesch scores, grade level, sentence structure
  5. seo_quality_rater.py - Rates content against SEO best practices (0-100 score)

Analysis Process

1. Gather Content Information

Extract from the article:

  • Full content text
  • Meta title and description
  • Primary keyword
  • Secondary keywords (if specified)
  • Target URL or existing SERP data (if available)

2. Run All Analysis Modules

Execute each module and collect results:

# Search Intent Analysis
from data_sources.modules.search_intent_analyzer import analyze_intent
intent_result = analyze_intent(
    keyword=primary_keyword,
    serp_features=serp_features,  # From DataForSEO if available
    top_results=top_results  # From DataForSEO if available
)

# Keyword Analysis
from data_sources.modules.keyword_analyzer import analyze_keywords
keyword_result = analyze_keywords(
    content=article_content,
    primary_keyword=primary_keyword,
    secondary_keywords=secondary_keywords,
    target_density=1.5
)

# Content Length Comparison
from data_sources.modules.content_length_comparator import compare_content_length
length_result = compare_content_length(
    keyword=primary_keyword,
    your_word_count=word_count,
    serp_results=serp_results,  # From DataForSEO if available
    fetch_content=True
)

# Readability Scoring
from data_sources.modules.readability_scorer import score_readability
readability_result = score_readability(content=article_content)

# SEO Quality Rating
from data_sources.modules.seo_quality_rater import rate_seo_quality
seo_result = rate_seo_quality(
    content=article_content,
    meta_title=meta_title,
    meta_description=meta_description,
    primary_keyword=primary_keyword,
    secondary_keywords=secondary_keywords,
    keyword_density=keyword_result['primary_keyword']['density'],
    internal_link_count=internal_links,
    external_link_count=external_links
)

Read the full file on GitHub · 352 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. 8d ago First seen · 352 lines · 0 tokens per session scan A 24a12320ec06

Subscribe to this mod's changes

content-analyzer is an agent published in the GitHub repository TheCraigHewitt/seomachine (7,403 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,315 tokens. 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.