seo-auditor

seo-auditor is a command for Claude Code from ricneves-ai/flowgrammers-skills. It costs 75 tokens per session (1,533 once invoked), scanned A, original, MIT.

A documentation SEO auditor that scans README files and documentation pages for search-related issues, including headings, keywords, readability, duplicate content, broken links, and metadata. It can apply non-destructive fixes, update a sitemap, and create a report.

In plain words
What is it for?
Use it to audit or optimize a documentation directory, run a report-only scan, fix supported issues in place, and update sitemap.xml.
Why use it?
It finds problems that can make documentation harder for people and search engines to understand. It also reduces the need to inspect many documentation files manually.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 marketing-skill/content-production/scripts/content_scorer.py {arquivo}.

Good fit Use it to audit or optimize a documentation directory, run a report-only scan, fix supported issues in place, and update sitemap.xml.

Compare 6 commands from other repositories ↓
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/ricneves-ai/flowgrammers-skills
agentmods
npx agentmods add commands/ricneves-ai/flowgrammers-skills/seo-auditor

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/seo-auditor/github.svg)](https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/seo-auditor)
Your own site
<a href="https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/seo-auditor"><img src="https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/seo-auditor/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-auditor

Your own site · 80×15
<a href="https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/seo-auditor"><img src="https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/seo-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,533 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00075 $0.01533
Opus 5 $0.00037 $0.00766
Sonnet 5 $0.00015 $0.00307
Haiku 4.5 $0.00007 $0.00153

Measured 9d ago against content hash 6903255123bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

seo-auditor scanned grade A with 1 finding 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 9d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find . -maxdepth 2 -name 'README.md' -not -path './.codex/*' -not -path './.gemini/*' | sort

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

commands/seo-auditor.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/seo-auditor

Varre, audita e otimiza sistematicamente arquivos de documentação para SEO. Foca em README.md e páginas docs/ — corrige problemas in-place, preserva rankings de páginas de alto desempenho e gera um relatório final.

Uso

/seo-auditor                    # Audita todos os docs/ e README.md raiz
/seo-auditor docs/skills/       # Audita um subdiretório específico
/seo-auditor --report-only      # Varre sem fazer alterações

O que faz

Executa todas as 7 fases sequencialmente. Corrige automaticamente problemas não destrutivos. Preserva conteúdo já bem posicionado. Reporta tudo ao final.


Fase 1: Descoberta e Linha de Base

1a. Identificar arquivos alvo

find docs/ -name '*.md' -type f | sort
find . -maxdepth 2 -name 'README.md' -not -path './.codex/*' -not -path './.gemini/*' | sort

Classifica cada arquivo:

  • Novos/modificados recentemente — arquivos alterados nos últimos 2 commits
  • Páginas índice — arquivos index.md (alta autoridade, tratar com cuidado)
  • Páginas de skilldocs/skills/**/*.md
  • Páginas estáticasdocs/index.md, docs/getting-started.md, etc.
  • Arquivos README — README.md raiz e de domínios

1b. Capturar linha de base

Para cada arquivo alvo, extrai o estado SEO atual: campo title:, campo description:, primeiro # H1, todos os H2/H3, contagem de palavras, links internos e externos.


Fase 2: Auditoria de Meta Tags

Tag de Título (title:)

  • Deve existir e não estar vazia
  • Tamanho ideal: 50–60 caracteres
  • Deve conter uma palavra-chave principal
  • Não deve duplicar o título de outra página

Meta Descrição (description:)

  • Deve existir e não estar vazia
  • Tamanho: 120–160 caracteres
  • Deve conter a palavra-chave principal de forma natural
  • Deve ser única entre todas as páginas
  • Não deve começar com "Esta página..." ou "Este documento..."

Fase 3: Qualidade de Conteúdo e Legibilidade

Estrutura de Headings

  • Exatamente um # H1 por página
  • H2s seguem H1, H3s seguem H2 — sem pular níveis
  • Headings devem conter palavras-chave de forma natural
  • Sem headings duplicados na mesma página

Read the full file on GitHub · 177 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. 9d ago First seen · 177 lines · 75 tokens per session scan A 6903255123bf

Subscribe to this mod's changes

seo-auditor is a command published in the GitHub repository ricneves-ai/flowgrammers-skills (112 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 1,533 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.