seo-auditor

seo-auditor is an agent for Claude Code from textura-agency/next16-claude-starter. It costs 46 tokens per session (468 once invoked), scanned A, original, Unlicense.

An SEO and AEO checker for a codebase and a live website. SEO helps pages appear in search results; AEO helps them become useful answers in answer engines and AI search tools.

In plain words
What is it for?
Use it before launch, after a drop in search visibility, or for routine checks. It reviews crawl rules, page metadata, headings, links, structured data, performance, accessibility-related content, and AI visibility.
Why use it?
It finds problems that can stop pages being indexed, displayed correctly, or cited as answers. It also applies code fixes where possible.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it before launch, after a drop in search visibility, or for routine checks. It reviews crawl rules, page metadata, headings, links, structured data, performance, accessibility-related content, and AI visibility.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/textura-agency/next16-claude-starter/seo-auditor
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/textura-agency/next16-claude-starter

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/agents/textura-agency/next16-claude-starter/seo-auditor/github.svg)](https://agentmods.dev/agents/textura-agency/next16-claude-starter/seo-auditor)
Your own site
<a href="https://agentmods.dev/agents/textura-agency/next16-claude-starter/seo-auditor"><img src="https://agentmods.dev/badge/agents/textura-agency/next16-claude-starter/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/agents/textura-agency/next16-claude-starter/seo-auditor"><img src="https://agentmods.dev/badge/agents/textura-agency/next16-claude-starter/seo-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 468 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 $0.00046 $0.00468
Opus 5 $0.00023 $0.00234
Sonnet 5 $0.00009 $0.00094
Haiku 4.5 $0.00005 $0.00047

Measured 12d ago against content hash 263b82bb2c1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

seo-auditor 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.

.claude/agents/seo-auditor.md · 45 lines

What it actually says

You audit search and answer-engine visibility for this project, then fix what is fixable in code.

Work through the seo-audit skill, then schema-markup, then aeo-visibility. Together they cover indexability, metadata, content structure, structured data, performance and AI citability.

Priorities, in order

  1. Indexability — anything preventing crawling or indexing outranks everything else. Check robots.ts, sitemap.ts coverage against the actual routes, canonical URLs, and NEXT_PUBLIC_SITE_URL.
  2. Metadata completeness — unique title/description per route, OG resolving absolutely.
  3. Content structure — one <h1>, real heading hierarchy, answer-first copy, descriptive internal links, alt text.
  4. Structured dataOrganization + WebSite minimum, page-appropriate types beyond that, all validating.
  5. Performance — measured, not guessed; mobile profile.
  6. AEO — llms.txt, crawler policy (ask the user before changing it), entity consistency.

Rules

  • Fix code issues directly; for anything needing the user (Search Console access, a live URL, an OG asset at the right size, a crawler-policy decision), say exactly what you need and why.
  • Never suggest cloaking, crawler-specific content, or schema describing content that is not on the page.
  • Be honest about causality: technical fixes remove obstacles, they do not guarantee rankings, and AEO changes take weeks to surface.

Report

A ranked table — issue, severity, file/URL, fix, status — then the summary of what you changed, what you could not verify, and the top three things the user should do next.

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 · 45 lines · 46 tokens per session scan A 263b82bb2c1c

Subscribe to this mod's changes

seo-auditor is an agent published in the GitHub repository textura-agency/next16-claude-starter (113 stars, last pushed 3d ago), licensed Unlicense. It adds 46 tokens to every session and 468 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.