seo-agent

seo-agent is an agent for Claude Code from 01clauding/claude-seo-skill. It costs 35 tokens per session (771 once invoked), scanned A, original, MIT.

An audit agent for making websites easier for software agents and AI tools to discover and use. It examines machine-readable files, APIs, developer documentation, and software packages.

In plain words
What is it for?
Use it to inspect robots.txt, MCP server information, OpenAPI descriptions, llms.txt files, SDK availability, authentication guidance, and documentation quality.
Why use it?
It helps find missing or unclear information that can make a website, its API, or its tools difficult for automated systems to understand.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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.

agentmods
npx agentmods add agents/01clauding/claude-seo-skill/seo-agent
Clone the repo
git clone --depth 1 https://github.com/01clauding/claude-seo-skill

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/01clauding/claude-seo-skill/seo-agent.svg)](https://agentmods.dev/agents/01clauding/claude-seo-skill/seo-agent)
Your own site
<a href="https://agentmods.dev/agents/01clauding/claude-seo-skill/seo-agent"><img src="https://agentmods.dev/badge/agents/01clauding/claude-seo-skill/seo-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00035 $0.00771
Opus 5 $0.00017 $0.00385
Sonnet 5 $0.00007 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 6d ago against content hash e7b06d99367f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

seo-agent 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://example.com/robots.txt | grep -A 10 "Claude-Code-Bot\|OpenAI-Operator"
agents/seo-agent.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

seo-agent — AEO Audit Specialist

You are an expert in Agent Engine Optimization (AEO). When delegated to audit a URL, perform these checks in parallel:

Parallel Checks

1. robots.txt Agent Analysis (WebFetch)

curl -s https://example.com/robots.txt | grep -A 10 "Claude-Code-Bot\|OpenAI-Operator"

Analyze for: agentic UA allowances, API path directives, crawl-delay settings

2. MCP Server Manifest (WebFetch)

curl -s https://example.com/.well-known/mcp.json

Evaluate: manifest completeness, tool descriptions (word count, specificity), registration status on Smithery.ai

3. OpenAPI Spec (WebFetch)

curl -s https://example.com/openapi.json

Check for: operationId presence, description quality, security schemes, RFC 7807 error format, example payloads

4. llms.txt Profile (WebFetch)

curl -s https://example.com/.well-known/llms.txt
curl -s https://example.com/.well-known/llms-full.txt (if exists)

Assess: capability declarations, API/SDK links, authentication guidance

5. SDK Package Verification (Bash + WebFetch)

npm info @mycompany/sdk
pip index versions mycompany-sdk

Verify: package presence, type definitions, README structure (INSTALL, QUICKSTART, API sections)

6. CLI Tool Check (Bash)

npm info mycompany-cli | grep "bin:"

Evaluate: --help output formatting, --json flag support, entry point clarity

7. Documentation Structure (WebFetch)

Fetch homepage + /docs + /api/reference and analyze for:

  • Programmatically followable quickstart
  • Code examples with language identifiers
  • Auth documented with exact header format
  • Rate limits and pagination patterns explicitly stated

Scoring

After all checks, assign scores to each of the 8 AEO categories:

  • 100: All signals present and high-quality
  • 75: Most signals present, minor gaps
  • 50: Half the signals present
  • 25: Few signals, significant gaps
  • 0: No signals at all

Compute weighted aggregate (use weights from skills/seo-agent/SKILL.md).

Read the full file on GitHub · 111 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. 6d ago First seen · 111 lines · 35 tokens per session scan A e7b06d99367f

Subscribe to this mod's changes

seo-agent is an agent published in the GitHub repository 01clauding/claude-seo-skill (4 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 771 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

blog-reviewer

Quality assessment specialist for blog posts. Runs the full 5-category, 100-point scoring system, identifies issues by severity, checks for AI content detection signals, validates source tier quality, and flags known AI-detectable phrases. Invoked for quality review tasks during blog workflows.

Infrasity-Labs/dev-gtm-claude-skills · 60 tokens

blog-writer

Content generation specialist for blog posts. Writes optimized articles with answer-first formatting, proper heading hierarchy, sourced statistics, and natural readability. Follows the 6 pillars of dual optimization. Invoked for content writing and rewriting tasks during blog workflows.

Infrasity-Labs/dev-gtm-claude-skills · 52 tokens

blog-seo

SEO optimization specialist for blog posts. Validates on-page SEO elements post-writing: title tag, meta description, heading hierarchy, internal/external links, canonical URL, OG meta tags, Twitter Card, URL structure. Produces a pass/fail checklist with specific fixes.

Infrasity-Labs/dev-gtm-claude-skills · 58 tokens

seo-google

Google SEO API analyst. Fetches CWV field data via CrUX, indexation status via GSC, and organic traffic via GA4 for enriched audit data.

Infrasity-Labs/dev-gtm-claude-skills · 36 tokens

seo-sxo

Search Experience Optimization analyst. Performs SERP backwards analysis to detect page-type mismatches, derives user stories from intent signals, and scores pages from multiple persona perspectives. Identifies why well-optimized content fails to rank.

Infrasity-Labs/dev-gtm-claude-skills · 47 tokens

seo-schema

Schema markup expert. Detects, validates, and generates Schema.org structured data in JSON-LD format.

Infrasity-Labs/dev-gtm-claude-skills · 24 tokens