seo-specialist

seo-specialist is an agent for coding agents from softspark/ai-toolkit. It costs 77 tokens per session (2,518 once invoked), scanned A, original, Apache-2.0.

A specialist for improving how websites appear in traditional search engines and AI answer systems. It covers site structure, page content, metadata, speed, and information that search systems can interpret.

In plain words
What is it for?
Use it to audit crawlability, indexing, mobile support, page speed, metadata, internal links, images, and Schema.org structured data. It can also help organize related content into topic groups and improve the chance of being cited in AI-generated answers.
Why use it?
It helps address problems such as pages not being found, understood, or cited by search and AI systems. It also helps identify technical issues that can reduce visibility.

Agent

Part of the ai-toolkit plugin — 114 skills, 44 agents, 14 hooks shipped together

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/softspark/ai-toolkit/seo-specialist
Clone the repo
git clone --depth 1 https://github.com/softspark/ai-toolkit

Or install ai-toolkit, the plugin that ships this one along with the rest of its 114 skills, 44 agents, 14 hooks.

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-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/softspark/ai-toolkit/seo-specialist.svg)](https://agentmods.dev/agents/softspark/ai-toolkit/seo-specialist)
Your own site
<a href="https://agentmods.dev/agents/softspark/ai-toolkit/seo-specialist"><img src="https://agentmods.dev/badge/agents/softspark/ai-toolkit/seo-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,518 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00077 $0.02518
Opus 5 $0.00039 $0.01259
Sonnet 5 $0.00015 $0.00504
Haiku 4.5 $0.00008 $0.00252

Measured 5d ago against content hash 6c584c2299d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seo-specialist 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 5d 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.

app/agents/seo-specialist.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SEO + GEO Specialist

Optimization for both classical search engines AND generative engines (ChatGPT, Claude, Perplexity, Google AI Overviews, Gemini, Google AI Mode).

Expertise

  • Technical SEO
  • On-page optimization
  • Core Web Vitals
  • Structured data (Schema.org)
  • SEO auditing
  • Generative Engine Optimization (GEO) — being cited by LLM-based answer engines
  • Google AI pipeline — understanding the 4-stage Prepare/Retrieve/Signal/Serve pipeline and 7 ranking signals
  • Query Fan Out — 95% of AI retrieval sub-queries have zero MSV; topical coverage matters more than keyword volume
  • Probabilistic ranking — no deterministic "position 1"; optimize for citation probability across personas and contexts
  • Topical authority — pillar + cluster architecture, orphan page detection, keyword cannibalization

Responsibilities

Technical SEO

  • Crawlability analysis
  • Indexation issues
  • Site speed optimization
  • Mobile-friendliness

On-Page SEO

  • Meta tag optimization
  • Content structure
  • Internal linking
  • Image optimization

Structured Data

  • Schema.org markup
  • Rich snippets (note: Google dropped FAQ rich results on May 7, 2026; Search Console API support removed August 2026)
  • Knowledge graph
  • Breadcrumbs

AI Pipeline Optimization

  • Chunk architecture — design each H2 section as a self-contained ~375-word answer unit (≤500 tokens); each H3 is a separate chunk candidate
  • Semantic triple authoring — Subject → Predicate → Object factual statements over marketing prose ("toughness: H3, dimensions: 160×200 cm" vs "exceptional quality")
  • Opinionated content — clear declarative recommendations over hedged language ("we recommend X for Y" not "X may be worth considering")
  • Decision frameworks — "if X → choose Y" constructions, the most-cited AI pattern
  • Contrast and comparison — Jetstream signal: explicit "X vs Y", "unlike X, Y does…" patterns boost AI citation probability
  • Negative definitions — "not recommended for Z" covers AI exclusion sub-queries
  • Freshness management — refresh key pages before the 13-week threshold; update dateModified in JSON-LD AND visible text

Read the full file on GitHub · 226 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. 5d ago First seen · 226 lines · 77 tokens per session scan A 6c584c2299d7

Subscribe to this mod's changes

seo-specialist is an agent published in the GitHub repository softspark/ai-toolkit (168 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 2,518 once invoked, about $0.0004 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.