agentmods.dev

seo-validate

seo-validate is a skill for Claude Code from softspark/ai-toolkit. It costs 59 tokens per session (4,021 once invoked), scanned A, original, Apache-2.0.

A read-only checker for website search visibility, covering page metadata, structured data, language links, crawlability, accessibility, and loading-performance signals.

In plain words
What is it for?
Use it to inspect HTML and web projects for SEO problems such as missing metadata, incorrect Schema.org data, rendering issues, and Core Web Vitals risks.
Why use it?
It helps find technical issues that can stop search engines from understanding or indexing a site, or that can hurt user experience.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Part of the ai-toolkit plugin — 113 skills, 44 agents, 14 hooks shipped together

not rated 170repo +2 2d ago A scan 59 tokens original Apache-2.0

Good fit Use it to inspect HTML and web projects for SEO problems such…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/softspark/ai-toolkit/seo-validate
View source ↗ softspark/ai-toolkit softspark.eu
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.

Any agent
npx skills add softspark/ai-toolkit --skill seo-validate
Clone the repo
git clone --depth 1 https://github.com/softspark/ai-toolkit

Made for: Claude Code.

Or install ai-toolkit, the plugin that ships this one along with the rest of its 113 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-validate

README.md
[![agentmods](https://agentmods.dev/badge/skills/softspark/ai-toolkit/seo-validate.svg)](https://agentmods.dev/skills/softspark/ai-toolkit/seo-validate)
Your own site
<a href="https://agentmods.dev/skills/softspark/ai-toolkit/seo-validate"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/seo-validate.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,021 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 $0.00059 $0.04021
Opus 5 $0.00030 $0.02011
Sonnet 5 $0.00012 $0.00804
Haiku 4.5 $0.00006 $0.00402

Measured 3d ago against content hash 7701f632f942, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

seo-validate 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/seo-scanner.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/seo-validate/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/seo-validate — SEO Validation Scanner

$ARGUMENTS

Scan a codebase for SEO issues using pattern-matching heuristics. Detects W3C/HTML violations, meta tag gaps, structured data problems, hreflang errors, Core Web Vitals risks (LCP/INP/CLS), resource-hint misuse, above-the-fold anti-patterns, GEO gaps (chunk architecture, hedging language, decision frameworks, semantic triples, freshness), topical authority gaps (pillar/cluster structure, orphan pages, cannibalization), SPA/CSR/SSG crawlability problems, technical SEO misconfigurations, and accessibility-for-SEO issues. Read-only — never modifies files.

Standards basis: W3C HTML5 Recommendation, W3C WCAG 2.2, Schema.org vocabulary, IETF RFC 5646 (BCP 47 language tags) for hreflang, web.dev Core Web Vitals thresholds (LCP <2.5s, INP <200ms, CLS <0.1), Google Search Central crawlability guidelines, and emerging GEO (Generative Engine Optimization) practices.

Usage

/seo-validate                                # Scan full project, auto-detect framework
/seo-validate src/                           # Scan specific path
/seo-validate --scope rendering              # Only SPA/CSR/SSG crawlability checks
/seo-validate --scope performance            # Only Core Web Vitals static signals
/seo-validate --scope geo                    # Only GEO (Generative Engine Optimization)
/seo-validate --scope topical               # Only topical authority and cluster architecture
/seo-validate --severity high                # Filter to HIGH findings only
/seo-validate --framework next               # Force framework (skip auto-detection)
/seo-validate --rendering csr                # Force rendering-mode interpretation
/seo-validate --output json                  # Structured JSON output for CI integration

Scopes:

  • full (default) — all 10 categories
  • technical — HTML semantics, hreflang, CWV, rendering, technical SEO (categories 1, 4, 5, 7, 8)
  • content — meta/OG, structured data, GEO, a11y-for-SEO (categories 2, 3, 6, 9)
  • performance — only CWV static signals (category 5)
  • geo — only GEO / citability checks (category 6)
  • rendering — only category 7 (SPA/CSR/SSG crawlability) — useful for migration audits
  • topical — only topical authority and cluster architecture (category 10)

Read the full file on GitHub · 246 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 246 lines · 59 tokens per session scan A 7701f632f942

Subscribe to this mod's changes

seo-validate is a skill published in the GitHub repository softspark/ai-toolkit (170 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 4,021 once invoked, about $0.0003 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 2026-09-03.

Claude CodeMarketing and SEOai-agentsai-skillsanthropicclaudecline
Related

Other skills, from other repositories

cline-fix-volatile-msg

Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.

OnlyTerp/prompt-cache-skills · 50 tokens

aider-1h-ttl

Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.

OnlyTerp/prompt-cache-skills · 38 tokens

continue-enable-defaults

Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.

OnlyTerp/prompt-cache-skills · 27 tokens

continue-gemini-explicit

Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.

OnlyTerp/prompt-cache-skills · 31 tokens

opencode-bedrock-doc-blocks

OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.

OnlyTerp/prompt-cache-skills · 32 tokens

roo-fix-volatile-msg

Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).

OnlyTerp/prompt-cache-skills · 42 tokens