image-seo-audit

image-seo-audit is a skill for Claude Code, Codex from JakeLabate/Claude-SEO-Skills. It costs 103 tokens per session (1,669 once invoked), scanned A, original, MIT.

A website image audit that checks images for search visibility, accessibility, loading speed, and technical problems. It looks for issues such as missing alternative text, layout-shift risks, large files, outdated formats, generic names, and broken URLs.

In plain words
What is it for?
Use it to inspect a full website, a section, or selected pages for image-related SEO and Core Web Vitals issues, with optional file checks.
Why use it?
It shows which images may be hard for people using screen readers to understand, slow pages down, or hurt search results. The report turns those problems into specific fixes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect a full website, a section, or selected pages for image-related SEO and Core Web Vitals issues, with optional file checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jakelabate/claude-seo-skills/image-seo-audit
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 JakeLabate/Claude-SEO-Skills --skill image-seo-audit
Clone the repo
git clone --depth 1 https://github.com/JakeLabate/Claude-SEO-Skills

Made for: Claude Code, Codex.

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 image-seo-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/jakelabate/claude-seo-skills/image-seo-audit/github.svg)](https://agentmods.dev/skills/jakelabate/claude-seo-skills/image-seo-audit)
Your own site
<a href="https://agentmods.dev/skills/jakelabate/claude-seo-skills/image-seo-audit"><img src="https://agentmods.dev/badge/skills/jakelabate/claude-seo-skills/image-seo-audit/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 image-seo-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/jakelabate/claude-seo-skills/image-seo-audit"><img src="https://agentmods.dev/badge/skills/jakelabate/claude-seo-skills/image-seo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,669 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 $0.00103 $0.01669
Opus 5 $0.00051 $0.00834
Sonnet 5 $0.00021 $0.00334
Haiku 4.5 $0.00010 $0.00167

Measured 11d ago against content hash 199048b47a84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

image-seo-audit 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 11d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/audit_images.py, scripts/extract_images.py, scripts/fetch_pages.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.

skills/image-seo-audit/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image SEO Audit

Audit the images of a website and produce an actionable SEO and performance report.

When to use this skill

Use this skill when the user asks to:

  • Audit or analyze the images on a website for SEO or accessibility
  • Find images with missing, empty, or poor alt text
  • Find images that cause layout shift (missing width/height) or load slowly (no lazy loading, oversized files)
  • Identify images served in legacy formats instead of WebP/AVIF
  • Find broken images or generic, uninformative filenames

Inputs to collect

Before starting, confirm with the user:

  1. Site URL or local files — a live site root URL (e.g., https://example.com), a sitemap URL, a list of URLs, or a local folder of HTML files.
  2. Scope — full site, a specific section (e.g., /blog/), or a list of URLs.
  3. Crawl limits — max pages (default 500) for live crawls.
  4. File checks — whether to fetch each image to measure byte size and detect broken images (the --check-files flag; slower but enables the oversized-file and broken-image checks).
  5. Size budget — the byte threshold above which an image is "oversized" (default 200 KB).

Workflow

Step 1: Gather the page set and extract images

  • If a sitemap is available (/sitemap.xml), it is used to get the canonical page list.
  • Otherwise, the crawler starts from the homepage following only same-host links.
  • For local HTML folders, all .html files are enumerated.

Use scripts/extract_images.py to build an image inventory:

python3 scripts/extract_images.py https://example.com --max-pages 500 --check-files --output image_inventory.json
# already crawled once (e.g. in a full SEO audit)? skip the crawl and reuse the shared cache:
# python3 scripts/fetch_pages.py https://example.com --output page_cache.json
# python3 scripts/extract_images.py --from-cache page_cache.json --check-files --output image_inventory.json

For every <img> the inventory records: absolute src, alt (null if the attribute is absent vs. empty string if alt=""), width/height attributes, loading, whether it has a srcset, whether it sits inside a <picture>, and its position in the page. With --check-files, each unique image URL is HEAD-requested to record HTTP status, content type, and byte size.

Read the full file on GitHub · 131 lines

Files

What ships with it

7 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. 11d ago First seen · 131 lines · 103 tokens per session scan A 199048b47a84

Subscribe to this mod's changes

image-seo-audit is a skill published in the GitHub repository JakeLabate/Claude-SEO-Skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 1,669 once invoked, about $0.0005 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 2026-08-31.