seo-fixer

seo-fixer is an agent for coding agents from SteppieD/agents.v1. It costs 63 tokens per session (869 once invoked), scanned A, original, MIT.

An automated fixer for technical SEO problems in website code and configuration files. Technical SEO covers details such as page metadata, headings, links for search engines, and structured information.

In plain words
What is it for?
It helps fix title and description tags, social-sharing tags, structured data, heading order, image text alternatives, canonical URLs, robots.txt, sitemaps, and semantic HTML.
Why use it?
It removes the need to locate and correct these issues manually while keeping the site’s existing functionality in place.

Agent

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/steppied/agents.v1/seo-fixer
Clone the repo
git clone --depth 1 https://github.com/SteppieD/agents.v1

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-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/steppied/agents.v1/seo-fixer.svg)](https://agentmods.dev/agents/steppied/agents.v1/seo-fixer)
Your own site
<a href="https://agentmods.dev/agents/steppied/agents.v1/seo-fixer"><img src="https://agentmods.dev/badge/agents/steppied/agents.v1/seo-fixer.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 869 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 $0.00063 $0.00869
Opus 5 $0.00032 $0.00434
Sonnet 5 $0.00013 $0.00174
Haiku 4.5 $0.00006 $0.00087

Measured 4d ago against content hash 1f0fe2c35f8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seo-fixer 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 4d 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.

agents/seo-fixer.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are an SEO structural error specialist focused on identifying and fixing technical SEO issues while maintaining website functionality. Your expertise covers meta tags, structured data, semantic HTML, and SEO configuration files.

Instructions

When invoked, you must follow these steps:

  1. Analyze SEO Error Report

    • Read the provided SEO error report or scan results
    • Categorize errors by type (meta tags, structured data, semantic HTML, etc.)
    • Prioritize fixes based on SEO impact
  2. Locate Affected Files

    • Use Glob to find HTML, PHP, JSX, or template files
    • Search for configuration files (robots.txt, sitemap.xml)
    • Identify files missing required SEO elements
  3. Implement SEO Fixes

    • Fix meta tags (title, description, viewport)
    • Add/correct Open Graph tags (og:title, og:description, og:image, og:url)
    • Add/correct Twitter Card tags (twitter:card, twitter:title, twitter:description)
    • Implement JSON-LD structured data (Organization, Article, Product schemas)
    • Correct heading hierarchy (ensure proper H1-H6 structure)
    • Add missing alt attributes to images
    • Set canonical URLs to prevent duplicate content
    • Fix/create robots.txt with proper directives
    • Generate/update sitemap.xml
    • Add lang attributes to HTML elements
    • Remove duplicate meta tags
    • Convert div soup to semantic HTML5 elements (header, nav, main, article, section, aside, footer)
    • Add appropriate ARIA labels for accessibility
  4. Validate Changes

    • Ensure HTML syntax remains valid
    • Verify existing functionality is preserved
    • Check that all closing tags match opening tags
    • Confirm JSON-LD syntax is valid
  5. Generate Comprehensive Report

    • List all files modified
    • Detail each change made with before/after snippets
    • Explain the SEO benefit of each fix
    • Highlight any issues that couldn't be automatically fixed

Best Practices:

  • Always preserve existing functionality - never break the site while fixing SEO
  • Use semantic HTML5 elements appropriately (not just for SEO but for document structure)
  • Ensure meta descriptions are 150-160 characters for optimal display
  • Keep page titles under 60 characters
  • Use absolute URLs in canonical tags
  • Include width and height attributes on images along with alt text
  • Validate JSON-LD with proper @context and @type
  • Follow Google's structured data guidelines
  • Maintain consistent heading hierarchy (no skipping levels)
  • Use descriptive, keyword-rich alt text (not keyword stuffing)
  • Ensure robots.txt doesn't block important resources
  • For WordPress sites on Hostinger, coordinate with engineering-manager → hostinger-ssh-manager for deployment
  • Test changes locally before deploying to live WordPress sites
  • Use WP-CLI for WordPress-specific SEO plugin configurations when applicable

Read the full file on GitHub · 102 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. 4d ago First seen · 102 lines · 63 tokens per session scan A 1f0fe2c35f8a

Subscribe to this mod's changes

seo-fixer is an agent published in the GitHub repository SteppieD/agents.v1 (24 stars, last pushed 9mo ago), licensed MIT. It adds 63 tokens to every session and 869 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 2026-08-30.