MCPGateway: Skill for Claude Code

.agents/skills/seo-recovery/SKILL.md

seo-recovery is a skill for Claude Code from abdullah1854/MCPGateway. It costs 98 tokens per session (5,871 once invoked), scanned A, original, MIT.

An SEO recovery guide investigates why pages receive less traffic from search engines such as Google. It covers indexing, canonical URLs, language tags, sitemaps, robots.txt, and Search Console, Google's site-monitoring service.

In plain words
What is it for?
Use it to investigate traffic drops, pages missing from search, incorrect canonical URLs, language-tag errors, sitemap problems, crawl errors, and robots.txt or noindex issues.
Why use it?
It replaces guesses about search visibility with checks of actual search data and page source, helping identify technical causes of lost traffic.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is abdullah1854/MCPGateway's own configuration. It tells Claude Code how to work on MCPGateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MCPGateway configures →

Reuse

Borrowing it

Nothing to install: this file belongs to abdullah1854/MCPGateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/abdullah1854/MCPGateway/main/.agents/skills/seo-recovery/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/abdullah1854/MCPGateway

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-recovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/abdullah1854/mcpgateway/seo-recovery/github.svg)](https://agentmods.dev/skills/abdullah1854/mcpgateway/seo-recovery)
Your own site
<a href="https://agentmods.dev/skills/abdullah1854/mcpgateway/seo-recovery"><img src="https://agentmods.dev/badge/skills/abdullah1854/mcpgateway/seo-recovery/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 seo-recovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/abdullah1854/mcpgateway/seo-recovery"><img src="https://agentmods.dev/badge/skills/abdullah1854/mcpgateway/seo-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,871 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00098 $0.05871
Opus 5 $0.00049 $0.02936
Sonnet 5 $0.00020 $0.01174
Haiku 4.5 $0.00010 $0.00587

Measured 11d ago against content hash c33e47a19e36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

seo-recovery 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 11d 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.

| **VERIFY CANONICAL TAGS IN SOURCE** | Always `curl` or read the actual HTML source. Do NOT trust CMS admin panels or visual page checks -- the rendered HTML is ground truth |
.agents/skills/seo-recovery/SKILL.md · 574 lines

How it starts

The opening of the file, as written. The whole thing — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SEO Recovery Protocol

When This Skill Activates

  • "SEO traffic dropped", "organic traffic down", "lost rankings"
  • "Indexing issues", "pages not indexed", "deindexed"
  • "Canonical URL", "canonical mismatch", "wrong canonical"
  • "Hreflang", "hreflang errors", "language tags"
  • "Sitemap", "sitemap errors", "toxic sitemap", "missing sitemap"
  • "Search Console", "GSC", "crawl errors", "coverage issues"
  • "Robots.txt", "noindex", "blocked by robots"
  • "Google not showing my pages"

Anti-Hallucination Rules (NEVER violate)

Rule Description
NEVER ASSUME INDEXING STATUS Always verify via GSC URL Inspection or site: search. Never say "this page is indexed" without checking
GSC DATA BEFORE CONCLUSIONS Pull actual Search Analytics data before diagnosing. Traffic estimates, guesses, or assumptions are forbidden
VERIFY CANONICAL TAGS IN SOURCE Always curl or read the actual HTML source. Do NOT trust CMS admin panels or visual page checks -- the rendered HTML is ground truth
CHECK BOTH HTTP AND HTTPS Canonical mismatches often involve protocol differences. Always check both variants
DISTINGUISH CRAWLED VS INDEXED A page being crawled does NOT mean it is indexed. These are separate states in GSC Coverage
HOSTINGER CDN DISTRUST After deploying SEO fixes to Hostinger, verify at server level via curl. CDN may serve stale content for 5-15 minutes
NO BULK CHANGES WITHOUT BACKUP Before modifying sitemaps, robots.txt, or canonical tags at scale, document the current state
TIMESTAMP YOUR EVIDENCE GSC data has processing delays (24-72h). Always note when data was pulled vs when changes were made

Phase 0: Confirm Scope (MANDATORY - Do This First)

Before any investigation:

1. What is the domain? (exact URL, including protocol and www vs non-www)
2. When did the traffic drop start? (exact date or date range)
3. How severe is the drop? (percentage, from X to Y)
4. Is it site-wide or specific pages/sections?
5. Were any changes deployed around that time? (redesign, migration, CMS update, hosting change)
6. Which GSC property are we using? (domain property vs URL prefix?)
7. What is the hosting platform? (Hostinger? Other? -- affects deployment workflow)

Read the full file on GitHub · 574 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. 11d ago First seen · 574 lines · 98 tokens per session scan A c33e47a19e36

Subscribe to this mod's changes

seo-recovery is a skill published in the GitHub repository abdullah1854/MCPGateway (15 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 5,871 once invoked, about $0.0005 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 2026-08-30.