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.
npx skills add AutomateLab-tech/seo-performance-mcp --skill seo-performancegit clone --depth 1 https://github.com/AutomateLab-tech/seo-performance-mcpWrote 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.
[](https://agentmods.dev/skills/automatelab-tech/seo-performance-mcp/seo-performance)<a href="https://agentmods.dev/skills/automatelab-tech/seo-performance-mcp/seo-performance"><img src="https://agentmods.dev/badge/skills/automatelab-tech/seo-performance-mcp/seo-performance.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00117 | $0.00835 |
| Opus 5 | $0.00059 | $0.00417 |
| Sonnet 5 | $0.00023 | $0.00167 |
| Haiku 4.5 | $0.00012 | $0.00084 |
Grade A, and why
seo-performance 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seo-performance
Companion skill for the @automatelab/seo-performance-mcp server. It tells the model which MCP tool to call for which content-ops question.
When to use
Fire this skill whenever the user is making an editorial decision about an existing URL. Not for new-post writing - that's a different skill.
The mental model
Every URL on a content site is in one of six states:
| Verdict | Trigger |
|---|---|
refresh |
Decay > 30%/30d OR CTR << position-expected OR AI citations dropped |
expand |
Thin content + low dwell |
merge |
Cannibalisation with a sibling URL |
kill |
Stagnant, no clicks despite impressions |
double_down |
Rising clicks OR active AI citations |
hold |
Too young (<90d) OR healthy plateau |
The MCP server returns one of those verdicts deterministically. Your job in this skill is to route the question to the right tool.
Tool routing
| User asks | Call |
|---|---|
| "audit my blog" / "what should I refresh this week" | cohort_report with min_age_days=90, then posts_refresh_brief on every refresh/expand/merge row |
| "any quick title rewrites" / "low CTR pages" | gsc_quick_wins (window=90, positions 5-15) |
| "is this post dying" / "show me the data for X" | posts_snapshot + posts_decay_curve + posts_verdict on the URL |
| "give me a refresh brief for X" | posts_refresh_brief |
| "did we lose any AI citations" | posts_cite_loss per URL, or use the citation_loss_sweep prompt |
| "list my posts" | posts_list (sitemap-driven; no CMS plugin needed) |
Prompts available from the MCP server
These ship with the server and any MCP client can list them:
audit_cohort- the full weekly audit playbookfind_quick_wins- SERP quick-win sweep with rewrite suggestionscitation_loss_sweep- AI-citation recovery loop
Prefer invoking a prompt over re-deriving the workflow.
Output discipline
- When showing verdict output, always lead with the URL and verdict label, then reasons, then numbers. Reasons explain the verdict; numbers prove it.
- For refresh briefs, hand the markdown to the user verbatim - don't paraphrase.
- Never recommend an edit that wasn't grounded in a tool call this turn.
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.
- 8d ago First seen · 77 lines · 117 tokens per session scan A 457978a8c8ce
seo-performance is a skill published in the GitHub repository AutomateLab-tech/seo-performance-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 117 tokens to every session and 835 once invoked, about $0.0006 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.
Other skills, from other repositories
fire-your-seo-agency
A procedure for improving how a website appears in search engines and how AI answer systems find and cite it. It covers search, answer-engine, generative-AI, and Naver visibility.
geo-loop
Run one bounded eGEOagents loop iteration over a workspace domain - read the charter and fresh collector data, do ONE unit of work, write substrate artifacts, append one Timeline entry and one LOG line. Use for loop mode, /geo:loop, scheduled GEO runs, or continuous monitoring.
competitive-analysis
Analyze AI-search competitors for a query and recommend ranking strategy. Use when users ask competitor analysis, who ranks, or competitive landscape.
validation-doctor
Check Brave Search and Chrome DevTools MCP availability and provide exact setup snippets. Use when validation dependencies are missing or uncertain.
geo-content-research
Researches what prompts people ask AI engines (ChatGPT, Gemini, Perplexity, Claude) about a product category and produces a prompts.csv artifact — a prioritized, strictly-schema'd list of the queries where the brand should be cited. Feeds the monitor workflow.
create-geo-charts
Creates data visualizations (charts, graphs, tables) optimized for AI engine parsing and citation. Produces inline SVG/HTML with text summaries, data tables, and JSON-LD so AI engines can quote the data.