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 alpha-ai-labs/seoproai-mcp --skill seoproai-operatorgit clone --depth 1 https://github.com/alpha-ai-labs/seoproai-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/alpha-ai-labs/seoproai-mcp/seoproai-operator)<a href="https://agentmods.dev/skills/alpha-ai-labs/seoproai-mcp/seoproai-operator"><img src="https://agentmods.dev/badge/skills/alpha-ai-labs/seoproai-mcp/seoproai-operator/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.
<a href="https://agentmods.dev/skills/alpha-ai-labs/seoproai-mcp/seoproai-operator"><img src="https://agentmods.dev/badge/skills/alpha-ai-labs/seoproai-mcp/seoproai-operator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.01055 |
| Opus 5 | $0.00031 | $0.00528 |
| Sonnet 5 | $0.00012 | $0.00211 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
seoproai-operator 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 12d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEOPro AI Operator
Use this skill when someone wants to inspect website SEO performance, plan or generate content, review drafts, publish approved content, request indexing, or report outcomes through the configured SEOPro AI MCP server. It works for a founder managing one website, a small team, an in-house marketer, a consultant, or an agency managing multiple clients.
This skill does not contain or proxy the hosted server implementation. It never asks the user to paste a credential into chat. The plugin's root mcp.json declares the connection to:
https://api.seoproai.co/api/mcp
Agent Plugins 1.0.0 leaves authentication to the client. Complete OAuth through the client or configure a scoped API key in the client's secret store; never add credentials to this skill or mcp.json.
Operating rules
- Call
list_websitesbefore using a website-scoped tool. Match the requested website or client by URL/name; never guess a numeric ID. - Default to read-only analysis. State clearly when a requested next step changes SEOPro AI state or affects an external CMS/search engine.
- Never send tool arguments, credentials, customer content, returned search data, or raw output to another analytics or external service.
- Treat generated recommendations as proposals. Separate observed data from inference and never guarantee rankings, traffic, citations, or revenue.
- Keep list queries bounded and date ranges explicit. Use the last 28 or 30 days when the user does not specify a reporting period.
- Article generation is asynchronous. Poll
get_article_statusno more often than every 30–60 seconds and do not start duplicates. - Never publish or request indexing in the same step as analysis or generation.
Mandatory approval gates
CMS publishing
Before calling publish_article:
- Retrieve the article metadata (and content when review is requested).
- Show the user the title, target website, current status, and whether the CMS result will be a draft or live page.
- Ask for explicit approval for that article and destination.
- Only after approval, call the tool with
confirm_publish=true.
What ships with it
1 file 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.
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.
- 12d ago First seen · 99 lines · 62 tokens per session scan A be3f27a5a807
seoproai-operator is a skill published in the GitHub repository alpha-ai-labs/seoproai-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,055 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 2026-08-31.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
grounded-citations
Ground answers and documents in cited, verifiable sources.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
flash-attention
Speed up long-sequence transformer training and inference.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).