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 seovendorco/sv-mcp-skills --skill sv-seogptgit clone --depth 1 https://github.com/seovendorco/sv-mcp-skillsWrote 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/seovendorco/sv-mcp-skills/sv-seogpt)<a href="https://agentmods.dev/skills/seovendorco/sv-mcp-skills/sv-seogpt"><img src="https://agentmods.dev/badge/skills/seovendorco/sv-mcp-skills/sv-seogpt/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/seovendorco/sv-mcp-skills/sv-seogpt"><img src="https://agentmods.dev/badge/skills/seovendorco/sv-mcp-skills/sv-seogpt.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 | $0.00061 | $0.00622 |
| Opus 5.5 | $0.00024 | $0.00249 |
| Sonnet 5.5 | $0.00012 | $0.00124 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
sv-seogpt 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 today.
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.
What it actually says
SV SEO GPT: seogpt
MCP tool: seogpt · Mode: synchronous (returns the text directly)
API reference: SEO GPT
When to use this
Use for one specific, usually short piece of on-brand content: a meta title, a meta description, an FAQ answer, an ad headline, a social post. For a full article or blog post use sv-prose. To reshape text the user already has, use sv-content-transformer.
Parameters
| Parameter | Required | Notes |
|---|---|---|
keyword |
yes | 4 to 300 characters. |
type |
yes | Content type ID, 0 to 332. Examples: 0 = Title, 8 = Page Title, 18 = Meta Description, 26 = FAQ. |
web |
no | Website URL, max 300 characters. url is accepted as a fallback. |
brand |
no | Max 60 characters. |
brandpersona |
no | Max 2000 characters. |
length |
no | Length preset ID, 0 to 14. |
qty |
no | Number of variations, as an index: 0 = 1, 1 = 2, up to 9 = 10. |
language |
no | 0 to 39. 0 = US English. |
engine |
no | Writing engine ID, 0 to 18. |
The full ID lists are in the tool's own schema. Read them there instead of guessing.
Example call
{ "keyword": "white label seo", "type": 18, "web": "https://example.com", "brand": "Acme SEO" }
Result
The generated text, as plain text or HTML depending on the content type. With qty above 0 you get several variations.
Chaining
Usually the last step: sv-better-keywords → sv-topical-authority → sv-seogpt for the individual snippets in the plan.
Gotchas
- There are 333 type IDs and new ones can be added. Never hard-code a
typefrom memory. Look up the ID in the tool schema, and if the user's request does not clearly match one, ask which content type they want. qtyis zero-based.qty: 0returns one item, not zero.keywordmust be at least 4 characters.
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.
- today First seen · 50 lines · 61 tokens per session scan A 401e8be73913
sv-seogpt is a skill published in the GitHub repository seovendorco/sv-mcp-skills (2 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 622 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-16.
Other skills, from other repositories
linkedin-post
Draft a daily LinkedIn post for S M Moshiur Rahman about business development, grounded in a real problem he hit that day and real numbers from OmniRank. Use when he says "linkedin post", "today's post", "draft a post", or describes friction he wants written up.
audit
Use when asked to audit a site's SEO, check AEO or answer-engine readiness, diagnose why a page is not ranking or not being cited by AI, verify structured data, or run pre-deploy discoverability checks on built HTML.
geo-artifacts
Use when asked to generate or fix llms.txt, llms-full.txt or facts.json, make a site citable or ingestible by ChatGPT, Claude, Perplexity or Gemini, or publish machine-readable ground truth for AI crawlers.
extract-source-sample
Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…
create-video-seedance-2-fal
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills…
comprehensive-enrichment
Enrich any person or company from any identifier — email, name, LinkedIn URL, domain, company name, Twitter/X handle. Use when asked to enrich, look up, or research a lead, contact, person, or company.