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 PavloSEO/seohead-seotools --skill backlinks-checkgit clone --depth 1 https://github.com/PavloSEO/seohead-seotoolsWrote 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/pavloseo/seohead-seotools/backlinks-check)<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/backlinks-check"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/backlinks-check/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/pavloseo/seohead-seotools/backlinks-check"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/backlinks-check.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 | $0.00178 | $0.00869 |
| Opus 5 | $0.00089 | $0.00434 |
| Sonnet 5 | $0.00036 | $0.00174 |
| Haiku 4.5 | $0.00018 | $0.00087 |
Grade A, and why
backlinks-check 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 10d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlinks Check — are links from donor pages live and do they pass link equity?
The presence of an <a href> is not enough. A link does not pass link equity if it
uses rel=nofollow (or ugc/sponsored), if the donor page is blocked from indexing
with meta robots noindex, if it applies nofollow to all links at once, or if it
is canonicalized to another URL. The tool checks all of these conditions and groups
the results by cause.
Important scope boundary: this checks your list of donor pages (purchased links, crowd-marketing links, guest posts, directories); it does not investigate someone else's backlink profile. External databases (Ahrefs, Majestic, GSC) are not available here; a request to "show every link to the site" requires one of them.
The tool is seohead backlinks-check (CLI + MCP seo_backlinks_check + HTTP).
When to use it
- "check my backlinks," "are the links still live," "was the link removed";
- "dofollow or nofollow," "does it pass link equity";
- "does page X link to our site";
- regular monitoring of purchased backlinks.
Workflow
Target: a domain (any link to the domain or one of its subdomains will match):
seohead backlinks-check --target example.com --donors "https://donor1.example/post,https://donor2.example/page"
Target: an exact URL (the address must match exactly):
seohead backlinks-check --target https://example.com/landing --donors-file donors.txt
--donors-file is a file containing one URL per line, with # marking comments.
--concurrency N is the number of parallel requests (default: 3; maximum: 10).
The limit is 500 donor pages per run.
Response contents
summary:found(link exists),missing(link is absent),dofollow,nofollow,on_noindex_page(the donor page is blocked from indexing, so no equity is passed).results[]for each donor page:found,status_code,donor_indexable,canonical/canonical_elsewhere,links[](for every link found:href,anchor,rel,follow,blocked_by), andreason, which explains why the link is absent or why it does not work.
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.
- 10d ago First seen · 66 lines · 178 tokens per session scan A 6159aa1887ae
backlinks-check is a skill published in the GitHub repository PavloSEO/seohead-seotools (0 stars, last pushed 6d ago), licensed MIT. It adds 178 tokens to every session and 869 once invoked, about $0.0009 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.
content-scoring
Score content against the 10 GEO criteria with evidence and prioritized fixes. Use when users ask to score, rate, evaluate, or estimate ranking strength.
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.