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 lionkiii/claude-seo-skills --skill seo-ahrefs-new-linksgit clone --depth 1 https://github.com/lionkiii/claude-seo-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/lionkiii/claude-seo-skills/seo-ahrefs-new-links)<a href="https://agentmods.dev/skills/lionkiii/claude-seo-skills/seo-ahrefs-new-links"><img src="https://agentmods.dev/badge/skills/lionkiii/claude-seo-skills/seo-ahrefs-new-links/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/lionkiii/claude-seo-skills/seo-ahrefs-new-links"><img src="https://agentmods.dev/badge/skills/lionkiii/claude-seo-skills/seo-ahrefs-new-links.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 | $0.00063 | $0.01002 |
| Opus 5 | $0.00032 | $0.00501 |
| Sonnet 5 | $0.00013 | $0.00200 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade C, and why
seo-ahrefs-new-links scanned grade C with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Verify with: cat ~/.claude/mcp.json | grep -i ahrefs Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- Verify with: cat ~/.claude/mcp.json | grep -i ahrefs How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ahrefs New and Lost Links
Fetches referring domain history from Ahrefs, filtered to show recently acquired domains (last 30 days) and any lost referring domains.
References
@skills/seo/references/mcp-degradation.md @skills/seo/references/ahrefs-api-reference.md
Inputs
domain: The bare domain to analyze (e.g.,example.com). Striphttps://,http://, and trailing slashes before passing to Ahrefs tools.
MCP Check
Before proceeding, verify Ahrefs MCP is available:
- Use ToolSearch with query
+ahrefs - If tools are returned → Ahrefs MCP is available, proceed to Execution
- If no tools returned → display the Ahrefs MCP error template from
references/mcp-degradation.mdand stop
Execution
Step 1 — Call Referring Domains
Call mcp__claude_ai_ahrefs__site-explorer-referring-domains with:
target: the bare domain (e.g.,example.com)
Returns per referring domain: domain, domain_rating, backlinks count,
first_seen date (ISO 8601), and optionally lost_date for domains no longer linking.
Step 2 — Filter by Date (Client-Side)
The tool may not support native date filtering. If no native date filter exists:
- Compute the cutoff date: current date minus 30 days
- Filter entries where
first_seen >= cutoff_date→ these are new referring domains - Separate entries where
lost_dateis present → these are lost referring domains
Step 3 — Sort and Summarize
- New referring domains: sort by
domain_ratingdescending (highest DR new links first) - Lost referring domains: sort by
domain_ratingdescending (highest DR losses first) - Calculate net change: new count minus lost count
Output Format
## Ahrefs New & Lost Links: example.com (Last 30 Days)
### Net Change Summary
| Metric | Value |
|--------|-------|
| New Referring Domains | +12 |
| Lost Referring Domains | -3 |
| Net Change | +9 |
### New Referring Domains (Last 30 Days)
| Domain | DR | Backlinks from Domain | First Seen |
|--------|----|-----------------------|------------|
| highdr-news.com | 71 | 1 | 2026-02-18 |
| industry-blog.io | 58 | 3 | 2026-02-10 |
| partner-site.com | 44 | 2 | 2026-02-05 |
### Lost Referring Domains
| Domain | DR | Lost Date |
|--------|----|-----------|
| old-partner.com | 52 | 2026-01-28 |
### Observations
- Gained 12 new referring domains this month — healthy link velocity
- Lost 3 domains — investigate whether content was removed or sites changed focus
- Highest-DR gain: highdr-news.com (DR 71) — strong editorial link
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 · 127 lines · 63 tokens per session scan C 2484cba8a491
seo-ahrefs-new-links is a skill published in the GitHub repository lionkiii/claude-seo-skills (20 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 1,002 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
seo-images
Image SEO audit for a URL or domain. Pulls raw image inventory via Firecrawl, then audits alt-text quality, modern-format coverage (WebP / AVIF), responsive sizing (srcset / sizes), lazy-loading and LCP signals (loading, fetchpriority, decoding), CLS-safe dimensions, descriptive file names, and ImageObject JSON-LD.…
seo-technical-audit
Focused one-shot technical SEO audit for a domain. Crawlability, indexability, security, mobile, structured data, JS rendering — single-pass deliverable, not a diff. Distinct from seo-drift (which tracks changes over time) and from seo-page (which audits keywords/traffic for one URL, not technical health). Use when…
seo-api
DataForSEO API integration architect for developers. Covers the entire DataForSEO surface — DataForSEO Labs (ranked keywords, keyword ideas/suggestions/related, domain rank overview, competitors, domain/page intersection, subdomains, relevant pages, bulk keyword difficulty, bulk traffic estimation, search intent…
seo-ads
Paid-search competitive landscape for a domain or keyword. Reconstructs the paid footprint keyword-by-keyword from live SERP ad blocks — advertisers, ad copy patterns, who else bids on the same keywords, CPC/competition signals, SERP shopping/ad-pack visibility — and produces a competitive ads brief plus a recommended…
seo-backlinks-profile
Full backlink profile for a domain — referring domains, anchor text distribution, authority distribution, IP and subnet diversity, growth/decay trend, toxic-candidate flagging. Distinct from seo-backlink-gap (which is gap-vs-competitor only). Produces a profile health score and reviewable disavow candidate list (never…
seo-content-audit
E-E-A-T + CITE quality audit for an EXISTING piece of content. Scores Experience, Expertise, Authoritativeness, Trustworthiness, and citation-readiness for AI search; surfaces veto items that block publication; produces a publish / publish-with-fixes / no-publish verdict. Distinct from seo-content-brief (produces a…