Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/thisisAhsanIqbal/nextjs-seo-auditnpx agentmods add skills/thisisahsaniqbal/nextjs-seo-audit/backlink-monitoringWrote 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/thisisahsaniqbal/nextjs-seo-audit/backlink-monitoring)<a href="https://agentmods.dev/skills/thisisahsaniqbal/nextjs-seo-audit/backlink-monitoring"><img src="https://agentmods.dev/badge/skills/thisisahsaniqbal/nextjs-seo-audit/backlink-monitoring/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/thisisahsaniqbal/nextjs-seo-audit/backlink-monitoring"><img src="https://agentmods.dev/badge/skills/thisisahsaniqbal/nextjs-seo-audit/backlink-monitoring.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 | $0.00043 | $0.00703 |
| Opus 5.5 | $0.00017 | $0.00281 |
| Sonnet 5.5 | $0.00009 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
backlink-monitoring 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 2mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlink Monitoring
Analyse outbound links on the page for SEO link strategy.
Note: This skill owns external/outbound link analysis. For internal link counts and structure, see the onpage-optimization skill.
1. Identify external links
For each <a href="..."> element:
- External:
hrefstarts withhttp://orhttps:// - Classify as dofollow (default) or nofollow (if
relcontainsnofollow)
Report: ✅ PASS "Found N external link(s): X dofollow, Y nofollow"
2. Nofollow strategy
| Condition | Status |
|---|---|
| All external links are dofollow, none nofollow | ⚠️ WARN "Consider adding rel=nofollow to untrusted or sponsored links" |
| Mix of dofollow and nofollow | ✅ PASS (healthy strategy) |
3. Sponsored and UGC attributes
- Links with
rel="sponsored"→ ✅ PASS "N link(s) properly marked as sponsored" - Links with
rel="ugc"→ ✅ PASS "N link(s) marked as UGC (user-generated content)"
4. Anchor text quality
- External links with empty anchor text (and no child
<img>) → ⚠️ WARN "Descriptive anchor text improves SEO"
5. Domain diversity
- Extract unique hostnames from all external link
hrefvalues - Report: ✅ PASS "Links point to N unique domain(s): [list domains]"
6. No external links
- If zero external links found → ⚠️ WARN "Linking to authoritative sources can boost SEO credibility"
Best practices to suggest
- Use
rel="nofollow"for untrusted, paid, or user-submitted links - Use
rel="sponsored"for paid/advertising links - Use
rel="ugc"for user-generated content (comments, forums) - Write descriptive anchor text — avoid "click here" or empty links
- Link to authoritative, relevant external sources
- Maintain domain diversity — don't link excessively to one domain
Edge cases
- Ignore
javascript:,mailto:, andtel:hrefs — these are not external links - Links with multiple
relvalues (e.g.rel="nofollow sponsored") — check each value separately - Links inside
<template>,<noscript>, or hidden elements should still be audited but noted as potentially inactive - Social media share buttons (Twitter, Facebook intents) are external but should not trigger nofollow warnings
- CDN links (e.g.
cdn.jsdelivr.net,fonts.googleapis.com) are resource links, not editorial — exclude from domain diversity count
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.
- 2mo ago First seen · 69 lines · 43 tokens per session scan A 736bd8e3433d
backlink-monitoring is a skill published in the GitHub repository thisisAhsanIqbal/nextjs-seo-audit (7 stars, last pushed 8mo ago), licensed MIT. It adds 43 tokens to every session and 703 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 2026-08-31.
backlink-monitoring compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| backlink-monitoringthisisAhsanIqbal/nextjs-seo-audit | Skill | 7 | 8mo ago | MIT | A | 43 | Claude Code, Codex |
| podlite-markuppodlite/podlite-skills | Skill | 3 | 13d ago | MIT | A | 47 | Claude Code |
| podlite-verifypodlite/podlite-skills | Skill | 3 | 13d ago | MIT | A | 64 | Claude Code |
| wgmagent-frontier/wgm | Skill | 3 | 3d ago | MIT | A | 155 | Claude Code, Codex |
| ruggedagent-frontier/wgm | Skill | 3 | 3d ago | MIT | A | 182 | Claude Code, Codex |
| teach-meagent-frontier/wgm | Skill | 3 | 3d ago | MIT | A | 149 | Claude Code, Codex |
| quiz-meagent-frontier/wgm | Skill | 3 | 3d ago | MIT | B | 151 | Claude Code, Codex |