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 | $0.00022 | $0.00351 |
| Sonnet 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 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 — 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.
- 12d 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 6mo ago), licensed MIT. It adds 43 tokens to every session and 703 once invoked, about $0.0002 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
wgm
Autonomous build skill that turns a rough request into working software through a relentless requirements interview (grill), a persistent plan, and a Ralph-style build loop (analyze → implement → validate → review → record). Use when the user runs /wgm, or asks to build, implement, prototype, or ship a feature or app…
rugged
Companion review skill that stress-tests a request, spec, plan, diff, or system against the operators and environment that will actually run it, not an idealized one. Runs a disciplined lifecycle (Triage -> Context -> Bottleneck decomposition -> Simplify -> Field test -> Verdict) and emits exactly one of three…
teach-me
Companion learning skill that makes a codebase legible fast. Surveys a repository, builds a cited map, runs a guided tour in dependency order, and finishes with a validated first change so the learner has actually moved the code. Use when the user runs /teach-me, or asks to learn, understand, onboard onto, get up to…
podlite-markup
Create and edit Podlite markup files. Use when working with .podlite files, or when the user mentions Podlite, formatting codes, declarative blocks, structured markup for documentation, or AI agent instructions.
podlite-verify
Validate, lint, and self-check Podlite markup. Use after generating or editing .podlite files, when asked to verify/validate/lint/check Podlite, or to catch structural errors (unbalanced =begin/=end, attribute syntax, nested angles, list nesting) before delivering output.
quiz-me
Companion assessment skill that grills a user on a codebase until their understanding is proven rather than assumed. Asks one question at a time, grades every answer against the real code with citations, scores 0-100 by difficulty tier, and drills the weak areas it finds. Use when the user runs /quiz-me, or asks to be…