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 indranilbanerjee/digital-marketing-pro --skill hreflang-checkgit clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-proWrote 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/indranilbanerjee/digital-marketing-pro/hreflang-check)<a href="https://agentmods.dev/skills/indranilbanerjee/digital-marketing-pro/hreflang-check"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/digital-marketing-pro/hreflang-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/indranilbanerjee/digital-marketing-pro/hreflang-check"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/digital-marketing-pro/hreflang-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 | $0.00155 | $0.02718 |
| Opus 5 | $0.00077 | $0.01359 |
| Sonnet 5 | $0.00031 | $0.00544 |
| Haiku 4.5 | $0.00015 | $0.00272 |
Grade A, and why
hreflang-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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digital-marketing-pro:hreflang-check
Purpose
Audit hreflang tag implementation for multilingual and multi-regional SEO. Hreflang annotations tell search engines which language and regional version of a page to serve to which audience — when implemented incorrectly, the wrong language version appears in search results, pages compete against each other for the same queries, and international organic traffic is lost to mis-served content. This command performs a thorough technical audit of hreflang implementation, checking that all language versions are properly cross-referenced with correct annotations, that every page references itself, that references are bidirectional (if page A points to page B, page B points back to page A), that language-region codes are valid, that x-default fallback is configured, and that no orphaned references point to non-existent pages.
Critical for any brand operating multilingual or multi-regional websites. Hreflang errors are among the most common international SEO issues — they are invisible to users, rarely caught in manual QA, and silently degrade search performance across every affected market. Even a single missing bidirectional reference can prevent search engines from correctly associating language versions, causing the wrong page to rank or duplicate content signals to suppress both versions. This command surfaces every implementation error with specific fix instructions and corrected code snippets.
Input Required
The user must provide (or will be prompted for):
- Website URL or sitemap URL: The starting point for the audit. Can be a single page URL (audits hreflang on that page and its referenced alternates), a sitemap URL (audits all pages listed in the sitemap), or a list of specific page URLs to check. Note: the plugin does not crawl websites directly — if a URL is provided, the user will be guided to provide the HTML source or hreflang data for analysis. Alternatively, the user can paste HTML source, hreflang tag sets, or exported hreflang data directly
- Specific page URLs to check (optional): A subset of pages to focus the audit on — useful for auditing a specific section (e.g., all product pages, all blog posts) rather than the entire site. If omitted, all pages with hreflang annotations in the provided data are audited
- Expected language-region codes (optional): The set of language-region codes that should appear in hreflang annotations (e.g., en-US, de-DE, fr-FR, es-ES, ja-JP). Defaults to the brand's configured languages from the language configuration in profile.json. Used to flag missing language versions — if the brand targets de-DE but no hreflang for de-DE exists on a page, that is flagged as a gap
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.
- 5d ago First seen · 54 lines · 155 tokens per session scan A 5994d88a46a0
hreflang-check is a skill published in the GitHub repository indranilbanerjee/digital-marketing-pro (812 stars, last pushed 5d ago), licensed MIT. It adds 155 tokens to every session and 2,718 once invoked, about $0.0008 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 2026-09-07.
Other skills, from other repositories
cf-translate
Translate publication-ready ContentForge content into any of 15 languages at three localization levels (literal, adapted, transcreated) — preserving brand voice, keeping citation URLs and DOIs untouched, and adapting SEO keyword placements for the target market — delivered as a translated .docx plus a quality report…
localization-pass
7-dimension locale adaptation (currency / units / spelling-dialect / idioms / regulations / tone / date-format) + multilingual audit (translation coverage matrix / hreflang validation / SEO parity / freshness check). Triggered when state.brief.targetmarketlocale != en-US, or via /locale-audit on existing multilingual…
cf-brief
Generate a research-backed content brief from a keyword or topic — keyword data with volume and difficulty, top-5 competitor and E-E-A-T analysis, search-intent classification, audience pain points, a section-by-section outline with word counts and citation targets, plus SEO and AEO/GEO strategy (AI Overview status…
cf-style-guide
Import a brand voice profile from an existing style guide — a .docx/.pdf document, a URL, or manual input — extracting tone, formality, personality, approved/banned terminology, compliance guardrails, and author profiles into a structured brand-profile JSON at /.claude-marketing/{brand-slug}/Brand-Guidelines/, then…
marketing-expert
Build comprehensive marketing technology solutions including automation workflows, campaign management, analytics tracking, and multi-channel orchestration. Use when the user mentions marketing automation, campaign management, SEO, email or content marketing, attribution, or multi-channel orchestration.
cf-publish
Execute CMS publishing: push a finished, reviewed piece (Phase 8 complete, quality score >=7.0) to Webflow or WordPress via MCP connectors as draft, scheduled, or live — always showing a full publish preview and waiting for your explicit yes/no/edit confirmation before anything is pushed. Runs the EU AI Act Article 50…