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 FreeAutomation-Tech/claude-seo-kit --skill seo-hreflanggit clone --depth 1 https://github.com/FreeAutomation-Tech/claude-seo-kitWrote 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/freeautomation-tech/claude-seo-kit/seo-hreflang)<a href="https://agentmods.dev/skills/freeautomation-tech/claude-seo-kit/seo-hreflang"><img src="https://agentmods.dev/badge/skills/freeautomation-tech/claude-seo-kit/seo-hreflang/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/freeautomation-tech/claude-seo-kit/seo-hreflang"><img src="https://agentmods.dev/badge/skills/freeautomation-tech/claude-seo-kit/seo-hreflang.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 | $0.00045 | $0.00473 |
| Opus 5 | $0.00023 | $0.00236 |
| Sonnet 5 | $0.00009 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
seo-hreflang 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 11d 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.
What it actually says
Hreflang / International SEO
Validate the hreflang alternate-link signals on a page.
Procedure
-
Fetch and parse the page, then run the hreflang check:
python -m seo_kit.technical.hreflang "<url>"or from Python:
from seo_kit.crawler.page_fetcher import fetch_page, parse_html from seo_kit.technical.hreflang import run_hreflang_check _, html, _, _ = fetch_page("<url>") page = parse_html(html, "<url>") result = run_hreflang_check(page) print(result.to_dict()) -
Report:
- Whether any hreflang/alternate links exist at all
- Malformed or duplicate language-region codes
- Whether
x-defaultis declared - A score (0-100) with findings
-
Recommend fixes:
- No hreflang on a multi-language site → add
<link rel="alternate">per locale. - Missing
x-default→ addhreflang="x-default"for the primary version. - Invalid codes → correct to ISO 639-1 (
en,en-gb,de,fr-ca, ...).
- No hreflang on a multi-language site → add
Notes
- Detected via
<link rel="alternate" hreflang="...">in the page<head>. - Inspired by AgriciDaniel/claude-seo and seranking/seo-skills (both MIT).
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.
- 11d ago First seen · 55 lines · 45 tokens per session scan A 3806d6f1828f
seo-hreflang is a skill published in the GitHub repository FreeAutomation-Tech/claude-seo-kit (0 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 473 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
gr-blog-post
A Jekyll blog publishing workflow. Jekyll is a tool that turns text and templates into a website, and this workflow also prepares matching English, Japanese, and Korean posts.
gr-oss-marketing
A launch and growth plan for open-source software projects. It covers preparing a project, announcing it through developer communities, and publishing content in several languages.
sfcc-localization
Skill "sfcc-localization" from taurgis/sfcc-dev-mcp, covering localization skill, quick checklist, locale basics, core principles and minimal examples.
scrape-batch
Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
research-topic
Multi-step research orchestration. Use when user asks "research X", "summarize current state of Y", "what's the latest on Z", or compares approaches. Calls extract(action="agent") which searches the web, extracts top results, then synthesises a citation-preserving Markdown answer with one configured LLM.