Borrowing it
Nothing to install: this file belongs to prashishh/seo-geo-report-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/prashishh/seo-geo-report-engine/main/.agents/skills/hreflang-i18n/SKILL.mdgit clone --depth 1 https://github.com/prashishh/seo-geo-report-engineWrote 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/prashishh/seo-geo-report-engine/hreflang-i18n)<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/hreflang-i18n"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/hreflang-i18n/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/prashishh/seo-geo-report-engine/hreflang-i18n"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/hreflang-i18n.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 | $0.00193 | $0.01804 |
| Opus 5 | $0.00097 | $0.00902 |
| Sonnet 5 | $0.00039 | $0.00361 |
| Haiku 4.5 | $0.00019 | $0.00180 |
Grade A, and why
hreflang-i18n 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hreflang-i18n
Full-mesh hreflang validation and generation for multilingual / multi-region sites. The hard part
is the mesh: hreflang only works if every locale variant points at every other variant and
each gets a matching return tag back. One missing return tag silently voids the whole cluster, and
Google falls back to ranking the wrong language. This skill finds those breaks and emits a correct
mesh. Prefer Ahrefs MCP (see knowledge/ahrefs-mcp-map.md); call doc before first use of a tool.
Methodology in playbooks/i18n-seo.md.
Example use case: a client targeting en + ne (+ hi) across diaspora corridors
has zero i18n coverage — run AUDIT first to baseline, then GENERATE the mesh.
Methodology (PERCEIVE → ANALYZE → VALIDATE → ACT)
PERCEIVE — gather. Resolve the project (./bin/mkt config show --project <client>). Read
client.yml for languages / markets / domain and the target URL set (the page and its
locale variants). Decide the URL-structure pattern in use — ccTLD, subfolder (/ne/), or subdomain
(ne.) — because the mesh and x-default rules differ per pattern.
- Crawl the page set:
site-explorer-crawled-pagesorsite-audit-page-content/site-audit-page-explorerto pull each page's existing<link rel="alternate" hreflang>set, canonical, and HTTP headers. If a URL isn't in an Ahrefs project, fall back toWebFetchto read the live<head>andLink:headers directly. Note which implementation method is in use.
ANALYZE — run the 8 checks across the full cluster (record pass/fail + offending URL per check):
- Self-reference present — every page lists its own URL with its own hreflang. Missing → cluster may be ignored.
- Bidirectional return tags — if A→B, then B→A must exist (full mesh). Build the adjacency matrix; any asymmetric pair is invalid and Google drops it.
- x-default present — a
hreflang="x-default"entry exists for unmatched users / locale selector; flag if absent on a site that needs one. - ISO format valid — language is ISO 639-1 (
en,ne,hi), optional region is ISO 3166-1 alpha-2 (en-GB,ne-NP). Rejecten-UK,en_us, made-up codes, region-only without language. - Canonical-hreflang alignment — each page's
rel=canonicalis self-referential and matches the hreflang-listed URL exactly; a canonical pointing at another locale silently cancels hreflang. - Protocol/host consistency — all hreflang URLs use one protocol + host form (https, no www/non-www or trailing-slash drift); inconsistency fragments the mesh.
- Cross-domain correctness — for ccTLD/subdomain setups, return tags resolve across domains and each is reachable (200, not redirected/blocked).
- Locale-content parity — the variant is genuinely translated (not the source language with a
swapped URL), and is indexable (no
noindex, not redirected). Sample bodies via the crawl/WebFetch.
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 · 101 lines · 193 tokens per session scan A 3bc48b3e2e8c
hreflang-i18n is a skill published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 193 tokens to every session and 1,804 once invoked, about $0.0010 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
content-amplifier
Use when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification…
email-sequence-designer
Use when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", or "plan a cold-outbound sequence"; produces general lifecycle automation flows (welcome, cart, browse-abandon, post-purchase, in-flow re-engagement, B2B cold outbound)…
reactivation-specialist
Use when the user asks to "build a win-back campaign", "re-engage lapsed subscribers", "run a re-permission / re-consent sweep", or "sunset my dead list"; produces a closed-loop reactivation program — a lapsed-cohort definition, a staged offer ladder, a re-consent (re-permission) capture step, and a sunset-confirm /…
campaign-planner
Use when the user asks to "plan an influencer campaign", "build a campaign blueprint", "track or close a creator campaign", or "record a late campaign correction"; produces the plan and, when requested, a non-canonical evidence tracker with scoped identity, publication, reconciliation, close, and reopen receipts. Not…
product-feed-optimizer
Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax asset groups"; audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price…
attribution-reconciler
Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly) reconciliation workbook that de-dups stacked credit against an order-ID truth set, normalizes attribution windows and currency, compares attribution…