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 georgekhananaev/claude-skills-vault --skill claude-seogit clone --depth 1 https://github.com/georgekhananaev/claude-skills-vaultWrote 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/georgekhananaev/claude-skills-vault/claude-seo)<a href="https://agentmods.dev/skills/georgekhananaev/claude-skills-vault/claude-seo"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/claude-seo/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/georgekhananaev/claude-skills-vault/claude-seo"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/claude-seo.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 | $0.00120 | $0.00883 |
| Opus 5 | $0.00060 | $0.00441 |
| Sonnet 5 | $0.00024 | $0.00177 |
| Haiku 4.5 | $0.00012 | $0.00088 |
Grade A, and why
claude-seo 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude SEO
Comprehensive SEO toolkit (upstream v2.0.0) with parallel sub-agent delegation for full-site audits. Sub-skills live in skills/<name>/SKILL.md; shared Python helpers in scripts/ (referenced by sub-skills as the plugin-root scripts dir — resolve them relative to THIS skill's root).
Sub-Skills
Core analysis
| Skill | Description |
|---|---|
| seo-audit | Full website SEO audit — crawls site, delegates to specialists in parallel |
| seo-page | Deep single-page analysis — titles, metas, headings, structured data |
| seo-technical | Crawlability, indexing, site speed, Core Web Vitals (incl. INP) |
| seo-content | Content optimization — keyword use, readability, E-E-A-T, internal links |
| seo-content-brief | Competitive content briefs w/ per-section word counts & competitor scoring |
| seo-schema | Schema.org markup generation & validation |
| seo-sitemap | XML sitemap generation & validation |
| seo-images | Image SEO — alt text, compression, lazy loading, WebP |
| seo-hreflang | International SEO — hreflang for multi-language sites |
| seo-competitor-pages | Competitor page analysis & gap identification |
| seo-programmatic | Programmatic SEO — template pages at scale |
| seo-plan | SEO strategy planning w/ business-type templates |
New in v2.0
| Skill | Description |
|---|---|
| seo-geo | GEO — visibility in AI Overviews, ChatGPT, Perplexity |
| seo-local | Local SEO — Google Business Profile, NAP, citations, reviews, local schema |
| seo-maps | Maps intelligence — geo-grid rank tracking, GBP API audit, review mining |
| seo-backlinks | Backlink profile — referring domains, anchors, toxic links, gaps (free APIs: Moz, CommonCrawl) |
| seo-cluster | SERP-overlap topic clustering for content architecture |
| seo-sxo | Search Experience Optimization — SERP-derived intent & page-type match |
| seo-drift | "Git for SEO" — baseline, diff & track SEO-critical element regressions |
| seo-google | Google APIs — Search Console, PageSpeed Insights v5, CrUX history, Indexing |
| seo-ecommerce | Shopping visibility, product schema, marketplace & pricing intel |
| seo-flow | FLOW framework — evidence-led Find → Leverage → Optimize → Win loop |
| seo-dataforseo | Live SERP/keyword/competitor data via DataForSEO MCP (needs account) |
| seo-image-gen | AI-generated SEO assets (OG images, heroes) — needs Gemini API key |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/agent_ux_check.py 7.9 KB runs code
- scripts/analyze_visual.py 6.9 KB runs code
- scripts/backlinks_auth.py 15 KB runs code
- scripts/bing_webmaster.py 14 KB runs code
- scripts/capture_screenshot.py 6.4 KB runs code
- scripts/commoncrawl_graph.py 16 KB runs code
- scripts/content_humanize.py 7.2 KB runs code
- scripts/content_quality.py 9.7 KB runs code
- scripts/content_verify.py 7.1 KB runs code
- scripts/crux_history.py 10 KB runs code
- scripts/dataforseo_costs.py 16 KB runs code
- scripts/dataforseo_merchant.py 17 KB runs code
- scripts/dataforseo_normalize.py 15 KB runs code
- scripts/domain_history.py 9.6 KB runs code
- scripts/drift_baseline.py 13 KB runs code
- scripts/drift_compare.py 20 KB runs code
- scripts/drift_history.py 3.4 KB runs code
- scripts/drift_report.py 11 KB runs code
- scripts/fetch_page.py 7.9 KB runs code
- scripts/ga4_report.py 17 KB runs code
- scripts/gbp_deprecation_lint.py 5.5 KB runs code
- scripts/google_auth.py 30 KB runs code
- scripts/google_report.py 88 KB runs code
- scripts/gsc_inspect.py 11 KB runs code
- scripts/gsc_query.py 13 KB runs code
- scripts/indexing_notify.py 9.8 KB runs code
- scripts/indexnow_submit.py 8.4 KB runs code
- scripts/iptc_ai_label.py 7.4 KB runs code
- scripts/keyword_planner.py 11 KB runs code
- scripts/lcp_subparts.py 7.1 KB runs code
- scripts/moz_api.py 14 KB runs code
- scripts/nlp_analyze.py 10 KB runs code
- scripts/pagespeed_check.py 23 KB runs code
- scripts/parasite_risk.py 8.7 KB runs code
- scripts/parse_html.py 8.4 KB runs code
- scripts/portability_check.py 7.8 KB runs code
- scripts/preload_check.py 8.1 KB runs code
- scripts/release_sign.py 5.6 KB runs code
- scripts/render_page.py 15 KB runs code
- scripts/schema_ecommerce_validate.py 11 KB runs code
- scripts/schema_generate.py 12 KB runs code
- scripts/seo_updates.py 4.8 KB runs code
- scripts/sync_flow.py 10 KB runs code
- scripts/ucp_check.py 8.4 KB runs code
- scripts/unlighthouse_run.py 5.5 KB runs code
- scripts/url_safety.py 20 KB runs code
- scripts/validate_backlink_report.py 12 KB runs code
- scripts/verify_backlinks.py 13 KB runs code
- scripts/verify_release.py 4.8 KB runs code
- scripts/youtube_search.py 12 KB runs code
- skills/seo-audit/SKILL.md 6.1 KB
- skills/seo-backlinks/SKILL.md 12 KB
- skills/seo-cluster/SKILL.md 13 KB
- skills/seo-competitor-pages/SKILL.md 7.5 KB
- skills/seo-content-brief/SKILL.md 10 KB
- skills/seo-content/SKILL.md 8.9 KB
- skills/seo-dataforseo/SKILL.md 17 KB
- skills/seo-drift/SKILL.md 6.8 KB
- skills/seo-ecommerce/SKILL.md 12 KB
- skills/seo-flow/SKILL.md 5.5 KB
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 · 53 lines · 120 tokens per session scan A 614326ce5b6a
claude-seo is a skill published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 883 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
woocommerce-health-check
Use when the user says 'why is my checkout broken', 'audit my woocommerce store', 'cart problems woocommerce', or 'losing sales woocommerce'. Diagnoses checkout and cart failures, AJAX mismatches, caching conflicts, payment gateway setup, and SSL enforcement.
mobile-experience-report
Use when the user says 'my site looks bad on mobile', 'check mobile layout', 'responsive audit', or 'site broken on phones'. Diagnoses breakpoint problems, text sizing, column stacking failures, hidden elements, and navigation menu behavior, device by device.
content-portability
Use when the user says 'export my site', 'backup my pages before editing', 'download my content locally', or 'migrate content to my other site'. Exports pages, posts, and custom posts to portable local packages with builder data, media, and markdown, then imports elsewhere with ID remapping.
migrate-divi-to-breakdance
Use when the user says 'migrate divi to breakdance', 'convert divi to breakdance', or 'rebuild divi pages in breakdance'. Parses Divi shortcodes, maps modules to Breakdance elements, and creates draft duplicates for review.
migrate-divi-to-bricks
Use when the user says 'migrate divi to bricks', 'convert divi to bricks', or 'rebuild divi pages in bricks'. Parses Divi shortcode content, maps modules to Bricks elements, and generates draft duplicates for review.
migrate-divi-to-gutenberg
Use when the user says 'migrate divi to gutenberg', 'convert divi to blocks', 'get off divi', or 'decommission divi'. Parses Divi shortcodes, maps modules to core blocks, and creates draft duplicates for review.