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 arturseo-geo/claude-code-skills --skill seo-geogit clone --depth 1 https://github.com/arturseo-geo/claude-code-skillsWrote 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/arturseo-geo/claude-code-skills/seo-geo)<a href="https://agentmods.dev/skills/arturseo-geo/claude-code-skills/seo-geo"><img src="https://agentmods.dev/badge/skills/arturseo-geo/claude-code-skills/seo-geo/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/arturseo-geo/claude-code-skills/seo-geo"><img src="https://agentmods.dev/badge/skills/arturseo-geo/claude-code-skills/seo-geo.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 | $0.00246 | $0.02913 |
| Opus 5.5 | $0.00098 | $0.01165 |
| Sonnet 5.5 | $0.00049 | $0.00583 |
| Haiku 4.5 | $0.00025 | $0.00291 |
Grade A, and why
seo-geo-skill 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 2mo 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference Files — Load When Relevant
| Topic | File | Load when... |
|---|---|---|
| Keyword research stack | references/keyword-research.md |
Finding keywords, clustering, search volume, intent |
| SERP analysis | references/serp-analysis.md |
Analysing SERPs, AI Overviews, content gaps, briefs |
| Technical audit | references/technical-audit.md |
Site audits, crawling, meta tags, schema, Core Web Vitals |
| Backlink intelligence | references/backlinks.md |
Backlink discovery, toxic scoring, competitor gaps, broken links |
| Infrastructure | references/infrastructure.md |
Building tools, proxies, caching, deployment, APIs |
| Failure registry | references/failures.md |
Debugging, known pitfalls, API failures, library bugs |
Project Context
If project-context.md exists in the skill directory or .claude/ folder, read it
before any task. It contains brand details, website URLs, API credentials paths,
infrastructure setup, and content defaults — avoids re-explaining context each session.
Workflow Overview
1. Keyword Research → Find opportunities, cluster by intent, assess difficulty
2. SERP Analysis → Analyse top results, track AI Overviews, generate content briefs
3. Technical Audit → Crawl site, check on-page SEO, validate schema, measure Core Web Vitals
4. Content Optimisation → Fill content gaps, optimise meta/headings/schema, improve AI extractability
5. Backlink Intelligence → Discover links, score quality, find toxic links, analyse competitor gaps
6. Monitoring → Track rankings, AI Overview rates, backlink changes, technical health
Step 1: Keyword Research
Free Stack (No Paid APIs Required)
| Source | What it gives you | Cost |
|---|---|---|
| Google Autocomplete | Real-time query suggestions | Free (use Webshare proxies) |
| YouTube Autocomplete | Video-intent keywords | Free |
| People Also Ask | Question-format keywords | Free (via Serper SERP data) |
| Related Searches | Semantic variations | Free (via Serper SERP data) |
| GSC API | Queries you already rank for | Free (service account) |
| Serper Autocomplete | Google Trends proxy | Free (2,500/month) |
| DataForSEO | Volume, CPC, competition | Optional ($1 free credit) |
What ships with it
16 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.
- .claude-plugin/plugin.json 1.3 KB
- .github/ISSUE_TEMPLATE/bug-report.md 712 B
- .github/ISSUE_TEMPLATE/platform-update.md 885 B
- .github/pull_request_template.md 981 B
- .gitignore 25 B
- CONTRIBUTING.md 3.0 KB
- LICENSE 1.0 KB
- project-context.md 2.2 KB
- README.md 5.9 KB
- references/backlinks.md 12 KB
- references/failures.md 7.3 KB
- references/infrastructure.md 8.6 KB
- references/keyword-research.md 8.3 KB
- references/serp-analysis.md 8.3 KB
- references/technical-audit.md 12 KB
- SECURITY.md 1.3 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.
- 2mo ago First seen · 313 lines · 246 tokens per session scan A a6d55f11e226
seo-geo-skill is a skill published in the GitHub repository arturseo-geo/claude-code-skills (13 stars, last pushed 7mo ago), licensed MIT. It adds 246 tokens to every session and 2,913 once invoked, about $0.0010 per session on Opus 5.5. 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.
seo-geo-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| seo-geo-skillarturseo-geo/claude-code-skills | Skill | 13 | 7mo ago | MIT | A | 246 | Claude Code |
| csharp-patternssoftspark/ai-toolkit | Skill | 179 | 3d ago | Apache-2.0 | A | 61 | Claude Code |
| seo-validatesoftspark/ai-toolkit | Skill | 179 | 3d ago | Apache-2.0 | A | 59 | Claude Code |
| database-patternssoftspark/ai-toolkit | Skill | 179 | 3d ago | Apache-2.0 | A | 55 | Claude Code |
| ruby-patternssoftspark/ai-toolkit | Skill | 179 | 3d ago | Apache-2.0 | A | 60 | Claude Code |
| debugsoftspark/ai-toolkit | Skill | 179 | 3d ago | Apache-2.0 | A | 34 | Claude Code |
| rag-patternssoftspark/ai-toolkit | Skill | 179 | 3d ago | Apache-2.0 | A | 57 | Claude Code |