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-geogit 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-geo)<a href="https://agentmods.dev/skills/freeautomation-tech/claude-seo-kit/seo-geo"><img src="https://agentmods.dev/badge/skills/freeautomation-tech/claude-seo-kit/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/freeautomation-tech/claude-seo-kit/seo-geo"><img src="https://agentmods.dev/badge/skills/freeautomation-tech/claude-seo-kit/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 | $0.00070 | $0.00483 |
| Opus 5 | $0.00035 | $0.00242 |
| Sonnet 5 | $0.00014 | $0.00097 |
| Haiku 4.5 | $0.00007 | $0.00048 |
Grade A, and why
seo-geo 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 10d 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
GEO / AI-Search Readiness
Evaluate how likely a page is to be cited by LLM answer engines, and give concrete fixes to improve LLM visibility.
Procedure
-
Fetch and parse the page, then run the GEO check:
python -m seo_kit.content.geo "<url>"or from Python:
from seo_kit.crawler.page_fetcher import fetch_page, parse_html from seo_kit.content.geo import run_geo_check _, html, _, _ = fetch_page("<url>") page = parse_html(html, "<url>") result = run_geo_check(page) print(result.to_dict()) -
Report the score and findings, then recommend improvements:
- Question framing — add Q&A sections phrased as natural queries.
- Verifiable claims — attribute statistics and cite sources.
- Data density — use specific numbers, percentages, and dates.
- Entity signals — author bylines, publish dates, schema markup.
- Depth — expand past the LLM citation floor (~600+ words).
-
Offer to draft the rewrite (e.g., add an FAQ block, rewrite the intro as a direct answer, or insert sourced statistics).
Notes
- Scores 0-100 with findings per signal.
- 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.
- 10d ago First seen · 56 lines · 70 tokens per session scan A da0431af1491
seo-geo is a skill published in the GitHub repository FreeAutomation-Tech/claude-seo-kit (0 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 483 once invoked, about $0.0003 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
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.
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.
temporal-query
Answer time-travel questions over stored memory — what was believed at a past point in time, when a belief changed, and what replaced it. Use when the user says "as of", "back in", "at the time", "history of", "timeline", "what did I think then", or asks why a current memory contradicts an older one.
memory-commit
Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.