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 alebgl77/claude-inc --skill ai-seogit clone --depth 1 https://github.com/alebgl77/claude-incWrote 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/alebgl77/claude-inc/ai-seo)<a href="https://agentmods.dev/skills/alebgl77/claude-inc/ai-seo"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/ai-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/alebgl77/claude-inc/ai-seo"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/ai-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00114 | $0.00974 |
| Opus 5 | $0.00057 | $0.00487 |
| Sonnet 5 | $0.00023 | $0.00195 |
| Haiku 4.5 | $0.00011 | $0.00097 |
Grade A, and why
ai-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 9d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI SEO — Search Whisperer
"Rank in AI search"
When to use
- A page must rank in Google and get quoted by AI answers — "make this pillar page rank"
- Diagnosing invisibility — "why doesn't Perplexity ever cite our docs?"
- Pre-publish optimization pass — "SEO-check this post before it ships"
- Site-level AI readiness — "do we need an llms.txt? Set it up"
- Not for net-new persuasion copy — that's
copywriting
Workflow
- Pick the mode. Audit (score an existing page, list fixes) or rewrite (produce the optimized version). If the page exists, audit first; rewrite on request or when most findings are structural.
- Entity pass. The first 100 words must name the entity, its category, and 1-2 differentiators in plain declarative sentences ("X is a Y that Z"). AI systems quote pages that define themselves.
- Map real queries to H2s. Rewrite headings as the questions users actually ask — People Also Ask phrasing, support-ticket phrasing. One question, one H2.
- Write extractable answers. Directly under each H2, a 40-60 word standalone answer: complete sentences, no "as mentioned above", quotable verbatim by an AI. Depth and nuance follow after it.
- Emit schema. JSON-LD matching the page type — Article, FAQPage, Product, HowTo. Fill every required property; no empty fields, no invented ratings.
- Create or update llms.txt. Site purpose, key pages with one-line descriptions, canonical sources.
- Internal linking. 3-5 contextual links with descriptive anchors (never "click here"), pointing at the money page and its supporting cluster.
- E-E-A-T pass. Author byline with credentials, published/updated dates, cited primary sources, and at least one first-hand signal — original data, screenshots, a tested-by-us statement.
- Deliver the scorecard (audit) or the full rewrite plus schema and llms.txt snippet (rewrite).
Output format
MODE: <audit | rewrite>
PAGE: <path or URL>
TARGET QUERIES: <3-5 real queries this page should own>
SCORECARD (audit mode)
| Check | Status | Finding | Fix |
|---|---|---|---|
| Entity-rich intro | PASS/FAIL | ... | ... |
| Question-shaped H2s | ... | ... | ... |
| Extractable answers (40-60 w) | ... | ... | ... |
| Schema JSON-LD | ... | ... | ... |
| llms.txt | ... | ... | ... |
| Internal links | ... | ... | ... |
| E-E-A-T signals | ... | ... | ... |
REWRITE (rewrite mode)
<optimized page content>
SCHEMA
<script type="application/ld+json">{ ... }</script>
LLMS.TXT ENTRY
<lines to add>
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.
- 9d ago First seen · 75 lines · 114 tokens per session scan A 9087e3451006
ai-seo is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 974 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
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
box
Box manages cloud files, sharing, search, and metadata.
ima-skill
A unified IMA skill for managing personal notes and knowledge bases through the platform's APIs.
notes
A note-management skill for searching, reading, creating, and adding content to personal notes in IMA, a note and knowledge platform.
apple-notes
Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).
co-mail-and-drive
Read and send mail from the user's own Gmail or Outlook account, safely stage Gmail draft attachments, send from the agent's own address, manage Outlook contacts, and work with Google Drive files — with co gmail, co outlook, co email, and co gdrive. Use when the user asks about their inbox, an email or draft they want…