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 S3YED/appie-kit --skill ai-search-optimizationgit clone --depth 1 https://github.com/S3YED/appie-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/s3yed/appie-kit/ai-search-optimization)<a href="https://agentmods.dev/skills/s3yed/appie-kit/ai-search-optimization"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/ai-search-optimization.svg" alt="Measured on agentmods" 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 | $0.00119 | $0.01265 |
| Opus 5 | $0.00060 | $0.00633 |
| Sonnet 5 | $0.00024 | $0.00253 |
| Haiku 4.5 | $0.00012 | $0.00127 |
Grade A, and why
ai-search-optimization scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sI https://example.com/page | grep -i 'x-robots-tag' # nosnippet/noindex? How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Search Optimization (AEO / GEO)
Google's AI features (AI Overviews, AI Mode) use the same crawl, index, and core ranking as classic Search, plus grounding (RAG) and query fan-out (the model generates related sub-queries and pulls pages for each). There is no separate AI ranking system. Good classic SEO IS AI visibility. Source: developers.google.com/search/docs/fundamentals/ai-optimization-guide.
Eligibility checklist (same as Search eligibility)
A page can only surface in AI features if it is:
- Indexed — not blocked by
noindex, in the index, not a duplicate canonicalized away - Crawlable —
robots.txtallows it; JS unblocked so rendered content is visible - Publicly accessible — no login/paywall wall on the content that should rank
- Snippet-eligible — no
nosnippet/max-snippet:0/data-nosnippeton the content you want quoted - Meets Search technical requirements + spam policies (no cloaking, scaled-content abuse)
Note: meeting every requirement does not guarantee crawl, index, or serving.
Content: people-first + unique POV
- Write for humans. Offer a unique point of view, first-hand experience, original data, or expertise the model can't synthesize from everyone else.
- Avoid commodity summaries an LLM could generate itself — those don't earn citation.
- Avoid scaled content abuse (mass keyword/location variations to manipulate).
- No ideal length. Clear headings, sections, short paragraphs. Self-contained answers near the top help, but do not chunk content into tiny fragments.
DEBUNKED — do NOT waste effort on these
| Myth | Reality |
|---|---|
llms.txt / AI text files / ai.txt |
Google Search ignores them. Zero benefit. |
| Special markdown / "machine-readable AI" copies | Not used. Serve normal HTML. |
| "Chunk" content into micro-pieces for the LLM | No benefit; harms readability. |
| Write copy specifically for generative AI | Write for people; ranking follows. |
| Chase inauthentic "mentions" / brand name-drops | Not a ranking signal; can be spam. |
| Separate "AEO/GEO ranking system" to game | Doesn't exist. Same index + ranking. |
What ships with it
1 file 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.
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.
- 4d ago First seen · 83 lines · 119 tokens per session scan A 1fe863e08c59
ai-search-optimization is a skill published in the GitHub repository S3YED/appie-kit (7 stars, last pushed 12d ago), licensed MIT. It adds 119 tokens to every session and 1,265 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
knowledge-query
Hybrid search (vector + BM25 via RRF + metadata boost) against the pgvector Knowledge base, with optional RAG synthesis. Use when the user asks factual questions that should be grounded in indexed documents (e.g., 'what do we know about X', 'search the knowledge base for Y', '@knowledge '). Pass answer=true to…
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
hybrid-search-implementation
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
langchain-architecture
Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
rag-vector-search-review
Use when you need to review retrieval, embeddings, chunking, vector search, ranking, and grounding strategy.