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 cwinvestments/memstack --skill ai-search-visibilitygit clone --depth 1 https://github.com/cwinvestments/memstackWrote 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/cwinvestments/memstack/ai-search-visibility)<a href="https://agentmods.dev/skills/cwinvestments/memstack/ai-search-visibility"><img src="https://agentmods.dev/badge/skills/cwinvestments/memstack/ai-search-visibility.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 | $0.00071 | $0.04188 |
| Opus 5 | $0.00036 | $0.02094 |
| Sonnet 5 | $0.00014 | $0.00838 |
| Haiku 4.5 | $0.00007 | $0.00419 |
Grade A, and why
memstack-seo-ai-search-visibility 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 3d 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.
| llms.txt accessibility | After deploys | `curl https://domain.com/llms.txt` | How it starts
The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🤖 AI Search Visibility: Optimizing for AI search engines...
Evaluates and optimizes content for citation by AI search engines (ChatGPT, Perplexity, Google AI Overview, Claude): checking crawler access, content structure, llms.txt, and AI-friendly patterns.
Activation
When this skill activates, output:
🤖 AI Search Visibility: Analyzing AI search readiness...
Then execute the protocol below.
| Context | Status |
|---|---|
| User says "AI search" or "GEO" or "generative engine optimization" | ACTIVE |
| User says "ChatGPT ranking" or "Perplexity" or "AI overview" | ACTIVE |
| User says "llms.txt" or "AI visibility" | ACTIVE |
| Optimizing content for AI-generated citations and references | ACTIVE |
| Traditional SEO (meta tags, keywords) | DORMANT, use site-audit or meta-tag-optimizer |
| Building AI products (not optimizing for AI search) | DORMANT |
Anti-patterns
| Trap | Reality Check |
|---|---|
| "SEO is enough for AI" | AI search engines process content differently than Google. They need direct answers, not keyword-optimized copy. |
| "Block all AI crawlers" | Blocking AI crawlers means your content never appears in AI search results. Block selectively if at all. |
| "AI will find our content naturally" | AI systems prioritize structured, authoritative content. Unstructured marketing copy gets skipped. |
| "GEO is just a fad" | AI search usage is growing 10x year over year. Perplexity, ChatGPT search, and Google AI Overview are mainstream. |
| "We can't measure AI visibility" | You can check crawler logs, search your brand in AI tools, and track referral traffic from AI sources. |
Protocol
Step 1: Check AI Bot Crawler Access
Verify which AI crawlers can access your site:
# Check robots.txt for AI bot rules
cat public/robots.txt 2>/dev/null | grep -i "gptbot\|chatgpt\|perplexity\|claude\|anthropic\|cohere\|google-extended\|ccbot\|bytespider"
Known AI crawler user agents:
| Bot | Company | User-Agent | Purpose |
|---|---|---|---|
| GPTBot | OpenAI | GPTBot |
ChatGPT search, training |
| ChatGPT-User | OpenAI | ChatGPT-User |
ChatGPT browsing feature |
| PerplexityBot | Perplexity | PerplexityBot |
Perplexity search |
| ClaudeBot | Anthropic | ClaudeBot |
Claude web access |
| Google-Extended | Google-Extended |
Gemini, AI Overview | |
| CCBot | Common Crawl | CCBot |
Open dataset used by many AI |
| Bytespider | ByteDance | Bytespider |
TikTok/AI training |
| Cohere-ai | Cohere | cohere-ai |
Cohere models |
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.
- 3d ago Changed 780d4bcfe8c8
- 3d ago First seen · 360 lines · 71 tokens per session scan A 5eb855a989a4
memstack-seo-ai-search-visibility is a skill published in the GitHub repository cwinvestments/memstack (419 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 4,188 once invoked, about $0.0004 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
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
huggingface-best
Find and compare recommended Hugging Face models for a task using benchmarks, model size, and device constraints. Use for model selection questions; use huggingface-local-models for GGUF setup and hf-cli for Hub operations.
llm-patterns
AI-first application patterns, LLM testing, prompt management.
council-review
Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before executing.