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 multiplex-ai/muggle-ai-teams --skill geo-crawlersgit clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teamsWrote 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/multiplex-ai/muggle-ai-teams/geo-crawlers)<a href="https://agentmods.dev/skills/multiplex-ai/muggle-ai-teams/geo-crawlers"><img src="https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-teams/geo-crawlers/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/multiplex-ai/muggle-ai-teams/geo-crawlers"><img src="https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-teams/geo-crawlers.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 | $0.00047 | $0.04055 |
| Opus 5.5 | $0.00019 | $0.01622 |
| Sonnet 5.5 | $0.00009 | $0.00811 |
| Haiku 4.5 | $0.00005 | $0.00405 |
Grade A, and why
geo-crawlers 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 5d 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.
This is a copy
97% identical to geo-crawlers — 42 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Crawler Access Analysis Skill
Purpose
This skill analyzes a website's accessibility to AI crawlers -- the bots that AI companies use to discover, index, and train on web content. If AI crawlers are blocked, the site's content cannot appear in AI-generated responses regardless of its quality. Crawler access is the foundational technical requirement for GEO.
Key Insight
As of early 2026, many websites inadvertently block AI crawlers through overly aggressive robots.txt rules, inherited from legacy SEO configurations. An Originality.ai 2025 study found that over 35% of the top 1,000 websites block at least one major AI crawler, and 5-10% block all AI crawlers. Blocking AI crawlers is the single fastest way to become invisible in AI-generated search results.
Complete AI Crawler Reference
Tier 1: Critical for AI Search Visibility (RECOMMEND: ALLOW)
These crawlers power the AI search products where users actively look for answers. Blocking them directly reduces your visibility in AI-generated responses.
GPTBot
- Operator: OpenAI
- User-Agent:
GPTBot - Full User-Agent String:
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; GPTBot/1.2; +https://openai.com/gptbot) - Purpose: Fetches content for ChatGPT's web browsing, plugins, and search features. Content accessed by GPTBot may be used to improve OpenAI models.
- Impact of Blocking: Content will NOT appear in ChatGPT Search results or be accessible when users ask ChatGPT to browse the web. This is the highest-impact AI crawler to allow.
- Recommendation: ALLOW -- ChatGPT has 300M+ weekly active users as of 2025. Blocking GPTBot removes your content from one of the largest AI search surfaces.
OAI-SearchBot
- Operator: OpenAI
- User-Agent:
OAI-SearchBot - Full User-Agent String:
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; OAI-SearchBot/1.0; +https://docs.openai.com/bots/overview) - Purpose: Specifically powers ChatGPT's search feature. Unlike GPTBot, content accessed by OAI-SearchBot is NOT used for model training -- only for live search results.
- Impact of Blocking: Content will not appear in ChatGPT's search results even if GPTBot is allowed.
- Recommendation: ALLOW -- This is a search-only crawler with no training implications. There is no strategic reason to block it.
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.
- 5d ago First seen · 346 lines · 47 tokens per session scan A ca983eda10da
geo-crawlers is a skill published in the GitHub repository multiplex-ai/muggle-ai-teams (2 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 4,055 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to geo-crawlers, differing in 42 lines, and is treated as a copy.
Other skills, from other repositories
codex-handoff
Three-phase delivery workflow — Claude plans and writes a spec, a Claude subagent implements in the host working tree, a fresh Codex session adversarially reviews the diff (via the codex-plugin-cc plugin). Implementation and review are never the same model. Use for any change touching more than one file or real…
discuss
Decision-lock workflow for complex features. Asks targeted domain-specific questions, locks scope, and writes a CONTEXT.md that downstream skills consume. Auto-invoked when a feature touches 3+ files across 2+ concerns, or manually via /discuss.
skill-name
One-line description of what this skill does and when it triggers.
codex-handoff
Three-phase delivery workflow — Claude plans and writes a spec, a Claude subagent implements in the host working tree, a fresh Codex session adversarially reviews the diff (via the codex-plugin-cc plugin). Implementation and review are never the same model. Use for any change touching more than one file or real…
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.