geo-crawlers
Skill9 starsChanged 7 months agoMITView on GitHub
Parse a site's robots.txt and report AI-bot policy coherence. Classifies every relevant user-agent into 3 categories (training / RAG-search / user-request) and surfaces inversions (e.g. GPTBot allowed but OAI-SearchBot blocked — backwards configuration). Use when user asks about robots.txt, AI bots, GPTBot, ClaudeBot, crawler access.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- alpit-patel/seo-aeo-geo-kittheir own version, first seen Nov 8, 2026
- DoddleHQ/doddle-seo-geo-skillstheir own version, first seen Oct 20, 2026
- Ormus-Solutions/LibreGEO-Claude-Codetheir own version, first seen Oct 13, 2026
- techhorizonlabs/thl-opentheir own version, first seen Oct 9, 2026
- HermeticOrmus/LibreGEO-Claude-Codetheir own version, first seen Oct 1, 2026
- zubair-trabzada/geo-seo-claudetheir own version, first seen Aug 4, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- zubair-trabzada/geo-seo-claude★ 11ksame name
- techhorizonlabs/thl-open★ 16same name
- alpit-patel/seo-aeo-geo-kit★ 2same name
- HermeticOrmus/LibreGEO-Claude-Code★ 1same name
- Ormus-Solutions/LibreGEO-Claude-Code★ 1same name
- DoddleHQ/doddle-seo-geo-skills★ 0same name
- kennyolofsson23-netizen/claude-code-config★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- geoSkill
- geo-auditSkill
- geo-clientSkill
- geo-content-healthSkill
- geo-rrfSkill
- geo-schemaSkill
The file
Files
geo-crawlers — AI crawler policy audit
Single-call audit of a domain's robots.txt with 3-category bot taxonomy.
Command
python3 -m scripts.checks.crawlers <url>The script fetches <url>/robots.txt, parses every relevant directive (user-agent, allow, disallow), and classifies each AI-related bot it sees.
Bot taxonomy (3 categories)
The toolkit groups AI bots by what they do with the data, not by which company runs them. The three categories have opposite default policies:
| Category | Default policy | Examples |
| 🔴 Training | Block by default — fetched to train base models, no live citation benefit | GPTBot, ClaudeBot, anthropic-ai, CCBot, Applebot-Extended, Google-Extended |
| 🟢 RAG / search | Allow by default — fetched at query time to cite live in answers | OAI-SearchBot, PerplexityBot, Claude-SearchBot |
| 🟢 User-request | Allow by default — fetched only when a user explicitly asks the assistant to read a URL | ChatGPT-User, Claude-User, Perplexity-User, Google-Agent, MistralAI-User |
29 bots are catalogued in docs/CRAWLERS_TAXONOMY.md.
What gets flagged
CR1— A high-intent bot (RAG or user-request) is explicitly blocked. Likely an oversight; biggest hit on AI search visibility.CR2— Inverted config (e.g. ClaudeBot allowed, Claude-SearchBot blocked). The "wrong" bot of the pair has the right policy.CR-INFO2— RAG bot not explicitly listed (allowed viaUser-agent: *). Cosmetic — alowfinding for clarity / future-proofing.CR-INFO3— User-request bot not explicitly listed. Same.
Why this matters
Most public guides repeat "allow GPTBot to be visible in ChatGPT" — that's wrong. GPTBot is a training crawler; allowing it does not help you appear in ChatGPT search results. The bot to allow for ChatGPT live citation is OAI-SearchBot. Same pattern for Anthropic (ClaudeBot trains, Claude-SearchBot retrieves). The geo-crawlers audit catches this confusion.
Source: docs/sources/02-rankit-crawlers-ia-2026-03.md (archived).
Output
Markdown report to stdout. When called from run_audit.py, feeds Annex B.
Dependencies
scripts/checks/crawlers.py- Python:
requests
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.