robotstxt-ai: Skill for Claude Code

.claude/skills/robots-ai/SKILL.md

robots-ai is a skill for Claude Code from sharozdawa/robotstxt-ai. It costs 44 tokens per session (837 once invoked), scanned A, original, MIT.

A robots.txt analyzer and generator focused on AI crawlers. It identifies whether bots such as GPTBot, ClaudeBot, and PerplexityBot are allowed or blocked.

In plain words
What is it for?
Use it to analyze a website’s robots.txt, audit it for issues, generate a new file, or look up known AI crawler names and user-agents.
Why use it?
It makes unclear robots.txt rules easier to inspect and helps find missing or inconsistent AI-crawler rules.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is sharozdawa/robotstxt-ai's own configuration. It tells Claude Code how to work on robotstxt-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything robotstxt-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sharozdawa/robotstxt-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sharozdawa/robotstxt-ai/main/.claude/skills/robots-ai/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sharozdawa/robotstxt-ai

Made for: Claude Code.

Wrote 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.

agentmods badge for robots-ai

README.md
[![agentmods](https://agentmods.dev/badge/skills/sharozdawa/robotstxt-ai/robots-ai/github.svg)](https://agentmods.dev/skills/sharozdawa/robotstxt-ai/robots-ai)
Your own site
<a href="https://agentmods.dev/skills/sharozdawa/robotstxt-ai/robots-ai"><img src="https://agentmods.dev/badge/skills/sharozdawa/robotstxt-ai/robots-ai/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.

agentmods 80×15 button for robots-ai

Your own site · 80×15
<a href="https://agentmods.dev/skills/sharozdawa/robotstxt-ai/robots-ai"><img src="https://agentmods.dev/badge/skills/sharozdawa/robotstxt-ai/robots-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00837
Opus 5.5 $0.00018 $0.00335
Sonnet 5.5 $0.00009 $0.00167
Haiku 4.5 $0.00004 $0.00084

Measured 2mo ago against content hash 36319e039069, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

robots-ai 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 2mo 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.

.claude/skills/robots-ai/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

robots-ai

Analyze, audit, and generate robots.txt files with full awareness of 20+ AI crawlers.

Capabilities

  • Analyze any website's robots.txt to see which AI bots are blocked/allowed
  • Generate a robots.txt with toggleable AI bot blocking
  • Audit existing robots.txt for completeness and issues
  • List all known AI crawlers with their user-agents, companies, and documentation links

AI Bots Database

You know about these AI crawlers and their user-agents:

Bot User-Agent Company Type
GPTBot GPTBot OpenAI AI Crawler
ChatGPT-User ChatGPT-User OpenAI AI Search
OAI-SearchBot OAI-SearchBot OpenAI AI Search
ClaudeBot ClaudeBot Anthropic AI Crawler
anthropic-ai anthropic-ai Anthropic AI Crawler
Google-Extended Google-Extended Google AI Crawler
PerplexityBot PerplexityBot Perplexity AI Search
CCBot CCBot Common Crawl AI Crawler
Bytespider Bytespider ByteDance AI Crawler
Diffbot Diffbot Diffbot AI Crawler
cohere-ai cohere-ai Cohere AI Crawler
Amazonbot Amazonbot Amazon AI Crawler
Meta-ExternalAgent Meta-ExternalAgent Meta AI Crawler
Meta-ExternalFetcher Meta-ExternalFetcher Meta AI Crawler
Applebot-Extended Applebot-Extended Apple AI Crawler
YouBot YouBot You.com AI Search
Timpibot Timpibot Timpi AI Crawler
img2dataset img2dataset Open Source AI Crawler

Important Notes

  • Google-Extended controls Gemini training access but does NOT affect Google Search indexing
  • Blocking Googlebot removes the site from Google Search entirely — never do this unless explicitly asked
  • CCBot feeds Common Crawl, which is used by many AI companies for training data
  • Bytespider (ByteDance) and Timpibot are commonly blocked by default due to aggressive crawling

How to Analyze

When asked to analyze a robots.txt:

  1. Fetch the robots.txt from the URL (append /robots.txt if not included)
  2. Parse all User-agent directives and their Allow/Disallow rules
  3. Check each AI bot against the rules
  4. Report: which bots are blocked, which are allowed, and any issues found
  5. Suggest improvements if relevant

Read the full file on GitHub · 88 lines

Changes

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.

  1. 2mo ago First seen · 88 lines · 44 tokens per session scan A 36319e039069

Subscribe to this mod's changes

robots-ai is a skill published in the GitHub repository sharozdawa/robotstxt-ai (1 stars, last pushed 8mo ago), licensed MIT. It adds 44 tokens to every session and 837 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Related

robots-ai compared with skills from other repositories

robots-ai next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
robots-aisharozdawa/robotstxt-aiSkill18mo agoMITA44Claude Code
reskinCopilotKit/CopilotKitSkill39kyesterdayMITA154Claude Code
copilotkit-channelsCopilotKit/CopilotKitSkill39kyesterdayMITA112Claude Code
setup-slack-channelCopilotKit/CopilotKitSkill39kyesterdayMITA206Claude Code
a2ui-catalogCopilotKit/CopilotKitSkill39kyesterdayMITA190Claude Code
copilotkit-cliCopilotKit/CopilotKitSkill39kyesterdayMITA87Claude Code
a2ui-coreCopilotKit/CopilotKitSkill39kyesterdayMITA18Claude Code