{
 "name": "Crawler Log Triage — AI Crawler Index",
 "description": "Paste access-log lines and get back who crawled you. It classifies each line by operator and category, rolls the whole file up by operator with byte and hit counts, finds the lines that are LYING — a user-agent claiming an operator from an address outside every range that operator publishes — and turns the file you actually served into a robots.txt for a stated stance or a WAF ruleset for nginx, caddy, Cloudflare, haproxy or apache. Combined, common, JSON and bare ip+user-agent lines are understood; nothing is fetched and no log is stored. An address outside a published range is reported as unverifiable, which is not the same as fake. Deterministic and read-only: there is no model behind it — every answer comes from a public dataset rebuilt every six hours from each operator's own published documentation and IP ranges, and the same skills are also available as MCP tools at https://www.pathwren.workers.dev/mcp/triage. No key, no signup, no quota. Independent and unaffiliated with any operator it documents. TO CALL IT: send `message/send` (v1.0 name `SendMessage`) — the first example on every skill below is a complete request you can POST unedited, and it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. Nothing to hand over? The `whoami` skill takes no arguments and answers about you. Every skill on all eight agents of this host as a ready-to-send body: https://www.pathwren.workers.dev/a2a/example.json",
 "supportedInterfaces": [
  {
   "url": "https://www.pathwren.workers.dev/a2a/triage",
   "protocolBinding": "JSONRPC",
   "protocolVersion": "1.0"
  }
 ],
 "url": "https://www.pathwren.workers.dev/a2a/triage",
 "preferredTransport": "JSONRPC",
 "protocolVersion": "1.0",
 "provider": {
  "organization": "Pathwren",
  "url": "https://www.pathwren.workers.dev"
 },
 "version": "1.0.0",
 "documentationUrl": "https://www.pathwren.workers.dev/a2a.html",
 "iconUrl": "https://www.pathwren.workers.dev/icon.png",
 "capabilities": {
  "streaming": false,
  "pushNotifications": false,
  "extendedAgentCard": false,
  "extensions": [
   {
    "uri": "https://www.pathwren.workers.dev/changes.json",
    "description": "Since-cursor change feed over everything this agent answers from: GET /changes.json?since=<cursor> returns only what moved — operator IP-range lists that gained or lost prefixes, upstreams that failed or recovered, crawler records added or edited. Read `cursor` from the answer and send it back next time; it advances only on a real change, so an unchanged answer is proof and costs about 2.5 KB. The same feed is the changes_since skill on this endpoint.",
    "required": false,
    "params": {
     "cursorParameter": "since",
     "transport": "https-get",
     "minPollSeconds": 21600,
     "skill": "changes_since",
     "siblingDocument": "https://www.pathwren.workers.dev/data/agents.json"
    }
   },
   {
    "uri": "https://www.pathwren.workers.dev/mcp/triage",
    "description": "THE SAME AGENT ON THE OTHER PROTOCOL. Every skill on this card is also a tool on an MCP (Model Context Protocol) server at https://www.pathwren.workers.dev/mcp/triage — same name, same arguments, same answer, because one function answers both doors and a deploy that let them drift is refused. JSON-RPC 2.0 over a single HTTP POST: no session to open, no SSE stream to hold, no key, no signup, no quota. If your runtime speaks MCP rather than A2A, add that URL as a server and you have everything on this card without writing an A2A client. `params.initialize` and `params.callATool` are COMPLETE request bodies — POST either one unedited and it answers; `params.curl` is the same thing as one line. The tool named `example` takes no arguments at all and runs this server's own worked example end to end, so the first call needs nothing you do not already have.",
    "required": false,
    "params": {
     "protocol": "MCP (Model Context Protocol)",
     "endpoint": "https://www.pathwren.workers.dev/mcp/triage",
     "transport": "streamable-http (JSON-RPC 2.0 in one HTTP POST; the response is JSON, not a stream)",
     "protocolVersions": [
      "2026-07-28",
      "2025-11-25",
      "2025-06-18",
      "2025-03-26",
      "2024-11-05"
     ],
     "authentication": "none",
     "a2aTwin": "https://www.pathwren.workers.dev/a2a/triage",
     "toolNamesEqualSkillIds": true,
     "sameImplementation": "Each skill on this card and the tool of the same name on that server are answered by one function; the deploy gate compares them skill by skill.",
     "initialize": {
      "jsonrpc": "2.0",
      "id": 1,
      "method": "initialize",
      "params": {
       "protocolVersion": "2026-07-28",
       "capabilities": {},
       "clientInfo": {
        "name": "example-client",
        "version": "1.0.0"
       }
      }
     },
     "callATool": {
      "jsonrpc": "2.0",
      "id": 2,
      "method": "tools/call",
      "params": {
       "name": "example",
       "arguments": {}
      }
     },
     "curl": "curl -s https://www.pathwren.workers.dev/mcp/triage -H 'content-type: application/json' -d '{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"tools/call\",\"params\":{\"name\":\"example\",\"arguments\":{}}}'",
     "everyToolAsABody": "https://www.pathwren.workers.dev/tools/",
     "discovery": "https://www.pathwren.workers.dev/.well-known/mcp.json"
    }
   }
  ]
 },
 "defaultInputModes": [
  "application/json",
  "text/plain"
 ],
 "defaultOutputModes": [
  "application/json",
  "text/plain"
 ],
 "skills": [
  {
   "id": "triage_log",
   "name": "Triage a paste of log lines",
   "description": "Paste log lines — combined, JSON, `uniq -c`, `<ip> <ua>` or bare user-agents, auto-detected — for per-line crawler, operator, purpose and cost of blocking, a rollup by operator and category, and every line whose address contradicts its claim. Log text, never a URL. Example: log='66.249.66.1 Googlebot/2.1' returns Googlebot, Google, search, verified.",
   "tags": [
    "logs",
    "crawlers",
    "classification",
    "triage"
   ],
   "examples": [
    "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"message/send\",\"params\":{\"message\":{\"role\":\"ROLE_USER\",\"messageId\":\"1\",\"parts\":[{\"text\":\"{\\\"skill\\\":\\\"triage_log\\\",\\\"log\\\":\\\"66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \\\\\\\"GET /pricing HTTP/1.1\\\\\\\" 200 5120 \\\\\\\"-\\\\\\\" \\\\\\\"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\\\\\\\"\\\\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \\\\\\\"GET /docs HTTP/1.1\\\\\\\" 200 1234 \\\\\\\"-\\\\\\\" \\\\\\\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\\\\\\\"\\\",\\\"detail\\\":\\\"summary\\\"}\"}]}}}",
    "{\"skill\":\"triage_log\",\"log\":\"66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \\\"GET /pricing HTTP/1.1\\\" 200 5120 \\\"-\\\" \\\"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\\\"\\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \\\"GET /docs HTTP/1.1\\\" 200 1234 \\\"-\\\" \\\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\\\"\",\"detail\":\"summary\"}",
    "66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \"GET /pricing HTTP/1.1\" 200 5120 \"-\" \"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\"\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \"GET /docs HTTP/1.1\" 200 1234 \"-\" \"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\""
   ],
   "inputModes": [
    "application/json",
    "text/plain"
   ],
   "outputModes": [
    "application/json",
    "text/plain"
   ]
  },
  {
   "id": "find_impersonators",
   "name": "Find the lines that are lying",
   "description": "Only the lines claiming a crawler whose operator publishes address ranges, from an address in none of to run: this server makes no outbound request. Example: log='203.0.113.9 Googlebot/2.1' returns one impersonation.",
   "tags": [
    "logs",
    "spoofing",
    "security",
    "verification"
   ],
   "examples": [
    "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"message/send\",\"params\":{\"message\":{\"role\":\"ROLE_USER\",\"messageId\":\"1\",\"parts\":[{\"text\":\"{\\\"skill\\\":\\\"find_impersonators\\\",\\\"log\\\":\\\"66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \\\\\\\"GET /pricing HTTP/1.1\\\\\\\" 200 5120 \\\\\\\"-\\\\\\\" \\\\\\\"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\\\\\\\"\\\\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \\\\\\\"GET /docs HTTP/1.1\\\\\\\" 200 1234 \\\\\\\"-\\\\\\\" \\\\\\\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\\\\\\\"\\\"}\"}]}}}",
    "{\"skill\":\"find_impersonators\",\"log\":\"66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \\\"GET /pricing HTTP/1.1\\\" 200 5120 \\\"-\\\" \\\"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\\\"\\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \\\"GET /docs HTTP/1.1\\\" 200 1234 \\\"-\\\" \\\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\\\"\"}"
   ],
   "inputModes": [
    "application/json",
    "text/plain"
   ],
   "outputModes": [
    "application/json",
    "text/plain"
   ]
  },
  {
   "id": "summarize_by_operator",
   "name": "Roll a log up by operator and category",
   "description": "Aggregate only: who crawled you, how many requests each, what share, which category, and what blocking each would cost. Eats a `uniq -c` table straight from a shell pipeline. Example: log='412 GPTBot/1.2' returns OpenAI, 412 requests, 100%, ai-training.",
   "tags": [
    "logs",
    "reporting",
    "operators",
    "summary"
   ],
   "examples": [
    "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"message/send\",\"params\":{\"message\":{\"role\":\"ROLE_USER\",\"messageId\":\"1\",\"parts\":[{\"text\":\"{\\\"skill\\\":\\\"summarize_by_operator\\\",\\\"log\\\":\\\"66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \\\\\\\"GET /pricing HTTP/1.1\\\\\\\" 200 5120 \\\\\\\"-\\\\\\\" \\\\\\\"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\\\\\\\"\\\\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \\\\\\\"GET /docs HTTP/1.1\\\\\\\" 200 1234 \\\\\\\"-\\\\\\\" \\\\\\\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\\\\\\\"\\\"}\"}]}}}",
    "{\"skill\":\"summarize_by_operator\",\"log\":\"66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \\\"GET /pricing HTTP/1.1\\\" 200 5120 \\\"-\\\" \\\"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\\\"\\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \\\"GET /docs HTTP/1.1\\\" 200 1234 \\\"-\\\" \\\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\\\"\"}"
   ],
   "inputModes": [
    "application/json",
    "text/plain"
   ],
   "outputModes": [
    "application/json",
    "text/plain"
   ]
  },
  {
   "id": "robots_from_log",
   "name": "robots.txt from a log",
   "description": "A robots.txt naming only the crawlers in your log, each with its request count and cost of blocking, plus a warning for any that do not documentably obey it — there the file is a request, not enforcement. Example: log='412 GPTBot/1.2', stance='block-ai-training' blocks GPTBot only.",
   "tags": [
    "logs",
    "robots.txt",
    "policy",
    "generator"
   ],
   "examples": [
    "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"message/send\",\"params\":{\"message\":{\"role\":\"ROLE_USER\",\"messageId\":\"1\",\"parts\":[{\"text\":\"{\\\"skill\\\":\\\"robots_from_log\\\",\\\"log\\\":\\\"66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \\\\\\\"GET /pricing HTTP/1.1\\\\\\\" 200 5120 \\\\\\\"-\\\\\\\" \\\\\\\"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\\\\\\\"\\\\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \\\\\\\"GET /docs HTTP/1.1\\\\\\\" 200 1234 \\\\\\\"-\\\\\\\" \\\\\\\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\\\\\\\"\\\",\\\"stance\\\":\\\"block-ai-training\\\"}\"}]}}}",
    "{\"skill\":\"robots_from_log\",\"log\":\"66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \\\"GET /pricing HTTP/1.1\\\" 200 5120 \\\"-\\\" \\\"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\\\"\\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \\\"GET /docs HTTP/1.1\\\" 200 1234 \\\"-\\\" \\\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\\\"\",\"stance\":\"block-ai-training\"}"
   ],
   "inputModes": [
    "application/json",
    "text/plain"
   ],
   "outputModes": [
    "application/json",
    "text/plain"
   ]
  },
  {
   "id": "waf_ruleset_from_log",
   "name": "WAF ruleset from a log",
   "description": "nginx, Caddy, Cloudflare, HAProxy or Apache rules for only the crawlers in your log. The reply warns that a UA rule stops only an honest client, and that impersonation is an address problem needing the published prefixes as an allowlist. Example: log='412 GPTBot/1.2', target='nginx', scope='ai-training'.",
   "tags": [
    "logs",
    "waf",
    "nginx",
    "cloudflare"
   ],
   "examples": [
    "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"message/send\",\"params\":{\"message\":{\"role\":\"ROLE_USER\",\"messageId\":\"1\",\"parts\":[{\"text\":\"{\\\"skill\\\":\\\"waf_ruleset_from_log\\\",\\\"log\\\":\\\"66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \\\\\\\"GET /pricing HTTP/1.1\\\\\\\" 200 5120 \\\\\\\"-\\\\\\\" \\\\\\\"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\\\\\\\"\\\\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \\\\\\\"GET /docs HTTP/1.1\\\\\\\" 200 1234 \\\\\\\"-\\\\\\\" \\\\\\\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\\\\\\\"\\\",\\\"target\\\":\\\"nginx\\\",\\\"action\\\":\\\"block\\\"}\"}]}}}",
    "{\"skill\":\"waf_ruleset_from_log\",\"log\":\"66.249.66.1 - - [01/Sep/2026:06:12:44 +0000] \\\"GET /pricing HTTP/1.1\\\" 200 5120 \\\"-\\\" \\\"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)\\\"\\n20.171.206.5 - - [01/Sep/2026:06:12:45 +0000] \\\"GET /docs HTTP/1.1\\\" 200 1234 \\\"-\\\" \\\"Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)\\\"\",\"target\":\"nginx\",\"action\":\"block\"}"
   ],
   "inputModes": [
    "application/json",
    "text/plain"
   ],
   "outputModes": [
    "application/json",
    "text/plain"
   ]
  },
  {
   "id": "whoami",
   "name": "Who is calling? (no arguments)",
   "description": "Takes no arguments. Safe to call. Deterministic. Touches no third party. Classifies the request you just sent: the user-agent you claim, the address you came from, the class this host's own instrument books you as, whether we have seen you here before and what you fetched, and what this host's robots policy says about you. Every fact comes from the headers on your own request or from a file this host already publishes — nothing is fetched, nothing about you is invented, no argument exists. Example: arguments={} returns your user-agent, your address, the class we book you as and whether we have seen you here before.",
   "tags": [
    "identify",
    "no arguments",
    "diagnostics",
    "user-agent"
   ],
   "examples": [
    "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"message/send\",\"params\":{\"message\":{\"role\":\"ROLE_USER\",\"messageId\":\"1\",\"parts\":[{\"text\":\"{\\\"skill\\\":\\\"whoami\\\"}\"}]}}}",
    "{\"skill\":\"whoami\"}",
    "whoami",
    "who am i to you"
   ],
   "inputModes": [
    "application/json",
    "text/plain"
   ],
   "outputModes": [
    "application/json",
    "text/plain"
   ]
  },
  {
   "id": "example",
   "name": "Run this server's worked example (no arguments)",
   "description": "Takes no arguments. Safe to call. Deterministic. Touches no third party. Runs this server's own worked example end to end — one of its real tools, on a canned input taken from this host's own published data — and returns exactly the structuredContent a real call returns, not a mock and not a description of one. Use it to see the shape of an answer before you decide what to send. No URL of yours is fetched and no third party is touched. Example: arguments={} runs it and returns the real answer.",
   "tags": [
    "example",
    "no arguments",
    "demo",
    "getting started"
   ],
   "examples": [
    "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"message/send\",\"params\":{\"message\":{\"role\":\"ROLE_USER\",\"messageId\":\"1\",\"parts\":[{\"text\":\"{\\\"skill\\\":\\\"example\\\"}\"}]}}}",
    "{\"skill\":\"example\"}",
    "example",
    "show me a worked example"
   ],
   "inputModes": [
    "application/json",
    "text/plain"
   ],
   "outputModes": [
    "application/json",
    "text/plain"
   ]
  }
 ]
}