{ "name": "Agent Discovery Doctor — AI Crawler Index", "description": "Audit which agent-discovery documents a host actually serves — robots.txt, llms.txt, openapi.json, the .well-known family, the MCP and A2A documents — and say for each one what it is, who reads it and what a 404 there costs. It also validates a pasted llms.txt or a pasted A2A agent card against the spec, and drafts an llms.txt from a sitemap. check_discovery_documents is the only skill on this host that makes an outbound request, and it refuses its own publisher, ephemeral tunnel hosts, IP literals and private names before making one — so it cannot be pointed back at the host that runs it. 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/doctor. No key, no signup, no quota. Independent and unaffiliated with any operator it documents.", "supportedInterfaces": [ { "url": "https://www.pathwren.workers.dev/a2a/doctor", "protocolBinding": "JSONRPC", "protocolVersion": "1.0" } ], "url": "https://www.pathwren.workers.dev/a2a/doctor", "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= 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 a few hundred bytes. 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" } } ] }, "defaultInputModes": [ "application/json", "text/plain" ], "defaultOutputModes": [ "application/json", "text/plain" ], "skills": [ { "id": "check_discovery_documents", "name": "Which discovery documents does this host serve?", "description": "Probes 22 documents agents and trust indexes ask for — llms.txt, agent card, owners.json, oauth metadata, mcp.json, apis.json, openapi, robots, sitemap — as served, missing, gated or 200-with-HTML soft-404, and says who asks for each missing one. Refuses private, ephemeral and its own hosts. Example: host='example.com'.", "tags": [ "discovery", "well-known", "audit", "agents" ], "examples": [ "{\"skill\":\"check_discovery_documents\",\"host\":\"example.com\"}", "check_discovery_documents example.com" ], "inputModes": [ "application/json", "text/plain" ], "outputModes": [ "application/json", "text/plain" ] }, { "id": "explain_document", "name": "What is this document, and who reads it?", "description": "One catalogue entry: what the document is for, the named clients observed asking this host for it with dates and the status they took, what a 404 costs, and the spec URL. No argument lists all 22. Example: name='owners.json' names the bot that asks for it twice.", "tags": [ "discovery", "reference", "documentation", "well-known" ], "examples": [ "{\"skill\":\"explain_document\",\"name\":\"llms.txt\"}", "explain_document agent-card" ], "inputModes": [ "application/json", "text/plain" ], "outputModes": [ "application/json", "text/plain" ] }, { "id": "validate_llms_txt", "name": "Check a pasted llms.txt", "description": "Checks pasted llms.txt against the format: one H1, a blockquote summary, H2 sections of `- [name](url): notes`. Errors and warnings with line numbers and fixes, plus the parsed links. Text in, nothing fetched. Example: text='# Site' warns it has no summary and no sections.", "tags": [ "llms.txt", "validation", "spec", "lint" ], "examples": [ "{\"skill\":\"validate_llms_txt\",\"text\":\"# Example\\n\\n> One line about the site.\\n\\n## Docs\\n\\n- [API](https://example.com/api.md): the API\\n\"}" ], "inputModes": [ "application/json", "text/plain" ], "outputModes": [ "application/json", "text/plain" ] }, { "id": "llms_txt_from_sitemap", "name": "Draft an llms.txt from a sitemap", "description": "Paste sitemap.xml, or one URL per line, and get a draft llms.txt: URLs grouped into H2 sections by path, titles from slugs, lastmod kept, and a TODO wherever only you can write the sentence. A sitemap index is reported as one. Example: xml='https://e.com/docs/a\\nhttps://e.com/blog/b'.", "tags": [ "llms.txt", "sitemap", "generator", "draft" ], "examples": [ "{\"skill\":\"llms_txt_from_sitemap\",\"xml\":\"https://example.com/\",\"title\":\"Example\"}" ], "inputModes": [ "application/json", "text/plain" ], "outputModes": [ "application/json", "text/plain" ] }, { "id": "validate_agent_card", "name": "Check a pasted A2A agent card", "description": "Validates a pasted /.well-known/agent-card.json against the nine fields A2A marks required and each skill's id/name/description/tags, and warns on capabilities declared true that a reader will then try. Example: json='{\"name\":\"a\"}' returns the eight missing fields.", "tags": [ "a2a", "agent card", "validation", "spec" ], "examples": [ "{\"skill\":\"validate_agent_card\",\"json\":\"{\\\"name\\\":\\\"Demo\\\",\\\"description\\\":\\\"d\\\",\\\"url\\\":\\\"https://example.com/a2a\\\",\\\"version\\\":\\\"1.0.0\\\",\\\"skills\\\":[]}\"}" ], "inputModes": [ "application/json", "text/plain" ], "outputModes": [ "application/json", "text/plain" ] } ] }