roocode.com agentic web readiness

F Score 0 (coverage 0 + breadth 0 + conformance 0). 0 standards observed across 0 of 9 steps; 0 manifests present, 0 errors, 0 warnings. Checked 2026-10-18 23:43:03 UTC. This grades the agent-facing files published at roocode.com, not the organisation's products.

Badge for a README: ![agentic web grade](https://agenticweb.wiki/badge/roocode.com.svg) · JSON · Markdown · Re-check now

Coverage by step

01 Discovernothing observed 02 Identifynothing observed 03 Permitnothing observed 04 Readnothing observed 05 Actnothing observed 06 Coordinatenothing observed 07 Paynothing observed 08 Presentnothing observed 09 Accountnothing observed

Manifests

Manifest	Result	Findings
Agentic Resource Discovery `/.well-known/ard.json`	absent HTTP 301	not fetched: redirect off-host
AI Catalog well-known file `/.well-known/ai-catalog.json`	absent HTTP 301	not fetched: redirect off-host
MCP Server Cards (SEP-2127) `/mcp/server-card`	absent HTTP 301	not fetched: redirect off-host
Agent2Agent Protocol `/.well-known/agent-card.json`	absent HTTP 301	not fetched: redirect off-host
llms.txt `/llms.txt`	absent HTTP 301	not fetched: redirect off-host
AGENTS.md `/AGENTS.md`	absent HTTP 301	not fetched: redirect off-host
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs `/.well-known/api-catalog`	absent HTTP 301	not fetched: redirect off-host
AI Crawler User-Agent Tokens in robots.txt `/robots.txt`	absent HTTP 301	not fetched: redirect off-host
security.txt (RFC 9116) `/.well-known/security.txt`	absent HTTP 301	not fetched: redirect off-host
auth.md `/auth.md`	absent HTTP 301	not fetched: redirect off-host

Standards observed

None of the ~30 probed paths answered as a known standard.

Cheapest next steps

llms.txt: one Markdown index file; the most widely read agent-facing file
AI Crawler User-Agent Tokens in robots.txt: state what AI crawlers may do in robots.txt you already serve
Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch

How the grade is made

+10 per lifecycle step with a standard observed, counting manifests that validate or that the probe rule for the standard recognises (a valid MCP server card counts for MCP; max 90); +3 per observed standard beyond the first two (max 15); conformance +15 (+10 with one manifest) minus 5 per agent-facing manifest with errors, never below 0 (security.txt is reported, not scored). A+ >= 60, A >= 45, B >= 30, C >= 20, D >= 10. Errors are specification violations; warnings are best-practice gaps. Only public paths are fetched, without credentials, so standards that need a login (skipped in the probe) are not counted either way. The same report is the validate_manifest tool on the MCP server.

JSON · Markdown · probe rules