@goflag/cli 0.2.12 → 0.2.14

package/dist/cli.js

@@ -14,7 +14,7 @@ import {
   renderTerminal,
   runAudit,
   summarize
-} from "./chunk-QKXUKHXB.js";
+} from "./chunk-YQPL67HX.js";
 
 // src/report/diff.ts
 function collectFindings(report) {
@@ -1000,6 +1000,16 @@ var NORMATIVE = [
     retrievedAt: "2026-08-06",
     note: 'Defines rel="canonical": the preferred IRI for duplicative content. The target must not be a 404 and should not vary per duplicate (no self-referencing loops through redirects).'
   },
+  {
+    id: "ietf-rfc9110",
+    publisher: "IETF",
+    rigor: "normative",
+    title: "RFC 9110 \u2014 HTTP Semantics",
+    url: "https://www.rfc-editor.org/rfc/rfc9110",
+    retrievedAt: "2026-10-05",
+    quote: "The 404 (Not Found) status code indicates that the origin server did not find a current representation for the target resource or is not willing to disclose that one exists.",
+    note: "What a status code claims. 404 (\xA715.5.5) and 410 (\xA715.5.11, the permanent form) say there is nothing at the URL; a 2xx says there is; a 5xx (\xA715.6) says the server erred. Content-Type (\xA78.3) tells the recipient how to read what it was sent."
+  },
   {
     id: "ietf-rfc9309",
     publisher: "IETF",
@@ -1173,6 +1183,38 @@ var VENDOR = [
     retrievedAt: "2026-08-06",
     note: "How Meta's crawler builds link previews from og:* tags \u2014 including image size expectations (1200\xD7630 recommended, 200\xD7200 minimum) beyond what ogp.me specifies."
   },
+  {
+    id: "google-soft-404",
+    publisher: "Google",
+    rigor: "vendor-spec",
+    title: "Troubleshoot Google Search crawling errors \u2014 soft 404 errors",
+    url: "https://developers.google.com/search/docs/crawling-indexing/troubleshoot-crawling-errors",
+    anchor: "soft-404-errors",
+    retrievedAt: "2026-10-05",
+    quote: "If you removed the page and there's no replacement page on your site with similar content, return a 404 (not found) or 410 (gone) response (status) code for the page.",
+    note: "A soft 404 is a URL with no page behind it that answers 200 anyway. Google excludes such pages from Search and asks for a 404 or 410 instead. Search Console's Page indexing report (support.google.com/webmasters/answer/7440203) lists the same case and makes the same recommendation."
+  },
+  {
+    id: "google-http-status",
+    publisher: "Google",
+    rigor: "vendor-spec",
+    title: "How HTTP status codes, and network and DNS errors affect Google Search",
+    url: "https://developers.google.com/search/docs/crawling-indexing/http-network-errors",
+    anchor: "5xx-server-errors",
+    retrievedAt: "2026-10-05",
+    quote: "Google decreases the crawl rate for the site.",
+    note: "How Google's crawlers read each status class: a 4xx other than 429 means the content does not exist; a 5xx slows crawling of the whole site in proportion to the URLs that return one, and URLs that keep returning one leave the index."
+  },
+  {
+    id: "anthropic-crawlers",
+    publisher: "Anthropic",
+    rigor: "vendor-spec",
+    title: "Does Anthropic crawl data from the web, and how can site owners block the crawler?",
+    url: "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler",
+    retrievedAt: "2026-10-05",
+    quote: "Anthropic\u2019s Bots respect \u201Cdo not crawl\u201D signals by honoring industry standard directives in robots.txt.",
+    note: "Names Anthropic's agents, Claude-User among them \u2014 the one that fetches a page when a person asks Claude about it \u2014 and states that robots.txt governs all of them. An agent reading an llms.txt on a user's behalf is therefore bound by the same file that may forbid what the llms.txt lists."
+  },
   {
     id: "bing-webmaster-guidelines",
     publisher: "Microsoft",
@@ -1220,6 +1262,26 @@ var PRACTICAL = [
     retrievedAt: "2026-08-06",
     note: "The audit definitions Lighthouse ships (document has a title, has a meta description, valid hreflang, valid canonical, \u2026) \u2014 the closest thing to an industry-standard checklist to mirror."
   },
+  {
+    id: "lighthouse-llms-txt",
+    publisher: "Google",
+    rigor: "guideline",
+    title: "Lighthouse \u2014 llms.txt (agentic browsing audit)",
+    url: "https://developer.chrome.com/docs/lighthouse/agentic-browsing/llms-txt",
+    retrievedAt: "2026-10-05",
+    quote: "If the file is not provided by the server (resulting in a 404), the audit is marked as Not Applicable (N/A), as providing the file is optional at the moment.",
+    note: "Lighthouse's llms.txt audit fails a page when fetching /llms.txt returns a server error, and treats a 404 as not applicable. The cross-check for goflag's own reading: absent is fine, broken is not."
+  },
+  {
+    id: "llmstxt",
+    publisher: "llmstxt.org",
+    rigor: "guideline",
+    title: "The /llms.txt file (a proposal)",
+    url: "https://llmstxt.org/",
+    retrievedAt: "2026-10-05",
+    quote: "An H1 with the name of the project or site. This is the only required section",
+    note: "A proposal by Jeremy Howard, first published 2024-09-03 and revised since \u2014 not a standard, and no standards body has taken it up. It describes a markdown file at /llms.txt \u2014 an H1, then an optional summary, details and H2 file lists of [name](url) links \u2014 for agents to read on a user's behalf. Rules about it can claim no more than guideline."
+  },
   {
     id: "axe-core-rules",
     publisher: "Deque",