@goflag/cli 0.2.13 → 0.2.15

package/dist/index.d.ts

@@ -1,3 +1,6 @@
+/** The outcome of probing a single URL. */
+type LinkVerdict = "ok" | "redirect" | "broken" | "blocked" | "warning" | "skipped";
+
 /**
  * Canonical Goflag data model.
  *
@@ -19,6 +22,7 @@
  *    JSON-LD path). This is what powers Phase 4's "what if I remove
  *    `og:image`?" toggle and the Phase 9 diff classifier.
  */
+
 /**
  * Where a parsed value originated. Used by previews to highlight which tag a
  * given preview consumed and by rules/suggestions to point the user back at
@@ -141,9 +145,6 @@ interface I18nMatrix {
     cells: Record<string, Record<string, I18nCell>>;
 }
 
-/** The outcome of probing a single URL. */
-type LinkVerdict = "ok" | "redirect" | "broken" | "blocked" | "warning" | "skipped";
-
 /**
  * The extraction model — goflag's per-page observation contract.
  *

package/dist/index.js

@@ -12,7 +12,7 @@ import {
   runAudit,
   summarize,
   targetKey
-} from "./chunk-57NVXEJS.js";
+} from "./chunk-KHIN5TNX.js";
 export {
   Logger,
   SAMPLE_LIMIT,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@goflag/cli",
-  "version": "0.2.13",
+  "version": "0.2.15",
   "type": "module",
   "description": "Audits a site for broken links, missing translation pages, a robots.txt that contradicts your pages, and missing or misconfigured SEO metadata. JSON-first.",
   "keywords": [
@@ -86,7 +86,7 @@
     "@vitest/coverage-v8": "^2.1.8",
     "commit-and-tag-version": "^12.5.0",
     "hono": "^4.12.25",
-    "playwright": "1.63.0",
+    "playwright": "1.64.1",
     "tsup": "^8.5.1",
     "tsx": "^4.21.0",
     "typescript": "^5.7.2",

package/rules.json

@@ -1,10 +1,17 @@
 {
   "counts": {
     "page": 25,
-    "site": 28,
+    "site": 34,
     "prose": 5
   },
   "sources": {
+    "anthropic-crawlers": {
+      "id": "anthropic-crawlers",
+      "publisher": "Anthropic",
+      "title": "Does Anthropic crawl data from the web, and how can site owners block the crawler?",
+      "rigor": "vendor-spec",
+      "url": "https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler"
+    },
     "apple-web-apps": {
       "id": "apple-web-apps",
       "publisher": "Apple",
@@ -33,6 +40,13 @@
       "rigor": "vendor-spec",
       "url": "https://developers.google.com/search/docs/specialty/international/localized-versions"
     },
+    "google-http-status": {
+      "id": "google-http-status",
+      "publisher": "Google",
+      "title": "How HTTP status codes, and network and DNS errors affect Google Search",
+      "rigor": "vendor-spec",
+      "url": "https://developers.google.com/search/docs/crawling-indexing/http-network-errors"
+    },
     "google-robots-intro": {
       "id": "google-robots-intro",
       "publisher": "Google",
@@ -61,6 +75,13 @@
       "rigor": "guideline",
       "url": "https://developers.google.com/search/docs/appearance/snippet"
     },
+    "google-soft-404": {
+      "id": "google-soft-404",
+      "publisher": "Google",
+      "title": "Troubleshoot Google Search crawling errors — soft 404 errors",
+      "rigor": "vendor-spec",
+      "url": "https://developers.google.com/search/docs/crawling-indexing/troubleshoot-crawling-errors"
+    },
     "google-title-link": {
       "id": "google-title-link",
       "publisher": "Google",
@@ -75,6 +96,13 @@
       "rigor": "normative",
       "url": "https://www.rfc-editor.org/rfc/rfc6596"
     },
+    "ietf-rfc9110": {
+      "id": "ietf-rfc9110",
+      "publisher": "IETF",
+      "title": "RFC 9110 — HTTP Semantics",
+      "rigor": "normative",
+      "url": "https://www.rfc-editor.org/rfc/rfc9110"
+    },
     "ietf-rfc9309": {
       "id": "ietf-rfc9309",
       "publisher": "IETF",
@@ -82,6 +110,20 @@
       "rigor": "normative",
       "url": "https://www.rfc-editor.org/rfc/rfc9309"
     },
+    "lighthouse-llms-txt": {
+      "id": "lighthouse-llms-txt",
+      "publisher": "Google",
+      "title": "Lighthouse — llms.txt (agentic browsing audit)",
+      "rigor": "guideline",
+      "url": "https://developer.chrome.com/docs/lighthouse/agentic-browsing/llms-txt"
+    },
+    "llmstxt": {
+      "id": "llmstxt",
+      "publisher": "llmstxt.org",
+      "title": "The /llms.txt file (a proposal)",
+      "rigor": "guideline",
+      "url": "https://llmstxt.org/"
+    },
     "mdn-link-rel": {
       "id": "mdn-link-rel",
       "publisher": "MDN / Mozilla",
@@ -353,6 +395,19 @@
       "sources": [],
       "prose": "Your `<head>` advertises a translation your sitemap does not list. Is the sitemap missing an entry, or is the alternate pointing at a page you did not mean to publish?"
     },
+    {
+      "id": "http.not-found",
+      "scope": "site",
+      "severity": "error",
+      "kind": "boolean",
+      "summary": "A URL that does not exist must answer 404 or 410",
+      "rigor": "vendor-spec",
+      "sources": [
+        "ietf-rfc9110",
+        "google-soft-404",
+        "google-http-status"
+      ]
+    },
     {
       "id": "icons.apple-touch.missing",
       "scope": "page",
@@ -503,6 +558,65 @@
       ],
       "prose": "Is the text of this page actually written in the language its `lang` attribute declares?"
     },
+    {
+      "id": "llmstxt.content-type",
+      "scope": "site",
+      "severity": "warning",
+      "kind": "boolean",
+      "summary": "`/llms.txt` must be served as text — `text/plain` or `text/markdown` — not as a page",
+      "rigor": "guideline",
+      "sources": [
+        "llmstxt",
+        "ietf-rfc9110"
+      ]
+    },
+    {
+      "id": "llmstxt.h1.missing",
+      "scope": "site",
+      "severity": "warning",
+      "kind": "boolean",
+      "summary": "An llms.txt must have an H1 naming the site",
+      "rigor": "guideline",
+      "sources": [
+        "llmstxt"
+      ]
+    },
+    {
+      "id": "llmstxt.link.blocked-by-robots",
+      "scope": "site",
+      "severity": "warning",
+      "kind": "boolean",
+      "summary": "An llms.txt must not list URLs that robots.txt forbids fetching",
+      "rigor": "guideline",
+      "sources": [
+        "llmstxt",
+        "ietf-rfc9309",
+        "anthropic-crawlers"
+      ]
+    },
+    {
+      "id": "llmstxt.link.unreachable",
+      "scope": "site",
+      "severity": "warning",
+      "kind": "boolean",
+      "summary": "Every same-origin URL an llms.txt lists must answer",
+      "rigor": "guideline",
+      "sources": [
+        "llmstxt"
+      ]
+    },
+    {
+      "id": "llmstxt.unreachable",
+      "scope": "site",
+      "severity": "warning",
+      "kind": "boolean",
+      "summary": "`/llms.txt` must answer with the file or with 404, not with a server error",
+      "rigor": "guideline",
+      "sources": [
+        "lighthouse-llms-txt",
+        "llmstxt"
+      ]
+    },
     {
       "id": "og.description.missing",
       "scope": "page",
@@ -1134,7 +1248,7 @@
       "scope": "site",
       "severity": "warning",
       "kind": "boolean",
-      "summary": "Indexable pages the crawl found should be listed in the sitemap",
+      "summary": "Indexable pages the crawl found, and the canonical URLs they name, should be listed in the sitemap",
       "rigor": "guideline",
       "sources": [
         "sitemaps-protocol",