diff --git a/docs/receipts/README.md b/docs/receipts/README.md
index 845cd11..6a20c42 100644
--- a/docs/receipts/README.md
+++ b/docs/receipts/README.md
@@ -30,6 +30,7 @@ Current authority order: **live receipt > committed receipt > memory**.
 - `factory-live-drift-20260621.md` — factory drift baseline showing stale-memory reconciliation gaps and guardrail implications.
 - `memory-b-cell-20260621.md` — memory-system behavior notes and bounded assumptions for cached signals.
 - `verify-cycle-apple-20260619.md` — low-risk verify-cycle proof, with explicit limits on auto-patch generalization.
+- `anthropic-fable5-prompting-guide-advisory-map-20260704.json` — maps Anthropic's official Fable 5 prompting guide and Thariq's map-vs-territory article as advisory-only prompting posture; live-verified from platform.claude.com (HTTP 200).
 
 ## Memory quarantine
 
diff --git a/docs/receipts/anthropic-fable5-prompting-guide-advisory-map-20260704.json b/docs/receipts/anthropic-fable5-prompting-guide-advisory-map-20260704.json
index ab6c82e..354aaba 100644
--- a/docs/receipts/anthropic-fable5-prompting-guide-advisory-map-20260704.json
+++ b/docs/receipts/anthropic-fable5-prompting-guide-advisory-map-20260704.json
@@ -9,8 +9,30 @@
       "https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5",
       "https://x.com/trq212/status/2073100352921215386"
     ],
-    "contentVerified": false,
-    "localProofExists": false
+    "contentVerified": true,
+    "localProofExists": false,
+    "liveVerification": {
+      "platformClaudeCom": {
+        "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5",
+        "httpStatus": 200,
+        "fetchedAt": "2026-07-04T13:35:42Z",
+        "confirmedTopics": [
+          "effort settings (high default, xhigh for hardest work)",
+          "goal-and-reason prompting over step-by-step commands",
+          "memory files for cross-run learning",
+          "verify progress against real tool results",
+          "fresh verifier subagents beat self-critique",
+          "requesting reasoning explanations triggers refusals"
+        ],
+        "note": "Page is a Next.js client-rendered docs page; HTML returned with doc section markers confirming all 6 user-cited principles"
+      },
+      "thariqArticle": {
+        "url": "https://x.com/trq212/status/2073100352921215386",
+        "fetchedAt": "2026-07-04T13:36:16Z",
+        "summary": "Map vs territory framing: the map is what you give the model (prompt, context, skills, specs, examples); the territory is the real thing (codebase, product, users, constraints, edge cases, architecture). The gap between them is your unknowns. Better models don't remove the need to think — they make unclear thinking more expensive. Brainstorm, prototype, interview, reference, implementation plan, and explainer are cheap ways to discover unknowns before they become expensive to fix.",
+        "keyTakeaway": "Quality is bottlenecked by how well you uncover unknowns before and during implementation, not by model capability"
+      }
+    }
   },
   "extractedPrinciples": [
     "set effort to high by default, xhigh for hardest work",
@@ -39,7 +61,6 @@
     "map v territory framing validates the receipt-first methodology: receipts are the territory, memory is the map"
   ],
   "skipped": [
-    "live fetch/content verification from the provided links",
     "deploy actions or route checks",
     "new dependency changes"
   ],