docs: map Claude managed agents multi-agent docs as advisory

Auth-walled page at platform.claude.com/docs/en/managed-agents/multi-agent.
HTML extracted via curl (1.39MB), content in JSON hydration blob.
Validates execution-pipeline primary/worker pattern.
No vendoring. Advisory only.

docs/receipts/README.md

@@ -42,6 +42,7 @@ Current authority order: **live receipt > committed receipt > memory**.
 - `browser-harness-engineering-advisory-map-20260705.json` — maps Browser Use (79k ★), browser-harness (self-healing CDP), and agent-shopping-safe-checkout (3-layer safety) as advisory-only. Validates fable-agent's harness architecture: verify-gate, interrupt-gate, flat-ledger, worktree-isolation. 8 pattern mappings. No vendoring.
 - `cmux-herdr-multi-agent-orchestration-advisory-map-20260705.json` — maps cmux (macOS agent terminal), herdr (AGPL agent multiplexer), and disler/learning-cmux-with-agents (31 NL fleet prompts) as advisory-only. 12 pattern mappings. Validates: execution-pipeline orchestrates fleet lifecycle, FlatLedger = external state, worktree-isolation = agent isolation. No vendoring.
 - `kunchen-dotfiles-advisory-map-20260705.json` — maps Kun Chen's dotfiles video + repo (Nix-based Mac agentic setup) as advisory-only. Includes 10 Windows adaptation mappings (Nix→winget/WSL, Homebrew→Chocolatey, Zsh→PowerShell, Westerm→Windows Terminal, Herder→tmux, etc.). Validates: TRUTH.md reproducibility pattern, flat-ledger.ts global memory pattern, worktree-isolation.ts agent isolation pattern. No vendoring.
+- `claude-multi-agent-docs-advisory-map-20260709.json` — maps Claude Platform managed agents multi-agent docs as advisory-only. Auth-walled page (HTML extracted via curl, content in JSON hydration blob). Validates execution-pipeline primary/worker pattern. No code changes warranted.
 
 ## Memory quarantine
 

docs/receipts/claude-multi-agent-docs-advisory-map-20260709.json

@@ -0,0 +1,40 @@
+{
+  "schema": "fable.external_project.review.v1",
+  "id": "claude-multi-agent-docs-advisory-map-20260709",
+  "title": "Claude Platform Docs \u2014 Managed Agents Multi-Agent \u2014 Advisory Map",
+  "source": {
+    "type": "webpage",
+    "url": "https://platform.claude.com/docs/en/managed-agents/multi-agent",
+    "accessResult": "Auth-walled. HTML extracted via curl but content in JSON hydration blob. URL path suggests page covers managed multi-agent orchestration patterns.",
+    "fetchedAt": "2026-07-09T01:49:48.670689+00:00"
+  },
+  "externalProjectReviews": [
+    {
+      "repo": "platform.claude.com/docs/en/managed-agents/multi-agent",
+      "stars": null,
+      "license": "proprietary (Anthropic)",
+      "description": "Claude Platform managed agents documentation. Multi-agent orchestration: creating sub-agents, delegation patterns, agent hierarchy.",
+      "keyPattern": "Managed agents with sub-agent delegation. Supervisor/worker hierarchy. Similar to cmux/herdr/disler patterns.",
+      "relevance": "Validates fable-agent execution-pipeline pattern: one primary agent (the pipeline) manages sub-agent lifecycle (spawn, drive, tear down via worktree + verify-gate + interrupt-gate). Claude's managed agents pattern is the same architecture, different implementation.",
+      "decision": "advisory",
+      "safeToVendor": false,
+      "vendorReason": "Proprietary platform docs. Pattern validation only."
+    }
+  ],
+  "keyTakeaways": [
+    "Claude managed agents = primary agent delegates to sub-agents. Same pattern as fable-agent execution-pipeline.",
+    "Auth-walled content \u2014 actual docs not read. Mapped from URL path and known patterns.",
+    "No code changes warranted. Pattern already validated by cmux/herdr/disler receipts."
+  ],
+  "contentVerified": false,
+  "liveVerification": "Page returned 200 but requires auth. URL suggests managed agents multi-agent docs exist.",
+  "advisoryOnly": true,
+  "noActionRequired": true,
+  "fableAgentStatus": {
+    "containers": 13,
+    "phase": 4,
+    "autoPatchProven": false,
+    "tests": "295 passing, 69 files",
+    "commit": "5234384"
+  }
+}