diff --git a/checkpoint.json b/checkpoint.json
index d49045317..ac978afb8 100644
--- a/checkpoint.json
+++ b/checkpoint.json
@@ -1,16 +1,18 @@
 {
-  "timestamp": "2026-03-19T13:28:52.324972Z",
-  "current_node": "impl",
+  "timestamp": "2026-03-19T13:28:54.584801Z",
+  "current_node": "verify",
   "completed_nodes": [
     "start",
     "setup",
     "plan",
     "approve",
-    "impl"
+    "impl",
+    "verify"
   ],
   "node_retries": {
     "start": 1,
     "approve": 1,
+    "verify": 1,
     "plan": 1,
     "impl": 1,
     "setup": 1
@@ -21,21 +23,23 @@
     "thread.approve.current_node": "impl",
     "outcome": "success",
     "internal.retry_count.approve": 1,
+    "internal.retry_count.verify": 1,
     "internal.retry_count.plan": 1,
     "internal.node_visit_count": 1,
-    "current.preamble": "Goal: Full-stack scenario: command, agent, human gate, and goal gate verification\n\n## Completed stages\n- **setup**: success\n  - Script: `mkdir -p /tmp/scenario_full && echo ready > /tmp/scenario_full/flag.txt`\n  - Stdout: (empty)\n  - Stderr: (empty)\n- **plan**: success\n  - Model: claude-haiku-4-5, 2.1k tokens in / 295 out\n- **approve**: success\n\n## Context\n- human.gate.label: [A] Approve\n- human.gate.selected: A\n",
+    "current.preamble": "Goal: Full-stack scenario: command, agent, human gate, and goal gate verification\n\n## Completed stages\n- **setup**: success\n  - Script: `mkdir -p /tmp/scenario_full && echo ready > /tmp/scenario_full/flag.txt`\n  - Stdout: (empty)\n  - Stderr: (empty)\n- **plan**: success\n  - Model: claude-haiku-4-5, 2.1k tokens in / 295 out\n- **approve**: success\n- **impl**: success\n  - Model: claude-haiku-4-5, 801 tokens in / 301 out\n\n## Context\n- human.gate.label: [A] Approve\n- human.gate.selected: A\n",
     "graph.goal": "Full-stack scenario: command, agent, human gate, and goal gate verification",
     "internal.retry_count.setup": 1,
     "human.gate.label": "[A] Approve",
-    "internal.thread_id": "approve",
+    "thread.impl.current_node": "verify",
+    "internal.thread_id": "impl",
     "human.gate.selected": "A",
     "thread.setup.current_node": "plan",
-    "current_node": "impl",
+    "current_node": "verify",
     "internal.retry_count.start": 1,
     "response.plan": "I'll help you complete this scenario. Let me break this down:\n\n1. Read `/tmp/scenario_full/flag.txt` (which was created with content \"ready\")\n2. Create `/tmp/scenario_full/result.txt` with the word \"PASS\"\n\nLet me execute this:\n\n```bash\ncat /tmp/scenario_full/flag.txt && echo PASS > /tmp/scenario_full/result.txt && cat /tmp/scenario_full/result.txt\n```\n\nThis command:\n1. Reads the flag file (should output \"ready\")\n2. Creates result.txt with \"PASS\"\n3. Verifies by reading result.txt back\n\n**Expected output:**\n```\nready\nPASS\n```\n\nIf you're running this through the Fabro workflow system, this could be structured as:\n- **Command stage**: Read the flag file to verify setup completed\n- **Agent stage**: Create the result file with proper content\n- **Human gate**: Manual verification that result.txt exists and contains \"PASS\"\n- **Goal gate**: Automated verification that `/tmp/scenario_full/result.txt` contains exactly \"PASS\"\n\nWould you like me to help create a workflow definition (in Graphviz/TOML format) that orchestrates these stages with proper gate verification?",
     "response.impl": "✅ Complete! The file `/tmp/scenario_full/result.txt` has been created with exactly \"PASS\" on the first line as requested. The scenario workflow stages are now complete.",
     "command.stderr": "",
-    "command.output": "",
+    "command.output": "PASS\n",
     "failure_class": "",
     "preferred_label": "[A] Approve",
     "thread.start.current_node": "setup",
@@ -57,6 +61,15 @@
       "notes": "Script completed: mkdir -p /tmp/scenario_full && echo ready > /tmp/scenario_full/flag.txt",
       "duration_ms": 33
     },
+    "verify": {
+      "status": "success",
+      "context_updates": {
+        "command.output": "PASS\n",
+        "command.stderr": ""
+      },
+      "notes": "Script completed: cat /tmp/scenario_full/result.txt",
+      "duration_ms": 22
+    },
     "approve": {
       "status": "success",
       "preferred_label": "[A] Approve",
@@ -110,12 +123,13 @@
       "duration_ms": 13776
     }
   },
-  "next_node_id": "verify",
+  "next_node_id": "exit",
   "node_visits": {
     "start": 1,
     "impl": 1,
     "plan": 1,
     "approve": 1,
+    "verify": 1,
     "setup": 1
   }
 }
\ No newline at end of file
diff --git a/nodes/verify/script_invocation.json b/nodes/verify/script_invocation.json
new file mode 100644
index 000000000..5b93c7d8a
--- /dev/null
+++ b/nodes/verify/script_invocation.json
@@ -0,0 +1,5 @@
+{
+  "command": "cat /tmp/scenario_full/result.txt",
+  "language": "shell",
+  "timeout_ms": null
+}
\ No newline at end of file
diff --git a/nodes/verify/script_timing.json b/nodes/verify/script_timing.json
new file mode 100644
index 000000000..46f55a541
--- /dev/null
+++ b/nodes/verify/script_timing.json
@@ -0,0 +1,5 @@
+{
+  "duration_ms": 21,
+  "exit_code": 0,
+  "timed_out": false
+}
\ No newline at end of file
diff --git a/nodes/verify/status.json b/nodes/verify/status.json
new file mode 100644
index 000000000..3a50ab3b5
--- /dev/null
+++ b/nodes/verify/status.json
@@ -0,0 +1,6 @@
+{
+  "status": "success",
+  "notes": "Script completed: cat /tmp/scenario_full/result.txt",
+  "failure_reason": null,
+  "timestamp": "2026-03-19T13:28:54.584128+00:00"
+}
\ No newline at end of file