diff --git a/cli.py b/cli.py
index 7f2b160b1..2081c7aae 100755
--- a/cli.py
+++ b/cli.py
@@ -1724,6 +1724,8 @@ class HermesCLI:
             self._toggle_verbose()
         elif cmd_lower == "/compress":
             self._manual_compress()
+        elif cmd_lower == "/usage":
+            self._show_usage()
         else:
             # Check for skill slash commands (/gif-search, /axolotl, etc.)
             base_cmd = cmd_lower.split()[0]
@@ -1800,6 +1802,42 @@ class HermesCLI:
         except Exception as e:
             print(f"  ❌ Compression failed: {e}")
 
+    def _show_usage(self):
+        """Show cumulative token usage for the current session."""
+        if not self.agent:
+            print("(._.) No active agent -- send a message first.")
+            return
+
+        agent = self.agent
+        prompt = agent.session_prompt_tokens
+        completion = agent.session_completion_tokens
+        total = agent.session_total_tokens
+        calls = agent.session_api_calls
+
+        if calls == 0:
+            print("(._.) No API calls made yet in this session.")
+            return
+
+        # Current context window state
+        compressor = agent.context_compressor
+        last_prompt = compressor.last_prompt_tokens
+        ctx_len = compressor.context_length
+        pct = (last_prompt / ctx_len * 100) if ctx_len else 0
+        compressions = compressor.compression_count
+
+        msg_count = len(self.conversation_history)
+
+        print(f"  📊 Session Token Usage")
+        print(f"  {'─' * 40}")
+        print(f"  Prompt tokens (input):     {prompt:>10,}")
+        print(f"  Completion tokens (output): {completion:>9,}")
+        print(f"  Total tokens:              {total:>10,}")
+        print(f"  API calls:                 {calls:>10,}")
+        print(f"  {'─' * 40}")
+        print(f"  Current context:  {last_prompt:,} / {ctx_len:,} ({pct:.0f}%)")
+        print(f"  Messages:         {msg_count}")
+        print(f"  Compressions:     {compressions}")
+
         if self.verbose:
             logging.getLogger().setLevel(logging.DEBUG)
             for noisy in ('openai', 'openai._base_client', 'httpx', 'httpcore', 'asyncio', 'hpack', 'grpc', 'modal'):
diff --git a/hermes_cli/commands.py b/hermes_cli/commands.py
index 5de1c6bc6..b091a7905 100644
--- a/hermes_cli/commands.py
+++ b/hermes_cli/commands.py
@@ -27,6 +27,7 @@ COMMANDS = {
     "/platforms": "Show gateway/messaging platform status",
     "/verbose": "Cycle tool progress display: off → new → all → verbose",
     "/compress": "Manually compress conversation context (flush memories + summarize)",
+    "/usage": "Show token usage for the current session",
     "/quit": "Exit the CLI (also: /exit, /q)",
 }
 
diff --git a/run_agent.py b/run_agent.py
index 32b69489f..65dd3c2f0 100644
--- a/run_agent.py
+++ b/run_agent.py
@@ -535,6 +535,12 @@ class AIAgent:
         )
         self.compression_enabled = compression_enabled
         self._user_turn_count = 0
+
+        # Cumulative token usage for the session
+        self.session_prompt_tokens = 0
+        self.session_completion_tokens = 0
+        self.session_total_tokens = 0
+        self.session_api_calls = 0
         
         if not self.quiet_mode:
             if compression_enabled:
@@ -3105,6 +3111,11 @@ class AIAgent:
                             "total_tokens": total_tokens,
                         }
                         self.context_compressor.update_from_response(usage_dict)
+
+                        self.session_prompt_tokens += prompt_tokens
+                        self.session_completion_tokens += completion_tokens
+                        self.session_total_tokens += total_tokens
+                        self.session_api_calls += 1
                         
                         if self.verbose_logging:
                             logging.debug(f"Token usage: prompt={usage_dict['prompt_tokens']:,}, completion={usage_dict['completion_tokens']:,}, total={usage_dict['total_tokens']:,}")