diff --git a/frontend/src/components/StatusBar.jsx b/frontend/src/components/StatusBar.jsx
index 1132069..8007de2 100644
--- a/frontend/src/components/StatusBar.jsx
+++ b/frontend/src/components/StatusBar.jsx
@@ -22,6 +22,7 @@ export function StatusBar({ sessionStats, isProcessing, connected, permissionMod
     cacheReadTokens = 0,
     cacheCreationTokens = 0,
     numTurns = 0,
+    contextWindow = 200000,
     isCompacting = false,
   } = sessionStats || {};
 
@@ -29,10 +30,12 @@ export function StatusBar({ sessionStats, isProcessing, connected, permissionMod
   const currentMode = PERMISSION_MODES.find(m => m.value === permissionMode) || PERMISSION_MODES[0];
   const ModeIcon = currentMode.icon;
 
-  // Calculate total tokens and estimate context usage
-  const totalTokens = inputTokens + outputTokens;
-  // Claude has ~200k context, but we show relative usage
-  const contextPercent = Math.min(100, (inputTokens / 200000) * 100);
+  // Calculate context usage
+  // inputTokens from modelUsage represents tokens in current context (including cache reads)
+  // contextWindow is the model's max context size (e.g., 200000 for opus)
+  const contextUsed = inputTokens + outputTokens;
+  const contextPercent = contextWindow > 0 ? Math.min(100, (contextUsed / contextWindow) * 100) : 0;
+  const contextRemaining = Math.max(0, 100 - contextPercent);
 
   // Format cost
   const formatCost = (cost) => {
@@ -137,7 +140,7 @@ export function StatusBar({ sessionStats, isProcessing, connected, permissionMod
         {/* Right side: Token usage */}
         <div className="flex items-center gap-4">
           {/* Token counts */}
-          {totalTokens > 0 && (
+          {contextUsed > 0 && (
             <div className="flex items-center gap-3 text-dark-400">
               <span className="flex items-center gap-1">
                 <span className="text-dark-500">In:</span>
@@ -156,15 +159,18 @@ export function StatusBar({ sessionStats, isProcessing, connected, permissionMod
             </div>
           )}
 
-          {/* Context status - simple text based on remaining context */}
+          {/* Context status - shows remaining context percentage */}
           <div className="flex items-center gap-2">
             <span className="text-dark-500">Context:</span>
-            {inputTokens > 0 ? (
+            {contextUsed > 0 ? (
               <span className={`${
-                contextPercent >= 95 ? 'text-red-400 font-medium' :
-                contextPercent >= 85 ? 'text-yellow-400' : 'text-green-400'
+                contextRemaining <= 5 ? 'text-red-400 font-medium animate-pulse' :
+                contextRemaining <= 15 ? 'text-red-400' :
+                contextRemaining <= 30 ? 'text-yellow-400' : 'text-green-400'
               }`}>
-                {contextPercent >= 85 ? `${(100 - contextPercent).toFixed(0)}% left` : 'ok'}
+                {contextRemaining <= 30
+                  ? `${contextRemaining.toFixed(0)}% left`
+                  : `${contextPercent.toFixed(0)}% used`}
               </span>
             ) : (
               <span className="text-green-400">ok</span>
diff --git a/frontend/src/hooks/useClaudeSession.js b/frontend/src/hooks/useClaudeSession.js
index 33d072c..59095d6 100644
--- a/frontend/src/hooks/useClaudeSession.js
+++ b/frontend/src/hooks/useClaudeSession.js
@@ -32,6 +32,7 @@ export function useClaudeSession() {
     cacheReadTokens: 0,
     cacheCreationTokens: 0,
     numTurns: 0,
+    contextWindow: 200000, // Default, updated from modelUsage
     isCompacting: false,
   });
 
@@ -361,14 +362,29 @@ export function useClaudeSession() {
       setIsProcessing(false);
 
       // Update session stats from result event
-      if (event.usage || event.total_cost_usd !== undefined) {
+      // Claude sends detailed modelUsage with per-model stats including contextWindow
+      // usage contains: input_tokens (new), cache_read_input_tokens, cache_creation_input_tokens, output_tokens
+      if (event.usage || event.modelUsage || event.total_cost_usd !== undefined) {
+        // Get the primary model's usage (usually claude-opus or claude-sonnet)
+        const modelUsage = event.modelUsage || {};
+        const primaryModel = Object.keys(modelUsage).find(k => k.includes('opus') || k.includes('sonnet'))
+          || Object.keys(modelUsage)[0];
+        const primaryUsage = primaryModel ? modelUsage[primaryModel] : null;
+
+        // Calculate effective input tokens (what's actually in context)
+        // This is: new input + cache read (cache creation doesn't count towards context limit)
+        const effectiveInput = (event.usage?.input_tokens || 0) +
+                               (event.usage?.cache_read_input_tokens || 0);
+
         setSessionStats(prev => ({
-          totalCost: event.total_cost_usd || prev.totalCost,
-          inputTokens: event.usage?.input_tokens || prev.inputTokens,
-          outputTokens: event.usage?.output_tokens || prev.outputTokens,
-          cacheReadTokens: event.usage?.cache_read_input_tokens || prev.cacheReadTokens,
-          cacheCreationTokens: event.usage?.cache_creation_input_tokens || prev.cacheCreationTokens,
-          numTurns: event.num_turns || prev.numTurns,
+          totalCost: event.total_cost_usd ?? prev.totalCost,
+          // Use modelUsage for accurate per-turn counts, fallback to usage
+          inputTokens: primaryUsage?.inputTokens ?? effectiveInput ?? prev.inputTokens,
+          outputTokens: primaryUsage?.outputTokens ?? event.usage?.output_tokens ?? prev.outputTokens,
+          cacheReadTokens: primaryUsage?.cacheReadInputTokens ?? event.usage?.cache_read_input_tokens ?? prev.cacheReadTokens,
+          cacheCreationTokens: primaryUsage?.cacheCreationInputTokens ?? event.usage?.cache_creation_input_tokens ?? prev.cacheCreationTokens,
+          numTurns: event.num_turns ?? prev.numTurns,
+          contextWindow: primaryUsage?.contextWindow ?? prev.contextWindow,
           isCompacting: false,
         }));
       }