diff --git a/apps/backend/.env.example b/apps/backend/.env.example
index a2b98273..8c8e1a7e 100644
--- a/apps/backend/.env.example
+++ b/apps/backend/.env.example
@@ -7,7 +7,8 @@
 # Auto Claude uses Claude Code OAuth authentication.
 # Direct API keys (ANTHROPIC_API_KEY) are NOT supported to prevent silent billing.
 #
-# Option 1: Run `claude setup-token` to save token to macOS Keychain (recommended)
+# Option 1: Run `claude setup-token` to save token to system keychain (recommended)
+#           (macOS: Keychain, Windows: Credential Manager, Linux: secret-service)
 # Option 2: Set the token explicitly:
 # CLAUDE_CODE_OAUTH_TOKEN=your-oauth-token-here
 #
diff --git a/apps/backend/core/auth.py b/apps/backend/core/auth.py
index ae0c6bae..be105e1f 100644
--- a/apps/backend/core/auth.py
+++ b/apps/backend/core/auth.py
@@ -34,20 +34,30 @@ SDK_ENV_VARS = [
 
 def get_token_from_keychain() -> str | None:
     """
-    Get authentication token from macOS Keychain.
+    Get authentication token from system credential store.
 
-    Reads Claude Code credentials from macOS Keychain and extracts the OAuth token.
-    Only works on macOS (Darwin platform).
+    Reads Claude Code credentials from:
+    - macOS: Keychain
+    - Windows: Credential Manager
+    - Linux: Not yet supported (use env var)
 
     Returns:
-        Token string if found in Keychain, None otherwise
+        Token string if found, None otherwise
     """
-    # Only attempt on macOS
-    if platform.system() != "Darwin":
+    system = platform.system()
+
+    if system == "Darwin":
+        return _get_token_from_macos_keychain()
+    elif system == "Windows":
+        return _get_token_from_windows_credential_files()
+    else:
+        # Linux: secret-service not yet implemented
         return None
 
+
+def _get_token_from_macos_keychain() -> str | None:
+    """Get token from macOS Keychain."""
     try:
-        # Query macOS Keychain for Claude Code credentials
         result = subprocess.run(
             [
                 "/usr/bin/security",
@@ -64,14 +74,11 @@ def get_token_from_keychain() -> str | None:
         if result.returncode != 0:
             return None
 
-        # Parse JSON response
         credentials_json = result.stdout.strip()
         if not credentials_json:
             return None
 
         data = json.loads(credentials_json)
-
-        # Extract OAuth token from nested structure
         token = data.get("claudeAiOauth", {}).get("accessToken")
 
         if not token:
@@ -84,18 +91,45 @@ def get_token_from_keychain() -> str | None:
         return token
 
     except (subprocess.TimeoutExpired, json.JSONDecodeError, KeyError, Exception):
-        # Silently fail - this is a fallback mechanism
+        return None
+
+
+def _get_token_from_windows_credential_files() -> str | None:
+    """Get token from Windows credential files.
+
+    Claude Code on Windows stores credentials in ~/.claude/.credentials.json
+    """
+    try:
+        # Claude Code stores credentials in ~/.claude/.credentials.json
+        cred_paths = [
+            os.path.expandvars(r"%USERPROFILE%\.claude\.credentials.json"),
+            os.path.expandvars(r"%USERPROFILE%\.claude\credentials.json"),
+            os.path.expandvars(r"%LOCALAPPDATA%\Claude\credentials.json"),
+            os.path.expandvars(r"%APPDATA%\Claude\credentials.json"),
+        ]
+
+        for cred_path in cred_paths:
+            if os.path.exists(cred_path):
+                with open(cred_path, encoding="utf-8") as f:
+                    data = json.load(f)
+                    token = data.get("claudeAiOauth", {}).get("accessToken")
+                    if token and token.startswith("sk-ant-oat01-"):
+                        return token
+
+        return None
+
+    except (json.JSONDecodeError, KeyError, FileNotFoundError, Exception):
         return None
 
 
 def get_auth_token() -> str | None:
     """
-    Get authentication token from environment variables or macOS Keychain.
+    Get authentication token from environment variables or system credential store.
 
     Checks multiple sources in priority order:
     1. CLAUDE_CODE_OAUTH_TOKEN (env var)
     2. ANTHROPIC_AUTH_TOKEN (CCR/proxy env var for enterprise setups)
-    3. macOS Keychain (if on Darwin platform)
+    3. System credential store (macOS Keychain, Windows Credential Manager)
 
     NOTE: ANTHROPIC_API_KEY is intentionally NOT supported to prevent
     silent billing to user's API credits when OAuth is misconfigured.
@@ -109,7 +143,7 @@ def get_auth_token() -> str | None:
         if token:
             return token
 
-    # Fallback to macOS Keychain
+    # Fallback to system credential store
     return get_token_from_keychain()
 
 
@@ -120,9 +154,15 @@ def get_auth_token_source() -> str | None:
         if os.environ.get(var):
             return var
 
-    # Check if token came from macOS Keychain
+    # Check if token came from system credential store
     if get_token_from_keychain():
-        return "macOS Keychain"
+        system = platform.system()
+        if system == "Darwin":
+            return "macOS Keychain"
+        elif system == "Windows":
+            return "Windows Credential Files"
+        else:
+            return "System Credential Store"
 
     return None
 
@@ -142,13 +182,22 @@ def require_auth_token() -> str:
             "Direct API keys (ANTHROPIC_API_KEY) are not supported.\n\n"
         )
         # Provide platform-specific guidance
-        if platform.system() == "Darwin":
+        system = platform.system()
+        if system == "Darwin":
             error_msg += (
                 "To authenticate:\n"
                 "  1. Run: claude setup-token\n"
                 "  2. The token will be saved to macOS Keychain automatically\n\n"
                 "Or set CLAUDE_CODE_OAUTH_TOKEN in your .env file."
             )
+        elif system == "Windows":
+            error_msg += (
+                "To authenticate:\n"
+                "  1. Run: claude setup-token\n"
+                "  2. The token should be saved to Windows Credential Manager\n\n"
+                "If auto-detection fails, set CLAUDE_CODE_OAUTH_TOKEN in your .env file.\n"
+                "Check: %LOCALAPPDATA%\\Claude\\credentials.json"
+            )
         else:
             error_msg += (
                 "To authenticate:\n"
diff --git a/apps/backend/runners/github/runner.py b/apps/backend/runners/github/runner.py
index dabfa4d5..02af642e 100644
--- a/apps/backend/runners/github/runner.py
+++ b/apps/backend/runners/github/runner.py
@@ -46,6 +46,13 @@ import os
 import sys
 from pathlib import Path
 
+# Fix Windows console encoding for Unicode output (emojis, special chars)
+if sys.platform == "win32":
+    if hasattr(sys.stdout, "reconfigure"):
+        sys.stdout.reconfigure(encoding="utf-8", errors="replace")
+    if hasattr(sys.stderr, "reconfigure"):
+        sys.stderr.reconfigure(encoding="utf-8", errors="replace")
+
 # Add backend to path
 sys.path.insert(0, str(Path(__file__).parent.parent.parent))
 
@@ -79,34 +86,70 @@ def print_progress(callback: ProgressCallback) -> None:
 
 def get_config(args) -> GitHubRunnerConfig:
     """Build config from CLI args and environment."""
+    import shutil
+    import subprocess
+
     token = args.token or os.environ.get("GITHUB_TOKEN", "")
     bot_token = args.bot_token or os.environ.get("GITHUB_BOT_TOKEN")
     repo = args.repo or os.environ.get("GITHUB_REPO", "")
 
-    if not token:
+    # Find gh CLI - use shutil.which for cross-platform support
+    gh_path = shutil.which("gh")
+    if not gh_path and sys.platform == "win32":
+        # Fallback: check common Windows installation paths
+        common_paths = [
+            r"C:\Program Files\GitHub CLI\gh.exe",
+            r"C:\Program Files (x86)\GitHub CLI\gh.exe",
+            os.path.expandvars(r"%LOCALAPPDATA%\Programs\GitHub CLI\gh.exe"),
+        ]
+        for path in common_paths:
+            if os.path.exists(path):
+                gh_path = path
+                break
+
+    if os.environ.get("DEBUG"):
+        print(f"[DEBUG] gh CLI path: {gh_path}", flush=True)
+        print(
+            f"[DEBUG] PATH env: {os.environ.get('PATH', 'NOT SET')[:200]}...",
+            flush=True,
+        )
+
+    if not token and gh_path:
         # Try to get from gh CLI
-        import subprocess
+        try:
+            result = subprocess.run(
+                [gh_path, "auth", "token"],
+                capture_output=True,
+                text=True,
+            )
+            if result.returncode == 0:
+                token = result.stdout.strip()
+        except FileNotFoundError:
+            pass  # gh not installed or not in PATH
 
-        result = subprocess.run(
-            ["gh", "auth", "token"],
-            capture_output=True,
-            text=True,
-        )
-        if result.returncode == 0:
-            token = result.stdout.strip()
-
-    if not repo:
+    if not repo and gh_path:
         # Try to detect from git remote
-        import subprocess
-
-        result = subprocess.run(
-            ["gh", "repo", "view", "--json", "nameWithOwner", "-q", ".nameWithOwner"],
-            cwd=args.project,
-            capture_output=True,
-            text=True,
-        )
-        if result.returncode == 0:
-            repo = result.stdout.strip()
+        try:
+            result = subprocess.run(
+                [
+                    gh_path,
+                    "repo",
+                    "view",
+                    "--json",
+                    "nameWithOwner",
+                    "-q",
+                    ".nameWithOwner",
+                ],
+                cwd=args.project,
+                capture_output=True,
+                text=True,
+            )
+            if result.returncode == 0:
+                repo = result.stdout.strip()
+            elif os.environ.get("DEBUG"):
+                print(f"[DEBUG] gh repo view failed: {result.stderr}", flush=True)
+        except FileNotFoundError:
+            pass  # gh not installed or not in PATH
 
     if not token:
         print("Error: No GitHub token found. Set GITHUB_TOKEN or run 'gh auth login'")
@@ -133,27 +176,42 @@ async def cmd_review_pr(args) -> int:
     import sys
 
     # Force unbuffered output so Electron sees it in real-time
-    sys.stdout.reconfigure(line_buffering=True)
-    sys.stderr.reconfigure(line_buffering=True)
+    if hasattr(sys.stdout, "reconfigure"):
+        sys.stdout.reconfigure(line_buffering=True)
+    if hasattr(sys.stderr, "reconfigure"):
+        sys.stderr.reconfigure(line_buffering=True)
 
-    print(f"[DEBUG] Starting PR review for PR #{args.pr_number}", flush=True)
-    print(f"[DEBUG] Project directory: {args.project}", flush=True)
+    debug = os.environ.get("DEBUG")
+    if debug:
+        print(f"[DEBUG] Starting PR review for PR #{args.pr_number}", flush=True)
+        print(f"[DEBUG] Project directory: {args.project}", flush=True)
+        print("[DEBUG] Building config...", flush=True)
 
-    print("[DEBUG] Building config...", flush=True)
     config = get_config(args)
-    print(f"[DEBUG] Config built: repo={config.repo}, model={config.model}", flush=True)
 
-    print("[DEBUG] Creating orchestrator...", flush=True)
+    if debug:
+        print(
+            f"[DEBUG] Config built: repo={config.repo}, model={config.model}",
+            flush=True,
+        )
+        print("[DEBUG] Creating orchestrator...", flush=True)
+
     orchestrator = GitHubOrchestrator(
         project_dir=args.project,
         config=config,
         progress_callback=print_progress,
     )
-    print("[DEBUG] Orchestrator created", flush=True)
 
-    print(f"[DEBUG] Calling orchestrator.review_pr({args.pr_number})...", flush=True)
+    if debug:
+        print("[DEBUG] Orchestrator created", flush=True)
+        print(
+            f"[DEBUG] Calling orchestrator.review_pr({args.pr_number})...", flush=True
+        )
+
     result = await orchestrator.review_pr(args.pr_number)
-    print(f"[DEBUG] review_pr returned, success={result.success}", flush=True)
+
+    if debug:
+        print(f"[DEBUG] review_pr returned, success={result.success}", flush=True)
 
     if result.success:
         print(f"\n{'=' * 60}")
@@ -182,28 +240,38 @@ async def cmd_followup_review_pr(args) -> int:
     import sys
 
     # Force unbuffered output so Electron sees it in real-time
-    sys.stdout.reconfigure(line_buffering=True)
-    sys.stderr.reconfigure(line_buffering=True)
+    if hasattr(sys.stdout, "reconfigure"):
+        sys.stdout.reconfigure(line_buffering=True)
+    if hasattr(sys.stderr, "reconfigure"):
+        sys.stderr.reconfigure(line_buffering=True)
 
-    print(f"[DEBUG] Starting follow-up review for PR #{args.pr_number}", flush=True)
-    print(f"[DEBUG] Project directory: {args.project}", flush=True)
+    debug = os.environ.get("DEBUG")
+    if debug:
+        print(f"[DEBUG] Starting follow-up review for PR #{args.pr_number}", flush=True)
+        print(f"[DEBUG] Project directory: {args.project}", flush=True)
+        print("[DEBUG] Building config...", flush=True)
 
-    print("[DEBUG] Building config...", flush=True)
     config = get_config(args)
-    print(f"[DEBUG] Config built: repo={config.repo}, model={config.model}", flush=True)
 
-    print("[DEBUG] Creating orchestrator...", flush=True)
+    if debug:
+        print(
+            f"[DEBUG] Config built: repo={config.repo}, model={config.model}",
+            flush=True,
+        )
+        print("[DEBUG] Creating orchestrator...", flush=True)
+
     orchestrator = GitHubOrchestrator(
         project_dir=args.project,
         config=config,
         progress_callback=print_progress,
     )
-    print("[DEBUG] Orchestrator created", flush=True)
 
-    print(
-        f"[DEBUG] Calling orchestrator.followup_review_pr({args.pr_number})...",
-        flush=True,
-    )
+    if debug:
+        print("[DEBUG] Orchestrator created", flush=True)
+        print(
+            f"[DEBUG] Calling orchestrator.followup_review_pr({args.pr_number})...",
+            flush=True,
+        )
 
     try:
         result = await orchestrator.followup_review_pr(args.pr_number)
@@ -211,7 +279,10 @@ async def cmd_followup_review_pr(args) -> int:
         print(f"\nFollow-up review failed: {e}")
         return 1
 
-    print(f"[DEBUG] followup_review_pr returned, success={result.success}", flush=True)
+    if debug:
+        print(
+            f"[DEBUG] followup_review_pr returned, success={result.success}", flush=True
+        )
 
     if result.success:
         print(f"\n{'=' * 60}")
diff --git a/apps/backend/runners/github/services/orchestrator_reviewer.py b/apps/backend/runners/github/services/orchestrator_reviewer.py
index 32486977..ce64bbd0 100644
--- a/apps/backend/runners/github/services/orchestrator_reviewer.py
+++ b/apps/backend/runners/github/services/orchestrator_reviewer.py
@@ -628,7 +628,7 @@ class OrchestratorReviewer:
         )
 
         if prompt_file.exists():
-            base_prompt = prompt_file.read_text()
+            base_prompt = prompt_file.read_text(encoding="utf-8")
         else:
             logger.warning("Orchestrator prompt not found!")
             base_prompt = "You are a PR reviewer. Review the provided PR."
diff --git a/apps/backend/runners/github/services/pr_review_engine.py b/apps/backend/runners/github/services/pr_review_engine.py
index 38228d75..022834c6 100644
--- a/apps/backend/runners/github/services/pr_review_engine.py
+++ b/apps/backend/runners/github/services/pr_review_engine.py
@@ -476,7 +476,7 @@ class PRReviewEngine:
             / "pr_structural.md"
         )
         if prompt_file.exists():
-            prompt = prompt_file.read_text()
+            prompt = prompt_file.read_text(encoding="utf-8")
         else:
             prompt = self.prompt_manager.get_review_pass_prompt(ReviewPass.STRUCTURAL)
 
@@ -527,7 +527,7 @@ class PRReviewEngine:
             / "pr_ai_triage.md"
         )
         if prompt_file.exists():
-            prompt = prompt_file.read_text()
+            prompt = prompt_file.read_text(encoding="utf-8")
         else:
             prompt = self.prompt_manager.get_review_pass_prompt(
                 ReviewPass.AI_COMMENT_TRIAGE
diff --git a/apps/backend/runners/github/services/prompt_manager.py b/apps/backend/runners/github/services/prompt_manager.py
index 643528a5..da1c94ec 100644
--- a/apps/backend/runners/github/services/prompt_manager.py
+++ b/apps/backend/runners/github/services/prompt_manager.py
@@ -298,7 +298,7 @@ Output JSON array:
         """Get the main PR review prompt."""
         prompt_file = self.prompts_dir / "pr_reviewer.md"
         if prompt_file.exists():
-            return prompt_file.read_text()
+            return prompt_file.read_text(encoding="utf-8")
         return self._get_default_pr_review_prompt()
 
     def _get_default_pr_review_prompt(self) -> str:
@@ -338,7 +338,7 @@ Be specific and actionable. Focus on significant issues, not nitpicks.
         """Get the follow-up PR review prompt."""
         prompt_file = self.prompts_dir / "pr_followup.md"
         if prompt_file.exists():
-            return prompt_file.read_text()
+            return prompt_file.read_text(encoding="utf-8")
         return self._get_default_followup_review_prompt()
 
     def _get_default_followup_review_prompt(self) -> str:
@@ -380,7 +380,7 @@ Output JSON:
         """Get the issue triage prompt."""
         prompt_file = self.prompts_dir / "issue_triager.md"
         if prompt_file.exists():
-            return prompt_file.read_text()
+            return prompt_file.read_text(encoding="utf-8")
         return self._get_default_triage_prompt()
 
     def _get_default_triage_prompt(self) -> str:
diff --git a/apps/backend/runners/github/services/review_tools.py b/apps/backend/runners/github/services/review_tools.py
index 84e3ba9b..d36b0fd9 100644
--- a/apps/backend/runners/github/services/review_tools.py
+++ b/apps/backend/runners/github/services/review_tools.py
@@ -136,7 +136,7 @@ async def spawn_security_review(
             / "pr_security_agent.md"
         )
         if prompt_file.exists():
-            base_prompt = prompt_file.read_text()
+            base_prompt = prompt_file.read_text(encoding="utf-8")
         else:
             logger.warning("Security agent prompt not found, using fallback")
             base_prompt = _get_fallback_security_prompt()
@@ -222,7 +222,7 @@ async def spawn_quality_review(
             / "pr_quality_agent.md"
         )
         if prompt_file.exists():
-            base_prompt = prompt_file.read_text()
+            base_prompt = prompt_file.read_text(encoding="utf-8")
         else:
             logger.warning("Quality agent prompt not found, using fallback")
             base_prompt = _get_fallback_quality_prompt()
@@ -504,7 +504,7 @@ async def get_file_content(
     try:
         full_path = project_dir / file_path
         if full_path.exists():
-            return full_path.read_text()
+            return full_path.read_text(encoding="utf-8")
         return ""
     except Exception as e:
         logger.error(f"[Orchestrator] Failed to read {file_path}: {e}")
diff --git a/apps/frontend/package-lock.json b/apps/frontend/package-lock.json
index e5aa719d..6d443fd4 100644
--- a/apps/frontend/package-lock.json
+++ b/apps/frontend/package-lock.json
@@ -69,6 +69,7 @@
         "@types/uuid": "^10.0.0",
         "@vitejs/plugin-react": "^5.1.2",
         "autoprefixer": "^10.4.22",
+        "cross-env": "^10.1.0",
         "electron": "^39.2.7",
         "electron-builder": "^26.0.12",
         "electron-vite": "^5.0.0",
@@ -1101,6 +1102,13 @@
         "node": ">=14.14"
       }
     },
+    "node_modules/@epic-web/invariant": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/@epic-web/invariant/-/invariant-1.0.0.tgz",
+      "integrity": "sha512-lrTPqgvfFQtR/eY/qkIzp98OGdNJu0m5ji3q/nJI8v3SXkRKEnWiOxMmbvcSoAIzv/cGiuvRy57k4suKQSAdwA==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/@esbuild/aix-ppc64": {
       "version": "0.25.12",
       "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.25.12.tgz",
@@ -6215,6 +6223,24 @@
       "optional": true,
       "peer": true
     },
+    "node_modules/cross-env": {
+      "version": "10.1.0",
+      "resolved": "https://registry.npmjs.org/cross-env/-/cross-env-10.1.0.tgz",
+      "integrity": "sha512-GsYosgnACZTADcmEyJctkJIoqAhHjttw7RsFrVoJNXbsWWqaq6Ym+7kZjq6mS45O0jij6vtiReppKQEtqWy6Dw==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@epic-web/invariant": "^1.0.0",
+        "cross-spawn": "^7.0.6"
+      },
+      "bin": {
+        "cross-env": "dist/bin/cross-env.js",
+        "cross-env-shell": "dist/bin/cross-env-shell.js"
+      },
+      "engines": {
+        "node": ">=20"
+      }
+    },
     "node_modules/cross-spawn": {
       "version": "7.0.6",
       "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz",
diff --git a/apps/frontend/package.json b/apps/frontend/package.json
index e988c7f9..6424f361 100644
--- a/apps/frontend/package.json
+++ b/apps/frontend/package.json
@@ -21,7 +21,7 @@
   "scripts": {
     "postinstall": "node scripts/postinstall.cjs",
     "dev": "electron-vite dev",
-    "dev:debug": "DEBUG=true electron-vite dev",
+    "dev:debug": "cross-env DEBUG=true electron-vite dev",
     "dev:mcp": "electron-vite dev -- --remote-debugging-port=9222",
     "build": "electron-vite build",
     "start": "electron .",
@@ -107,6 +107,7 @@
     "@types/uuid": "^10.0.0",
     "@vitejs/plugin-react": "^5.1.2",
     "autoprefixer": "^10.4.22",
+    "cross-env": "^10.1.0",
     "electron": "^39.2.7",
     "electron-builder": "^26.0.12",
     "electron-vite": "^5.0.0",
diff --git a/apps/frontend/src/main/ipc-handlers/github/utils/subprocess-runner.ts b/apps/frontend/src/main/ipc-handlers/github/utils/subprocess-runner.ts
index dc82ccae..f53f4170 100644
--- a/apps/frontend/src/main/ipc-handlers/github/utils/subprocess-runner.ts
+++ b/apps/frontend/src/main/ipc-handlers/github/utils/subprocess-runner.ts
@@ -59,7 +59,9 @@ export function runPythonSubprocess<T = unknown>(
   // This is safe because: (1) user must explicitly enable via npm run dev:debug,
   // (2) it only enables our internal debug logging, not third-party framework debugging,
   // (3) no sensitive values are logged - only LLM reasoning and response text.
-  const safeEnvVars = ['PATH', 'HOME', 'USER', 'SHELL', 'LANG', 'LC_ALL', 'TERM', 'TMPDIR', 'TMP', 'TEMP', 'DEBUG'];
+  // Include platform-specific vars needed for shell commands and CLI tools
+  // Windows: SYSTEMROOT, COMSPEC, PATHEXT, WINDIR for shell; USERPROFILE, APPDATA, LOCALAPPDATA for gh CLI auth
+  const safeEnvVars = ['PATH', 'HOME', 'USER', 'SHELL', 'LANG', 'LC_ALL', 'TERM', 'TMPDIR', 'TMP', 'TEMP', 'DEBUG', 'SYSTEMROOT', 'COMSPEC', 'PATHEXT', 'WINDIR', 'USERPROFILE', 'APPDATA', 'LOCALAPPDATA', 'HOMEDRIVE', 'HOMEPATH'];
   const filteredEnv: Record<string, string> = {};
   for (const key of safeEnvVars) {
     if (process.env[key]) {