Add Python cache files to .gitignore

This adds a workaround for issue #12172 where the Write tool ignores
umask and creates files with hardcoded 0600 permissions.

The hook:
- Runs after Write/Edit tool operations
- Detects files with restrictive 0600 permissions
- Applies umask-respecting permissions (e.g., 0644 with umask 022)
- Includes comprehensive test suite with 15 test cases

Users can configure this hook in their settings to fix file permissions
until the underlying issue in the Write tool is resolved.

.gitignore

@@ -1,2 +1,3 @@
 .DS_Store
-
+__pycache__/
+*.pyc

CHANGELOG.md

@@ -1,28 +1,5 @@
 # Changelog
 
-## 2.0.72
-
-- Added Claude in Chrome (Beta) feature that works with the Chrome extension (https://claude.ai/chrome) to let you control your browser directly from Claude Code
-- Reduced terminal flickering
-- Added scannable QR code to mobile app tip for quick app downloads
-- Added loading indicator when resuming conversations for better feedback
-- Fixed `/context` command not respecting custom system prompts in non-interactive mode
-- Fixed order of consecutive Ctrl+K lines when pasting with Ctrl+Y
-- Improved @ mention file suggestion speed (~3x faster in git repositories)
-- Improved file suggestion performance in repos with `.ignore` or `.rgignore` files
-- Improved settings validation errors to be more prominent
-- Changed thinking toggle from Tab to Alt+T to avoid accidental triggers
-
-## 2.0.71
-
-- Added /config toggle to enable/disable prompt suggestions
-- Added `/settings` as an alias for the `/config` command
-- Fixed @ file reference suggestions incorrectly triggering when cursor is in the middle of a path
-- Fixed MCP servers from `.mcp.json` not loading when using `--dangerously-skip-permissions`
-- Fixed permission rules incorrectly rejecting valid bash commands containing shell glob patterns (e.g., `ls *.txt`, `for f in *.png`)
-- Bedrock: Environment variable `ANTHROPIC_BEDROCK_BASE_URL` is now respected for token counting and inference profile listing
-- New syntax highlighting engine for native build
-
 ## 2.0.70
 
 - Added Enter key to accept and submit prompt suggestions immediately (tab still accepts for editing)

examples/hooks/fix_file_permissions_example.py

@@ -0,0 +1,163 @@
+#!/usr/bin/env python3
+"""
+Claude Code Hook: Fix File Permissions After Write
+===================================================
+This hook runs as a PostToolUse hook for the Write and Edit tools.
+It fixes file permissions to respect the system's umask setting.
+
+This addresses the issue where Claude Code's Write tool creates files with
+restrictive 0600 permissions, ignoring the user's umask setting.
+
+Read more about hooks here: https://docs.anthropic.com/en/docs/claude-code/hooks
+
+Configuration example for ~/.claude/settings.json or .claude/settings.local.json:
+
+{
+  "hooks": {
+    "PostToolUse": [
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "python3 /path/to/claude-code/examples/hooks/fix_file_permissions_example.py"
+          }
+        ]
+      }
+    ]
+  }
+}
+
+How it works:
+- After Write or Edit tool completes, this hook runs
+- Gets the file path from the tool input
+- Calculates the correct permissions based on the current umask
+- Applies the umask-respecting permissions to the file
+
+For example:
+- With umask 022: files become 0644 (rw-r--r--)
+- With umask 002: files become 0664 (rw-rw-r--)
+- With umask 077: files remain 0600 (rw-------)
+"""
+
+import json
+import os
+import stat
+import sys
+
+
+def get_umask() -> int:
+    """Get the current umask value.
+
+    We temporarily set umask to get the current value, then restore it.
+    This is the standard way to read umask in Python.
+    """
+    current_umask = os.umask(0)
+    os.umask(current_umask)
+    return current_umask
+
+
+def calculate_file_permissions(umask_value: int) -> int:
+    """Calculate file permissions based on umask.
+
+    Standard Unix behavior: new files start with 0666 base permissions,
+    then umask is applied to remove bits.
+
+    Args:
+        umask_value: The current umask value (e.g., 0o022)
+
+    Returns:
+        The file permissions after applying umask (e.g., 0o644)
+    """
+    base_permissions = 0o666  # rw-rw-rw-
+    return base_permissions & ~umask_value
+
+
+def fix_file_permissions(file_path: str) -> dict:
+    """Fix permissions for a file to respect umask.
+
+    Args:
+        file_path: Path to the file to fix
+
+    Returns:
+        Dict with status information
+    """
+    if not file_path:
+        return {"status": "skipped", "reason": "no file path provided"}
+
+    if not os.path.exists(file_path):
+        return {"status": "skipped", "reason": "file does not exist"}
+
+    if not os.path.isfile(file_path):
+        return {"status": "skipped", "reason": "path is not a file"}
+
+    try:
+        # Get current permissions
+        current_mode = stat.S_IMODE(os.stat(file_path).st_mode)
+
+        # Calculate expected permissions based on umask
+        umask_value = get_umask()
+        expected_mode = calculate_file_permissions(umask_value)
+
+        # Only change if current permissions are more restrictive than expected
+        # This handles the case where Write tool sets 0600 instead of umask-based perms
+        if current_mode == 0o600 and expected_mode != 0o600:
+            os.chmod(file_path, expected_mode)
+            return {
+                "status": "fixed",
+                "file": file_path,
+                "old_mode": oct(current_mode),
+                "new_mode": oct(expected_mode),
+                "umask": oct(umask_value),
+            }
+        else:
+            return {
+                "status": "unchanged",
+                "file": file_path,
+                "current_mode": oct(current_mode),
+                "expected_mode": oct(expected_mode),
+            }
+
+    except PermissionError as e:
+        return {"status": "error", "reason": f"permission denied: {e}"}
+    except OSError as e:
+        return {"status": "error", "reason": f"OS error: {e}"}
+
+
+def main():
+    """Main entry point for the PostToolUse hook."""
+    try:
+        input_data = json.load(sys.stdin)
+    except json.JSONDecodeError as e:
+        # Exit 0 - don't block on invalid input, just log to stderr
+        print(f"Warning: Invalid JSON input: {e}", file=sys.stderr)
+        sys.exit(0)
+
+    tool_name = input_data.get("tool_name", "")
+
+    # Only process Write and Edit tools
+    if tool_name not in ("Write", "Edit"):
+        sys.exit(0)
+
+    tool_input = input_data.get("tool_input", {})
+    file_path = tool_input.get("file_path", "")
+
+    if not file_path:
+        sys.exit(0)
+
+    result = fix_file_permissions(file_path)
+
+    # Output result as JSON for logging/debugging
+    # This will appear in the transcript when running with --debug
+    if result.get("status") == "fixed":
+        output = {
+            "systemMessage": f"Fixed file permissions for {file_path}: {result['old_mode']} -> {result['new_mode']} (umask: {result['umask']})"
+        }
+        print(json.dumps(output))
+
+    # Always exit 0 - this is a PostToolUse hook, we don't want to block
+    sys.exit(0)
+
+
+if __name__ == "__main__":
+    main()

examples/hooks/test_fix_file_permissions.py

@@ -0,0 +1,278 @@
+#!/usr/bin/env python3
+"""
+Tests for the fix_file_permissions_example.py hook.
+
+Run these tests with:
+    python3 examples/hooks/test_fix_file_permissions.py
+
+Or with pytest:
+    pytest examples/hooks/test_fix_file_permissions.py -v
+"""
+
+import json
+import os
+import stat
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+# Path to the hook script
+HOOK_SCRIPT = Path(__file__).parent / "fix_file_permissions_example.py"
+
+
+class TestFixFilePermissionsHook(unittest.TestCase):
+    """Test cases for the file permissions fix hook."""
+
+    def setUp(self):
+        """Set up test fixtures."""
+        self.temp_dir = tempfile.mkdtemp()
+        self.test_file = os.path.join(self.temp_dir, "test_file.txt")
+
+    def tearDown(self):
+        """Clean up test files."""
+        if os.path.exists(self.test_file):
+            os.remove(self.test_file)
+        if os.path.exists(self.temp_dir):
+            os.rmdir(self.temp_dir)
+
+    def run_hook(self, tool_name: str, file_path: str) -> subprocess.CompletedProcess:
+        """Run the hook script with given input."""
+        input_data = {
+            "tool_name": tool_name,
+            "tool_input": {"file_path": file_path},
+            "session_id": "test-session",
+            "cwd": os.getcwd(),
+        }
+
+        result = subprocess.run(
+            [sys.executable, str(HOOK_SCRIPT)],
+            input=json.dumps(input_data),
+            capture_output=True,
+            text=True,
+        )
+        return result
+
+    def create_file_with_permissions(self, path: str, mode: int) -> None:
+        """Create a test file with specific permissions."""
+        with open(path, "w") as f:
+            f.write("test content")
+        os.chmod(path, mode)
+
+    def get_file_permissions(self, path: str) -> int:
+        """Get the permission bits of a file."""
+        return stat.S_IMODE(os.stat(path).st_mode)
+
+    def test_fixes_restrictive_permissions_with_umask_022(self):
+        """Test that 0600 permissions are fixed to 0644 with umask 022."""
+        # Save and set umask
+        old_umask = os.umask(0o022)
+        try:
+            # Create file with restrictive permissions (simulating Write tool bug)
+            self.create_file_with_permissions(self.test_file, 0o600)
+            self.assertEqual(self.get_file_permissions(self.test_file), 0o600)
+
+            # Run the hook
+            result = self.run_hook("Write", self.test_file)
+            self.assertEqual(result.returncode, 0)
+
+            # Check permissions were fixed
+            expected_mode = 0o644  # 0666 & ~0022
+            self.assertEqual(
+                self.get_file_permissions(self.test_file),
+                expected_mode,
+                f"Expected {oct(expected_mode)}, got {oct(self.get_file_permissions(self.test_file))}",
+            )
+        finally:
+            os.umask(old_umask)
+
+    def test_fixes_restrictive_permissions_with_umask_002(self):
+        """Test that 0600 permissions are fixed to 0664 with umask 002."""
+        # Save and set umask
+        old_umask = os.umask(0o002)
+        try:
+            # Create file with restrictive permissions
+            self.create_file_with_permissions(self.test_file, 0o600)
+            self.assertEqual(self.get_file_permissions(self.test_file), 0o600)
+
+            # Run the hook
+            result = self.run_hook("Write", self.test_file)
+            self.assertEqual(result.returncode, 0)
+
+            # Check permissions were fixed
+            expected_mode = 0o664  # 0666 & ~0002
+            self.assertEqual(
+                self.get_file_permissions(self.test_file),
+                expected_mode,
+                f"Expected {oct(expected_mode)}, got {oct(self.get_file_permissions(self.test_file))}",
+            )
+        finally:
+            os.umask(old_umask)
+
+    def test_preserves_permissions_matching_umask(self):
+        """Test that permissions already matching umask are not changed."""
+        old_umask = os.umask(0o022)
+        try:
+            # Create file with correct permissions already
+            self.create_file_with_permissions(self.test_file, 0o644)
+
+            # Run the hook
+            result = self.run_hook("Write", self.test_file)
+            self.assertEqual(result.returncode, 0)
+
+            # Permissions should be unchanged
+            self.assertEqual(self.get_file_permissions(self.test_file), 0o644)
+        finally:
+            os.umask(old_umask)
+
+    def test_respects_umask_077(self):
+        """Test that umask 077 results in 0600 (no change needed)."""
+        old_umask = os.umask(0o077)
+        try:
+            # Create file with 0600 permissions
+            self.create_file_with_permissions(self.test_file, 0o600)
+
+            # Run the hook
+            result = self.run_hook("Write", self.test_file)
+            self.assertEqual(result.returncode, 0)
+
+            # With umask 077, 0600 is correct - should remain unchanged
+            self.assertEqual(self.get_file_permissions(self.test_file), 0o600)
+        finally:
+            os.umask(old_umask)
+
+    def test_handles_edit_tool(self):
+        """Test that the hook also works for the Edit tool."""
+        old_umask = os.umask(0o022)
+        try:
+            self.create_file_with_permissions(self.test_file, 0o600)
+
+            result = self.run_hook("Edit", self.test_file)
+            self.assertEqual(result.returncode, 0)
+
+            self.assertEqual(self.get_file_permissions(self.test_file), 0o644)
+        finally:
+            os.umask(old_umask)
+
+    def test_ignores_other_tools(self):
+        """Test that the hook ignores non-Write/Edit tools."""
+        old_umask = os.umask(0o022)
+        try:
+            self.create_file_with_permissions(self.test_file, 0o600)
+
+            result = self.run_hook("Read", self.test_file)
+            self.assertEqual(result.returncode, 0)
+
+            # Permissions should be unchanged for Read tool
+            self.assertEqual(self.get_file_permissions(self.test_file), 0o600)
+        finally:
+            os.umask(old_umask)
+
+    def test_handles_nonexistent_file(self):
+        """Test that the hook handles non-existent files gracefully."""
+        result = self.run_hook("Write", "/nonexistent/path/file.txt")
+        self.assertEqual(result.returncode, 0)
+
+    def test_handles_empty_file_path(self):
+        """Test that the hook handles empty file path gracefully."""
+        input_data = {
+            "tool_name": "Write",
+            "tool_input": {},
+            "session_id": "test-session",
+        }
+
+        result = subprocess.run(
+            [sys.executable, str(HOOK_SCRIPT)],
+            input=json.dumps(input_data),
+            capture_output=True,
+            text=True,
+        )
+        self.assertEqual(result.returncode, 0)
+
+    def test_handles_invalid_json(self):
+        """Test that the hook handles invalid JSON input gracefully."""
+        result = subprocess.run(
+            [sys.executable, str(HOOK_SCRIPT)],
+            input="not valid json",
+            capture_output=True,
+            text=True,
+        )
+        # Should exit 0 even with invalid input (don't block the workflow)
+        self.assertEqual(result.returncode, 0)
+        self.assertIn("Invalid JSON", result.stderr)
+
+    def test_handles_directory_path(self):
+        """Test that the hook ignores directory paths."""
+        result = self.run_hook("Write", self.temp_dir)
+        self.assertEqual(result.returncode, 0)
+
+    def test_outputs_system_message_on_fix(self):
+        """Test that the hook outputs a systemMessage when fixing permissions."""
+        old_umask = os.umask(0o022)
+        try:
+            self.create_file_with_permissions(self.test_file, 0o600)
+
+            result = self.run_hook("Write", self.test_file)
+            self.assertEqual(result.returncode, 0)
+
+            # Check that stdout contains the systemMessage JSON
+            if result.stdout.strip():
+                output = json.loads(result.stdout)
+                self.assertIn("systemMessage", output)
+                self.assertIn("Fixed file permissions", output["systemMessage"])
+        finally:
+            os.umask(old_umask)
+
+
+class TestCalculateFilePermissions(unittest.TestCase):
+    """Test the calculate_file_permissions function directly."""
+
+    def test_umask_022(self):
+        """Test permission calculation with umask 022."""
+        # Import the function from the hook script
+        import importlib.util
+
+        spec = importlib.util.spec_from_file_location("hook", HOOK_SCRIPT)
+        hook = importlib.util.module_from_spec(spec)
+        spec.loader.exec_module(hook)
+
+        result = hook.calculate_file_permissions(0o022)
+        self.assertEqual(result, 0o644)
+
+    def test_umask_002(self):
+        """Test permission calculation with umask 002."""
+        import importlib.util
+
+        spec = importlib.util.spec_from_file_location("hook", HOOK_SCRIPT)
+        hook = importlib.util.module_from_spec(spec)
+        spec.loader.exec_module(hook)
+
+        result = hook.calculate_file_permissions(0o002)
+        self.assertEqual(result, 0o664)
+
+    def test_umask_077(self):
+        """Test permission calculation with umask 077."""
+        import importlib.util
+
+        spec = importlib.util.spec_from_file_location("hook", HOOK_SCRIPT)
+        hook = importlib.util.module_from_spec(spec)
+        spec.loader.exec_module(hook)
+
+        result = hook.calculate_file_permissions(0o077)
+        self.assertEqual(result, 0o600)
+
+    def test_umask_000(self):
+        """Test permission calculation with umask 000."""
+        import importlib.util
+
+        spec = importlib.util.spec_from_file_location("hook", HOOK_SCRIPT)
+        hook = importlib.util.module_from_spec(spec)
+        spec.loader.exec_module(hook)
+
+        result = hook.calculate_file_permissions(0o000)
+        self.assertEqual(result, 0o666)
+
+
+if __name__ == "__main__":
+    unittest.main()

plugins/code-review/commands/code-review.md

@@ -1,5 +1,5 @@
 ---
-allowed-tools: Bash(gh issue view:*), Bash(gh search:*), Bash(gh issue list:*), Bash(gh pr comment:*), Bash(gh pr diff:*), Bash(gh pr view:*), Bash(gh pr list:*), mcp__github_inline_comment__create_inline_comment
+allowed-tools: Bash(gh issue view:*), Bash(gh search:*), Bash(gh issue list:*), Bash(gh pr comment:*), Bash(gh pr diff:*), Bash(gh pr view:*), Bash(gh pr list:*)
 description: Code review a pull request
 ---
 
@@ -11,7 +11,7 @@ To do this, follow these steps precisely:
    - The pull request is closed
    - The pull request is a draft
    - The pull request does not need code review (e.g. automated PR, trivial change that is obviously correct)
-   - Claude has already commented on this PR (check `gh pr view <PR> --comments` for comments left by claude)
+   - You have already submitted a code review on this pull request
 
    If any condition is true, stop and do not proceed.
 
@@ -52,34 +52,15 @@ Note: Still review Claude generated PR's.
 
 6. Filter out any issues that were not validated in step 5. This step will give us our list of high signal issues for our review.
 
-7. Post summary comment FIRST using `gh pr comment` (if `--comment` argument is provided):
-   - Total number of issues found
-   - Brief one-line summary of each issue (no "Bug:" prefix)
-   - Or if no issues: "No issues found. Checked for bugs and CLAUDE.md compliance."
-
+7. Finally, output the review.
+   - If the `--comment` argument is provided, post the review as a comment on the pull request using `gh pr comment`
+   - Otherwise (default), output the review directly to the terminal for local viewing
    When writing your comment, follow these guidelines:
    a. Keep your output brief
    b. Avoid emojis
    c. Link and cite relevant code, files, and URLs for each issue
    d. When citing CLAUDE.md violations, you MUST quote the exact text from CLAUDE.md that is being violated (e.g., CLAUDE.md says: "Use snake_case for variable names")
 
-8. THEN post inline comments for each issue using `mcp__github_inline_comment__create_inline_comment`:
-   - `path`: the file path
-   - `line` (and `startLine` for ranges): select the buggy lines so the user sees them
-   - `body`: Brief description of the issue (no "Bug:" prefix). For small fixes (up to 5 lines changed), include a committable suggestion:
-     ```suggestion
-     corrected code here
-     ```
-     For larger fixes (6+ lines or structural changes), do NOT use suggestion blocks. Instead:
-     1. Describe what the issue is
-     2. Explain the suggested fix at a high level
-     3. Include a copyable prompt for Claude Code that the user can use to fix the issue, formatted as:
-        ```
-        Fix [file:line]: [brief description of issue and suggested fix]
-        ```
-
-   **IMPORTANT: Only post ONE comment per unique issue. Do not post duplicate comments.**
-
 Use this list when evaluating issues in Steps 4 and 5 (these are false positives, do NOT flag):
 
 - Pre-existing issues
@@ -114,8 +95,6 @@ Found 3 issues:
 
 <link to file and line with full sha1 + line range for context>
 
-<sub>If this code review was useful, please react with 👍. Otherwise, react with 👎.</sub>
-
 ---
 
 - Or, if you found no issues:
@@ -126,8 +105,6 @@ Found 3 issues:
 
 No issues found. Checked for bugs and CLAUDE.md compliance.
 
-<sub>If this code review was useful, please react with 👍. Otherwise, react with 👎.</sub>
-
 ---
 
 - When linking to code, follow the following format precisely, otherwise the Markdown preview won't render correctly: https://github.com/anthropics/claude-code/blob/c21d3c10bc8e898b7ac1a2d745bdc9bc4e423afe/package.json#L10-L15