Excellent! Average run length is 7.79 characters, and about 17 runs per frame. This means I can use efficient navigation with CR, LF, and BS. Let me implement a smarter strategy:

```json
{
  "analysis": "Average run length is 7.79 chars with ~17 runs per frame. I can use efficient 1-byte control characters (CR, LF, BS) instead of expensive escape sequences. The strategy: process rows in order, use CR+LF to advance lines, and BS to move left within a row.",
  "plan": "Implement a row-by-row strategy:\n1. Track current row/col\n2. For each run of changes, navigate efficiently using CR, LF, BS\n3. Only use escape sequences when absolutely necessary",
  "commands": [
    {
      "keystrokes": "cat > /app/termzip_ansi.py << 'ENDOFFILE'\n#!/usr/bin/env python3\nimport struct\nimport sys\n\ndef read_tza(filename):\n    with open(filename, 'rb') as f:\n        magic = f.read(4)\n        if magic != b'TZA1':\n            raise ValueError(f'Invalid magic: {magic}')\n        width, height = struct.unpack('<HH', f.read(4))\n        n_frames, max_bytes = struct.unpack('<II', f.read(8))\n        frames = []\n        for _ in range(n_frames):\n            frame_data = f.read(width * height)\n            frames.append(frame_data)\n        return width, height, n_frames, max_bytes, frames\n\ndef main():\n    if len(sys.argv) != 2:\n        sys.stderr.write(f'Usage: {sys.argv[0]} <frames.tza>\\n')\n        sys.exit(1)\n    \n    filename = sys.argv[1]\n    width, height, n_frames, max_bytes, frames = read_tza(filename)\n    \n    prev_frame = b' ' * (width * height)\n    output = bytearray()\n    \n    # Track cursor position (0-indexed for internal)\n    cur_row, cur_col = 0, 0\n    \n    def move_to(row, col):\n        nonlocal cur_row, cur_col, output\n        if row == cur_row and col == cur_col:\n            return\n        # Use efficient navigation\n        if row < cur_row:\n            # Moving up - use escape sequence\n            output.extend(f'\\x1b[{cur_row - row}A'.encode())\n        elif row > cur_row:\n            # Moving down - use LF\n            output.extend(b'\\n' * (row - cur_row))\n        cur_row = row\n        # Now handle column\n        if col == 0:\n            output.extend(b'\\r')\n        elif col < cur_col:\n            # Move left with BS\n            output.extend(b'\\b' * (cur_col - col))\n        elif col > cur_col:\n            # Move right - only use escape if worth it\n            if col - cur_col > 4:\n                output.extend(f'\\x1b[{col - cur_col}C'.encode())\n            else:\n                # Write spaces and backspace - actually don't do this, use escape\n                output.extend(f'\\x1b[{col - cur_col}C'.encode())\n        cur_col = col\n    \n    for frame in frames:\n        # Find runs of changes\n        for r in range(height):\n            row_start = r * width\n            c = 0\n            while c < width:\n                if prev_frame[row_start + c] != frame[row_start + c]:\n                    # Move to this position\n                    move_to(r, c)\n                    # Output consecutive changes\n                    while c < width and prev_frame[row_start + c] != frame[row_start + c]:\n                        output.append(frame[row_start + c])\n                        c += 1\n                        cur_col += 1\n                        if cur_col >= width:\n                            cur_col = 0\n                            cur_row += 1\n                else:\n                    c += 1\n        # Frame delimiter\n        output.append(0x1e)\n        prev_frame = frame\n    \n    sys.stdout.buffer.write(output)\n\nif __name__ == '__main__':\n    main()\nENDOFFILE\n",
      "duration": 0.5
    },
    {
      "keystrokes": "python3 /app/termzip_ansi.py /app/frames.tza | wc -c\n",
      "duration": 2.0
    }
  ]
}
```