cpu 8086
        bits 16
        org 256

start:
        jmp init

        align 4
int21old:
        dd 0

int21handler:
        jmp far [cs:int21old]

end_of_resident:

init:
        mov ax, 3521h
        int 21h
        mov word [int21old + 2], es
        mov word [int21old], bx

        mov ax, 2521h
        mov dx, int21handler
        int 21h

        mov ax, 3100h
        mov dx, (end_of_resident - start + 256 + 15) >> 4
        int 21h