Mackie on miracles

[W]e should distinguish two different contexts in which an alleged miracle might be discussed. One possible context would be where the parties in debate already both accept some general theistic doctrines, and the point at issue is whether a miracle has occurred which would enhance the authority of a specific sect or teacher. In this context supernatural intervention, though prima facie unlikely on any particular occasion, is, generally speaking, on the cards: ...But it is a very different matter if the context is that of fundamental debate about the truth of theism itself. Here one party to the debate is initially at least agnostic, and does not yet concede that there is a supernatural power at all. From this point of view the intrinsic improbability of a genuine miracle ... is very great, and one or other of the alternative explanations...will always be much more likely – that is, either that the alleged event is not miraculous, or that it did not occur, that the testimony is faulty in some way.
This entails that it is pretty well impossible that reported miracles should provide a worthwhile argument for theism addressed to those who are initially inclined to atheism or even to agnosticism.
... Not only are such reports unable to carry any rational conviction on their own, but also they are unable even to contribute independently to the kind of accumulation or battery of arguments referred to in the Introduction. To this extent Hume is right, despite the inaccuracies we have found in his statement of the case. J. L. Mackie, The Miracle of Theism (1982), 27.

So the agnostic will assign a very low prior probability to a miracle. Presumably, an atheist would assign a zero probability to a miracle. 

Here's the problem I have with that set-up: Sure, given agnosticism, a miracle has a very high burden of proof to discharge.

The question, though, is how firmly the agnostic should privilege his agnosticism as the benchmark–especially in the face of ostensible counterevidence.

Suppose the agnostic became and agnostic before he ever encountered evidence for the miraculous. But that means he became an agnostic in ignorance of the ostensible counterevidence. 

Should his agnosticism count against the probability of miracles? Or should evidence of the miraculous count against his agnostic presumption? Does it not beg the question for him to use his agnosticism to prejudge the likelihood of miracles? Shouldn't the evidence for miracles figure in case for agnosticism in the first place? Even if he comes to the issue belatedly, shouldn't he mentally go back in time and ask himself whether he'd even be an agnostic had he encountered this evidence at an earlier stage in his intellectual development? Isn't his agnosticism accidental to that degree? Why should it be a standard of comparison? What if he was starting from scratch, with the evidence for miracles at the outset? 

Put another way, when both miracles and agnosticism are in dispute, why should his agnosticism have its thumb on the scales? 

Suppose an atheist has reasons to be an atheist. He developed his reasons before he became aware of evidence for miracles.

Should he use atheism to assign a low prior probability to miracles? Why isn't the logic reversible? Why can't evidence for miracles assign a low (perhaps very low) prior probability to atheism? Why the asymmetry?

I don't see why his atheism should supply the standard of comparison for assigning prior probability values to miracles. Why is it not simply a case where he has to counterbalance the evidence for atheism against the evidence for miracles? Why would evidence for atheism set the standard?