I don't have a full strategy, but I have an idea for a data-gathering experiment:

I hand you a coin and try to get you to put it in the box for me. If you refuse, I update in the direction of the box harming people who put coins in it. If you comply, I watch and see what happens.

I have never posted on LW before, but this seems like a fine first time to do so.

I am really very curious to see the results of the real world cooperate/defect choice at the bottom of the test.