SpamAssassin Rulesets - add in rules by Jennifer Wheeler.  Kudos to Adam Lopresto and my SARE buddies. 

backhair.cf  (1.6 : 2004-04-05) --[words obfuscated by nonsense html tags]  Y<oivugriub>ou cou<iuqgheriugv9h>ld rea<y>lly u<owiuer88>se this.

chickenpox.cf (1.18 : 2004-04-05) --[words obfuscated by non word characters] Th1s |s a v3ry h4ndy se7 t0 c@tch th!s 50rt 0f (rap.

mangled.cf  (1.60 : 2004-06-04) --[Set of obfu/gappy words. exclusions allow for higher scores to bump up sleeper spam.]

weeds.cf  (1.1 : 2004-04-05) --[looks for Alpha decimal/hex encoding, lower and uppercase. Use this or Weeds 2, not both]

weeds_2.cf  (1.1 : 2004-04-05) --[same as the above Weeds set, but more limiting. this set is "safer", though I find the above set safe for my tastes. Use this or Weeds, not both]

The only set I would be caution you with is mangled.  If you're conservative, pull out all the rules for smaller words (4 letter words or less) and, as with any rule you didn't write, score based on your setup.  Set them low, see how they hit, and adjust accordingly.  Actually...  what I should have said is, read through the words it's looking for.  Pull out the words you don't want included in the overall set.  Be aware smaller words can sometimes fp, so drop their score lower, or pull 'em out if you're a real chicken.  I expect these to hit a bit in ham, but the idea is, there isn't enough other junk in the ham to make the entire message FP...  just juggle like you do everything else.  The reason I made this set is for very generic well written spam that sometimes needed a real good nudge to get it over the top.