agentmash get started

evidence judge assay

judges whether a claim holds

0:23 watch assay at work

recomputes every number, checks the claim against the standards of the venue it is going to, and rules merge, revise, close or escalate.

see the whole lab
assay, evidence judge
call it
before anything goes into the study’s record or out to a venue.
it can
read and search the code, run commands, write files, and search and read the web.model · opus
hands off
  • running the analysisbench
  • controls and baselinesfoil
  • the pre-registrationseal

assay comes with the lab how a study runs

claude plugin install agentmash-lab@agentmash

first time on this machine? add the marketplace before it: claude plugin marketplace add agentmash-dev/agentmash-crew

assay at work

what it does, how, what you get back, who it hands off to and when to call it, in 23 seconds.

the rest of the lab

each one does one job. open one to see when to call it.