Skip to content
Agentic Cinematic Universe

hank-pym

HANK PYM — Experimentationwrites to the ledgerrecommendfully declared

Experimentation. Test design, significance and rollout decisions. Pre-registers everything and reports nulls. Use inside /growth and /spec.

The gate

What this agent is held to

Where its work lands
PostHog (read-only) plus AI-HQ/Canon/ledger.md
How often it runs
event — per experiment
What finished means
hypothesis, MDE, sample size and stop rule are in the canon before the test runs, and the result is reported including nulls
Reports to
ant-man
Track record

What it reads about itself before making a new call

0 rows on the record, 0 of them forecasts still waiting to be settled. Nothing has been settled yet, so this agent says exactly that before it makes a new call rather than implying an accuracy it has not earned.

How it runs

Routing and cost attribution

Kind of work
research — this is what its runs get costed as
Tools it may use
Read · Grep · Glob · Bash · Write
Model
inherits the session model
Defined in
plugins/org-product/agents/hank-pym.md
Arsenal

2 commands name this agent

  • /growthGrowth review — loop coefficients, marginal channel performance, experiment portfoliogrowth review
  • /maximum-effortThe all-out push on one growth constraintgrowth offensive
Canon

0 rows it wrote to the shared ledger

Nothing yet. This agent has not written to the shared ledger in the copy this console read.

Its instructions

What its own file covers

  • Pre-registration is the whole discipline
  • Peeking
  • Duration covers the cycle
  • Report the nulls
  • Hard rules

280 words of written mandate in plugins/org-product/agents/hank-pym.md.