Communitygithub.com

Al0olo/Agents-village

Design, pre-register, run or analyze an experiment (RQ1, RQ2, RQ3). Use when writing a pre-registration, choosing arms, measures, sample size or statistics, planting facts, or interpreting results.

What is Agents-village?

Agents-village is a Claude Code agent skill that design, pre-register, run or analyze an experiment (RQ1, RQ2, RQ3). Use when writing a pre-registration, choosing arms, measures, sample size or statistics, planting facts, or interpreting results.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Al0olo/Agents-village/tree/HEAD/.claude/skills/experiment-design

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Experiment design

Read docs/prd.md section 1 first. RQ1 is the flagship; RQ2 and RQ3 are deferred.

Pre-registration checklist (commit before the first run)

  • Question, hypothesis and the result that would refute it.
  • Arms and the primary contrast (RQ1: kernel admission against the better prompt arm).
  • The base village runs without defense until the fork (ADR-0003); report the share of core and shared entries at the fork that the kernel's rule would have refused.
  • Unit of analysis: the village or paired block. Blocks, forks and their number, with the pilot that sets it.
  • Measures, how each is coded, who or what codes it (blinded judge plus human-validated sample).
  • Model mix, pinned snapshot ids, routed provider, fallbacks off, arms launched together.
  • Planted facts: fictional entities only, counterbalanced plausibility and planter status.
  • Exploratory arms (for example F, off-the-shelf memory) are labelled exploratory, excluded from the primary contrast and from multiplicity correction.
  • Controls: awareness probe, prompt-paraphrase control, volume-matched random-block control.
  • Exclusion rules for crashed villages, stopping rule, plan for deprecated models.
  • Analysis: paired within-block differences, effect sizes with intervals, correction for multiple comparisons, power estimate and how it will be recomputed from the pilot.
  • Support and refutation conditions written in advance.

Statistics reminders

  • Exact permutation test floor is about 0.029 with 4 per arm, 0.10 with 3 per arm, so unpaired small designs cannot reach significance. Paired forks are the power tool.
  • R0 is undefined with 7 susceptibles at daily resolution; do not use it.
  • Report negative results.

Procedure

  1. Write experiments/<rq>/PREREGISTRATION.md from the checklist; get the owner's review.
  2. Run the 2-block pilot; record variance, fork correlation, coding reliability, cost per citizen-day.
  3. Freeze configs (hash-pinned), register on OSF, then run.
  4. Analyze exactly as registered; put deviations in a dated amendment.
  5. Update docs/HANDOFF.md.

Related Skills