experiment-rigor

experiment-rigor is a skill for Codex from theam/limina. It costs 80 tokens per session (1,980 once invoked), scanned A, original, Apache-2.0.

A research workflow for designing, reviewing, and interpreting experiments. It covers hypotheses, datasets, comparison methods, measurements, stopping rules, and whether findings are conclusive.

In plain words
What is it for?
It is for defining experiments, choosing baselines, checking metrics and test cases, and deciding whether positive or negative results support a conclusion.
Why use it?
It helps separate evidence about a method from results caused by an unfair comparison, weak setup, or insufficient data.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit It is for defining experiments, choosing baselines, checking metrics and test cases, and deciding whether positive or negative results support a conclusion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/theam/limina/experiment-rigor
View source ↗ theam/limina
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add theam/limina --skill experiment-rigor
Clone the repo
git clone --depth 1 https://github.com/theam/limina

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for experiment-rigor

README.md
[![agentmods](https://agentmods.dev/badge/skills/theam/limina/experiment-rigor.svg)](https://agentmods.dev/skills/theam/limina/experiment-rigor)
Your own site
<a href="https://agentmods.dev/skills/theam/limina/experiment-rigor"><img src="https://agentmods.dev/badge/skills/theam/limina/experiment-rigor.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,980 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.01980
Opus 5 $0.00040 $0.00990
Sonnet 5 $0.00016 $0.00396
Haiku 4.5 $0.00008 $0.00198

Measured 7d ago against content hash 82a80a1123ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

experiment-rigor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/experiment-rigor/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experiment Rigor

Use this skill to turn Limina research into decision-grade evidence.

When to use it

Use this skill when you need to:

  • write or revise a serious H, E, or F
  • define a fair comparator baseline
  • decide whether a result is conclusive, inconclusive, or invalid
  • choose metrics, guardrails, slices, seeds, or stopping rules
  • review whether a negative result reflects the method or only the setup

Do not use it for:

  • generic brainstorming with no concrete research decision
  • one-off coding tasks with no experiment design component
  • literature mapping when the main gap is external landscape search rather than experiment validity

Read first

Read:

  • kb/mission/CHALLENGE.md
  • kb/ACTIVE.md
  • only the linked H, E, F, L, CR, or SR notes relevant to the current question

Before evaluating any nontrivial method, read the official paper, repo, or docs for that method. Record the setup requirements needed to expose its claimed advantage.

Use the reference files on demand:

  • references/hypothesis-rubric.md — writing or revising H
  • references/experiment-rubric.md — designing or reviewing E
  • references/metrics-storage.md — storing raw metrics and lineage under kb/research/data/

Non-negotiable rules

  1. Optimize for decisive evidence. If an experiment cannot change a decision, redesign it.
  2. Protect method validity. Never test a method in a setup that strips away the capability you are trying to evaluate.
  3. Compare fairly. Use strong baselines and control non-essential variables.
  4. Separate invalid test, implementation failure, insufficient signal, and true negative result.
  5. Reject a hypothesis only after a method-valid test with enough signal. Otherwise mark it inconclusive and design the next experiment.
  6. Keep kb/ as canonical memory. Narrative belongs in H/E/F; raw metrics belong in structured files under kb/research/data/.
  7. Use the current Limina templates and keep ## Links valid. Prefer python3 scripts/kb_new_artifact.py ... when a new core artifact is needed.
  8. Use CR or SR only when the direction is blocked, invalidated, plateaued, or strategically changing. Do not trigger them on a fixed cadence.

Read the full file on GitHub · 180 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 180 lines · 80 tokens per session scan A 82a80a1123ae

Subscribe to this mod's changes

experiment-rigor is a skill published in the GitHub repository theam/limina (39 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,980 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

sn-search-academic

An academic research tool for finding papers and encyclopedia entries, reading papers in full or by section, and tracing references and citations. It supports structured literature research.

OpenSenseNova/SenseNova-Skills · 31 tokens

paper-revision-author

Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.

opensquilla/opensquilla · 24 tokens

imaging-data-commons

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

synthetic-sciences/openscience · 62 tokens

clinical-decision-support

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…

synthetic-sciences/openscience · 97 tokens

immunology-assays

Computational analysis of immunology experimental data. ATAC-seq differential accessibility, immune cell tracking from microscopy, ELISA data processing with 4-parameter logistic fitting, immunohistochemistry quantification, antibody titer analysis, and cell cycle phase duration estimation. For flow cytometry use…

synthetic-sciences/openscience · 79 tokens

molecular-cloning

Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.

synthetic-sciences/openscience · 70 tokens