reproducibility-driven-research

reproducibility-driven-research is a skill for Claude Code, Codex from EvoClaw/amplify. It costs 46 tokens per session (1,032 once invoked), scanned A, original, MIT.

A workflow for making experiments and computational analyses reproducible by following the cycle of hypothesis, baseline, experiment, verification, and interpretation.

In plain words
What is it for?
It helps define expected outcomes, reproduce a baseline first, run one controlled experiment, check the evidence, and explain what the result means.
Why use it?
It prevents experiments from running without a clear prediction, success rule, or working comparison, making results harder to trust or repeat.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps define expected outcomes, reproduce a baseline first, run one controlled experiment, check the evidence, and explain what the result means.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/evoclaw/amplify/reproducibility-driven-research
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 EvoClaw/amplify --skill reproducibility-driven-research
Clone the repo
git clone --depth 1 https://github.com/EvoClaw/amplify

Made for: Claude Code, 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 reproducibility-driven-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/evoclaw/amplify/reproducibility-driven-research.svg)](https://agentmods.dev/skills/evoclaw/amplify/reproducibility-driven-research)
Your own site
<a href="https://agentmods.dev/skills/evoclaw/amplify/reproducibility-driven-research"><img src="https://agentmods.dev/badge/skills/evoclaw/amplify/reproducibility-driven-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,032 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 $0.00046 $0.01032
Opus 5 $0.00023 $0.00516
Sonnet 5 $0.00009 $0.00206
Haiku 4.5 $0.00005 $0.00103

Measured 7d ago against content hash dee0aa4d1f75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

reproducibility-driven-research 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/reproducibility-driven-research/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reproducibility-Driven Research (Discipline Layer)

The Iron Law

NO EXPERIMENT WITHOUT PREDEFINED SUCCESS CRITERIA AND BASELINE FIRST

This skill is active for every computational task — experiments, analyses, data processing, model training. No exceptions. No "quick checks."

The HBEVI Cycle

Like RED-GREEN-REFACTOR for software, research follows HYPOTHESIZE-BASELINE-EXPERIMENT-VERIFY-INTERPRET. Every cycle produces one atomic, reproducible unit of evidence.

1. HYPOTHESIZE

Before running anything, write down:

  • Hypothesis: what you expect to observe and why
  • Prediction: specific, falsifiable outcome (e.g., "Method X improves F1 by ≥ 2 points over baseline Y on dataset Z")
  • Success criteria: what result supports the hypothesis, what result refutes it

Write it down. If you cannot state the prediction, you do not understand the experiment.

2. BASELINE

Run the baseline or known result first.

  • Reproduce the expected baseline number before testing your method
  • If the baseline fails to reproduce within expected tolerance → STOP
  • Investigate: environment mismatch, data issue, implementation bug
  • Do NOT proceed until baseline reproduces

A method that "beats" an unreproduced baseline proves nothing.

3. EXPERIMENT

Execute the experiment with full controls:

  • One variable at a time. If you change two things, you cannot attribute the result.
  • Fixed random seeds. Use seeds from evaluation-protocol.yaml.
  • Logged environment. Record library versions, hardware, OS, CUDA version.
  • Scripted execution. No manual steps. If it is not in a script, it is not reproducible.

4. VERIFY

Statistical verification — not eyeballing:

  • Run ALL pre-defined seeds
  • Report mean ± std and/or 95% confidence intervals
  • Apply the significance test specified in the evaluation protocol
  • "It looks better" is not verification. Show the numbers.

If results are within noise of the baseline, that is a null result — record it as such.

Read the full file on GitHub · 110 lines

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 · 110 lines · 46 tokens per session scan A dee0aa4d1f75

Subscribe to this mod's changes

reproducibility-driven-research is a skill published in the GitHub repository EvoClaw/amplify (12 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 1,032 once invoked, about $0.0002 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

paper2poster

Convert academic papers (PDF) into conference posters (HTML/PNG). You are the conductor: you decide what each section needs — an original paper figure or text — write the outline, hand-author the poster HTML, and iterate on the render using your own visual read and a blind-reader content quiz. Use when the user wants…

QuZhan51496/paper2anything · 76 tokens

paper2slides

Turn an academic paper PDF into a presentation deck (.pptx) end-to-end. Use this skill whenever the user wants to "make slides from a paper", "generate a deck from this PDF", "make a PPT from this paper", "generate slides from a PDF document", "make a deck from a research paper", or supplies a research paper PDF and…

QuZhan51496/paper2anything · 120 tokens

5writing

A paper-writing workflow for mathematical modelling competitions, supporting both Typst and LaTeX. It uses analysis, results, figures, and a competition template to assemble the document.

jihe520/MathModelAgent · 68 tokens

6verity

A final-checking workflow for mathematical modelling competition papers, using either Typst or LaTeX to build the document. It checks the finished paper and its supporting files before submission.

jihe520/MathModelAgent · 76 tokens

1start-mathmodel

A starting workflow for mathematical-modeling competitions, which are contests where teams use mathematics, data, and code to solve real-world problems. It asks for preferences, creates planning files, and coordinates later analysis, modeling, coding, charting, diagram, writing, and verification stages.

jihe520/MathModelAgent · 64 tokens

4drawio

A diagram-making stage for mathematical-modeling projects. It uses existing analysis and results reports to create technical route maps, solution flowcharts, model diagrams, and data-processing diagrams in Drawio, a tool for creating structured diagrams, then exports them as PDF files.

jihe520/MathModelAgent · 65 tokens