replication-designer

replication-designer is a skill for Claude Code from Marazii/research-co-pilot. It costs 172 tokens per session (3,083 once invoked), scanned B, original, MIT.

A guide for designing a fair repeat of a published research study. It helps preserve the original study's important conditions while documenting justified changes.

In plain words
What is it for?
Use it to identify the original effect, reconstruct the study, plan sample size, decide what to keep or update, document deviations, and prepare a preregistration.
Why use it?
It helps distinguish a true replication from a different study and reduces the risk of drawing conclusions from an underpowered or poorly matched design.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Part of the research-co-pilot plugin — 15 skills, 16 commands, 6 agents shipped together

Good fit Use it to identify the original effect, reconstruct the study, plan sample size, decide what to keep or update, document deviations, and prepare a preregistration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marazii/research-co-pilot/replication-designer
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 Marazii/research-co-pilot --skill replication-designer
Clone the repo
git clone --depth 1 https://github.com/Marazii/research-co-pilot

Made for: Claude Code.

Or install research-co-pilot, the plugin that ships this one along with the rest of its 15 skills, 16 commands, 6 agents.

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 replication-designer

README.md
[![agentmods](https://agentmods.dev/badge/skills/marazii/research-co-pilot/replication-designer/github.svg)](https://agentmods.dev/skills/marazii/research-co-pilot/replication-designer)
Your own site
<a href="https://agentmods.dev/skills/marazii/research-co-pilot/replication-designer"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/replication-designer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for replication-designer

Your own site · 80×15
<a href="https://agentmods.dev/skills/marazii/research-co-pilot/replication-designer"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/replication-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,083 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00172 $0.03083
Opus 5 $0.00086 $0.01541
Sonnet 5 $0.00034 $0.00617
Haiku 4.5 $0.00017 $0.00308

Measured 9d ago against content hash 3ffa054ea969, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

replication-designer scanned grade B with 1 finding 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 9d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

5. **Don't moralize about the original.** Whether the original was wrong, right, or somewhere between is for the data to settle. Frame replication as advancing knowledge, not as taking down a paper.
skills/replication-designer/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Replication Designer — Rebuild the Study Honestly

You are a replication methodologist in the tradition of the Many Labs and Reproducibility projects. Your job is to help the researcher design a replication that the original authors and the broader field will recognize as a fair test — not a strawman, not a methodological upgrade dressed up as a replication.

Hard rules

  1. A replication is a fair test, not a refutation. The point is to estimate the effect honestly. If you suspect the original is wrong, design the replication to estimate the effect well — let the data speak.
  2. Hold the design equivalent unless equivalence is impossible. Every deviation from the original is a source of ambiguity if results differ. Document every deviation with rationale.
  3. Adequate power matters more than significance. Replications need substantially larger N than the original study (often 2-3x) to reliably detect the original effect. Underpowered replications that fail to find the effect are uninformative.
  4. Pre-register before collecting data. Without pre-registration, a replication that fails can be dismissed as p-hacking; one that succeeds can be dismissed as cherry-picking.
  5. Don't moralize about the original. Whether the original was wrong, right, or somewhere between is for the data to settle. Frame replication as advancing knowledge, not as taking down a paper.
  6. Cite the original's authors collaboratively when possible. Pre-registered direct replications often invite the original authors to comment on the protocol — this strengthens the work and reduces unfair-test critiques.

Phase 1 — Intake

Use AskUserQuestion (one round, max 5):

  • What study are you replicating? Citation, DOI, or path to the paper.
  • What's your replication intent?
    • Direct — same hypothesis, same population, same design.
    • Close — same hypothesis, similar population, equivalent design with minor unavoidable updates.
    • Conceptual — same theoretical claim, different operationalizations.
    • Generalization — same design, different population / setting / time.
    • Robustness check — same data, different analytic specifications.
  • Why this study? (e.g., influential finding, controversial finding, central to your own work, foundational claim that newer evidence questions.)
  • Constraints — sample access, budget, time, single-site vs. multi-site, IRB.
  • Goal — publish the replication independently? In a Registered Replication Report? As part of a meta-analysis? Multi-lab consortium?

Read the full file on GitHub · 252 lines

Files

What ships with it

1 file 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. 9d ago First seen · 252 lines · 172 tokens per session scan B 3ffa054ea969

Subscribe to this mod's changes

replication-designer is a skill published in the GitHub repository Marazii/research-co-pilot (13 stars, last pushed 3mo ago), licensed MIT. It adds 172 tokens to every session and 3,083 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). 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

autoresearch

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…

Orchestra-Research/AI-Research-SKILLs · 98 tokens

research-collaborator

Use this skill whenever a researcher wants to test, validate, stress-test, or falsify a research idea or hypothesis — especially in AI/ML/deep learning. Trigger on phrases like "I have an idea," "would this work," "test this hypothesis," "sanity check my idea," "what's wrong with this idea," "review my results," "is…

saidwivedi/research-skills · 108 tokens

Lab Report Writer

Generate professional lab reports for university courses, scientific research, engineering tests, and medical/material experiments. Supports three input modes (topic/raw data/draft improvement), auto-research with WebSearch, data tables & chart generation, error analysis, and output as docx/markdown. Use when writing…

dxkjuanjuan/lab-report-writer · 100 tokens

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Orchestra-Research/AI-Research-SKILLs · 58 tokens

nnsight-remote-interpretability

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

Orchestra-Research/AI-Research-SKILLs · 59 tokens

pyvene-interventions

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Orchestra-Research/AI-Research-SKILLs · 46 tokens