replicate

replicate is a command for coding agents from Marazii/research-co-pilot. It costs 14 tokens per session (294 once invoked), scanned A, original, MIT.

A process for planning a careful replication of an existing research study. Replication means repeating a study to see whether its findings hold under the same or deliberately changed conditions.

In plain words
What is it for?
Designing direct, close, conceptual, generalization, or robustness replications, including sample-size and preregistration plans.
Why use it?
It makes differences from the original study explicit and defines in advance how success will be judged.

Command

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

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.

agentmods
npx agentmods add commands/marazii/research-co-pilot/replicate
Clone the repo
git clone --depth 1 https://github.com/Marazii/research-co-pilot

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 replicate

README.md
[![agentmods](https://agentmods.dev/badge/commands/marazii/research-co-pilot/replicate.svg)](https://agentmods.dev/commands/marazii/research-co-pilot/replicate)
Your own site
<a href="https://agentmods.dev/commands/marazii/research-co-pilot/replicate"><img src="https://agentmods.dev/badge/commands/marazii/research-co-pilot/replicate.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00294
Opus 5 $0.00007 $0.00147
Sonnet 5 $0.00003 $0.00059
Haiku 4.5 $0.00001 $0.00029

Measured 4d ago against content hash 6ba97656efcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

replicate 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 4d 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.

commands/replicate.md · 24 lines

What it actually says

Invoke the replication-designer skill from the research-co-pilot plugin and execute its full workflow.

The skill file is at skills/replication-designer/SKILL.md relative to this plugin. Read it and follow it precisely — including:

  • Phase 1: Intake (target study, replication type — direct / close / conceptual / generalization / robustness — constraints, goal).
  • Phase 2: Extract the original design into a structured spec.
  • Phase 3: Decide what to hold equivalent vs update; document each deviation.
  • Phase 4: Sample size for adequate replication power (often 2-3x the original).
  • Phase 5: Pre-registration plan (OSF, AsPredicted, ClinicalTrials.gov).
  • Phase 6: Multi-site logistics if applicable.
  • Phase 7: Pre-specify replication-success criterion (significance + effect-size CI overlap + meta-analytic synthesis + equivalence test).
  • Phase 8: Output replication_design_<short_title>.md.

Frame as "estimate the effect honestly," not "prove it wrong."

User input: $ARGUMENTS

If no target study was given, ask for the citation / DOI / path to the paper and the replication intent.

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. 4d ago First seen · 24 lines · 14 tokens per session scan A 6ba97656efcc

Subscribe to this mod's changes

replicate is a command published in the GitHub repository Marazii/research-co-pilot (13 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 294 once invoked, about $0.0001 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.