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.
npx skills add Marazii/research-co-pilot --skill replication-designergit clone --depth 1 https://github.com/Marazii/research-co-pilotWrote 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.
[](https://agentmods.dev/skills/marazii/research-co-pilot/replication-designer)<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.
<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>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.
| Model | Per session | Once 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 |
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. 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
- 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.
- 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.
- 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.
- 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.
- 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.
- 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?
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.
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.
- 9d ago First seen · 252 lines · 172 tokens per session scan B 3ffa054ea969
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.
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…
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…
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…
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.
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.
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.