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 EvoClaw/amplify --skill reproducibility-driven-researchgit clone --depth 1 https://github.com/EvoClaw/amplifyWrote 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/evoclaw/amplify/reproducibility-driven-research)<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>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 | $0.00046 | $0.01032 |
| Opus 5 | $0.00023 | $0.00516 |
| Sonnet 5 | $0.00009 | $0.00206 |
| Haiku 4.5 | $0.00005 | $0.00103 |
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.
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.
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.
- 7d ago First seen · 110 lines · 46 tokens per session scan A dee0aa4d1f75
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.
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…
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…
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.
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.
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.
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.