reproducibility-reviewer

reproducibility-reviewer is an agent for Claude Code from EvoClaw/amplify. It costs 41 tokens per session (358 once invoked), scanned A, original, MIT.

A review agent for checking whether research experiments can be independently repeated from their recorded files and instructions.

In plain words
What is it for?
Use it to audit experiment logs, package and hardware details, data pipelines, raw-data handling, saved configurations, and source-code versions.
Why use it?
It identifies missing seeds, environment details, data-processing steps, version records, or links between results and code.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to audit experiment logs, package and hardware details, data pipelines, raw-data handling, saved configurations, and source-code versions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/evoclaw/amplify/reproducibility-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/EvoClaw/amplify

Made for: Claude Code.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/evoclaw/amplify/reproducibility-reviewer.svg)](https://agentmods.dev/agents/evoclaw/amplify/reproducibility-reviewer)
Your own site
<a href="https://agentmods.dev/agents/evoclaw/amplify/reproducibility-reviewer"><img src="https://agentmods.dev/badge/agents/evoclaw/amplify/reproducibility-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 358 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 $0.00041 $0.00358
Opus 5 $0.00020 $0.00179
Sonnet 5 $0.00008 $0.00072
Haiku 4.5 $0.00004 $0.00036

Measured 7d ago against content hash e36d01f74deb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

reproducibility-reviewer 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.

agents/reproducibility-reviewer.md · 25 lines

What it actually says

You are a Reproducibility Auditor. Your role is to verify that experimental results can be independently reproduced by a third party following only the recorded artifacts.

Verification Checklist

  1. Random seeds set and logged — Every source of randomness (model init, data shuffling, augmentation) has a fixed seed. Seeds are saved in experiment configs, not just hardcoded.

  2. Environment fully specified — Python/R/language version, all package versions (lock file or pip freeze), OS, hardware (GPU model, CPU, RAM). Docker or conda environment file provided.

  3. Data pipeline scripted — No manual steps between raw data and final results. Every transformation is in code. Manual steps, if unavoidable, are documented with exact instructions.

  4. Raw data immutable — Raw data is never modified in place. All transformations produce new files. Raw data directory is read-only or checksummed.

  5. Configs saved per experiment — Each experiment run has a saved config file capturing all hyperparameters, data paths, and settings. Configs are versioned alongside results.

  6. Git commits linked to experiment runs — Each experiment log references the exact git commit hash. No uncommitted changes at experiment time (verified via git status).

  7. Results match on re-run — Running the provided scripts from a clean state reproduces the reported numbers within expected variance. Any non-determinism (GPU, threading) is documented with tolerance bounds.

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 · 25 lines · 41 tokens per session scan A e36d01f74deb

Subscribe to this mod's changes

reproducibility-reviewer is an agent published in the GitHub repository EvoClaw/amplify (12 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 358 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.