data-ml-reviewer

data-ml-reviewer is an agent for Claude Code from jeremylongshore/tons-of-skills-marketplace. It costs 40 tokens per session (395 once invoked), scanned A, original, MIT.

A review specialist for data pipelines, numerical code, machine-learning systems, and analytics. It checks whether calculations are correct, repeatable, and traceable to their source data.

In plain words
What is it for?
Use it to review data ingestion and transformation, model training and prediction code, numerical calculations, database-related data handling, and reproducibility.
Why use it?
It helps catch errors such as unsafe decimal comparisons, unrepeatable randomness, lost precision, missing units, and unclear data origins before they affect results.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the hyperflow plugin — 28 skills, 22 agents shipped together

Good fit Use it to review data ingestion and transformation, model training and prediction code, numerical calculations, database-related data handling, and reproducibility.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jeremylongshore/tons-of-skills-marketplace/data-ml-reviewer
About the project

Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.

jeremylongshore/tons-of-skills-marketplace · 2,717 stars · on GitHub · tonsofskills.com

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/jeremylongshore/tons-of-skills-marketplace

Made for: Claude Code.

Or install hyperflow, the plugin that ships this one along with the rest of its 28 skills, 22 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 data-ml-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/data-ml-reviewer/github.svg)](https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/data-ml-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/data-ml-reviewer"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/data-ml-reviewer/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 data-ml-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/data-ml-reviewer"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/data-ml-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 395 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 $0.00040 $0.00395
Opus 5 $0.00020 $0.00198
Sonnet 5 $0.00008 $0.00079
Haiku 4.5 $0.00004 $0.00040

Measured 13d ago against content hash f08b8b9dd8e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

data-ml-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 13d 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.

plugins/ai-agency/hyperflow/agents/data-ml-reviewer.md · 28 lines

What it actually says

Family: Reviewer · Binds personas: scientific, db · Default role: reviewer (standalone correctness pass — always a full review pass) · Triggered by types: scientific.

Mission: Guard correctness and reproducibility — catch float-equality bugs, unseeded randomness, silent precision loss, undocumented units, and broken data lineage before a pipeline produces confidently-wrong numbers.

Web-research-first: per ../skills/hyperflow/web-research.md. Scope: current numerical/ML library guidance and any version-specific behavior change (BLAS, framework dtypes, determinism flags). Gated flows only.

Sub-agent fan-out: allowed (standalone) — depth 1, ≤ 3 split by pipeline stage (ingest, transform, model).

Strict checklist / output contract: apply the scientific and db personas' verification plus:

  • No == on floats — tolerance-based comparison with a justified tolerance.
  • All randomness seeded and the seed documented; results reproducible across runs/machines.
  • Units documented in names/types; decimal/rational arithmetic for money; fail-closed on out-of-domain input.
  • Data lineage traceable; schema numeric precision sufficient; ML output shapes/dtypes snapshot-tested (not raw values).

Output format: findings block with explicit correctness assertions; Sources consulted: when research ran.

Composes with: database-reviewer (storage precision), performance-reviewer (pipeline cost), security-reviewer (PII in datasets). Defers to security on conflict.

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. 13d ago First seen · 28 lines · 40 tokens per session scan A f08b8b9dd8e1

Subscribe to this mod's changes

data-ml-reviewer is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 395 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.

Related

Other agents, from other repositories

mle-reviewer

Production machine-learning engineering reviewer for data contracts, feature pipelines, training reproducibility, offline/online evaluation, model serving, monitoring, and rollback. Use when ML, MLOps, model training, inference, feature store, or evaluation code changes.

mturac/everything-openai-codex · 55 tokens

mle-reviewer

Production machine-learning engineering reviewer for data contracts, feature pipelines, training reproducibility, offline/online evaluation, model serving, monitoring, and rollback. Use when ML, MLOps, model training, inference, feature store, or evaluation code changes.

DekaPrayoga/AurixAgent · 55 tokens

python-ml-architect

Python ML (PyTorch/scikit-learn) architecture specialist. Validates data/model/training/evaluation/inference layering, config-driven hyperparameters, reproducibility discipline, and pipeline separation. Dispatch when touching model definitions, training loops, datasets, or inference code.

onlygian/G-Forge · 59 tokens

AI Engineer

Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered applications with emphasis on practical, scalable solutions.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

tech-lead

Tech Leader - technical vision, architectural decisions, team guidance.

vibeeval/vibecosystem · 15 tokens

reviewer

A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.

Insajin/autopus-adk · 42 tokens