A verification guide for machine-learning code, configuration, and mathematics. It checks proposed work against framework documentation and known configuration practices before costly training or deployment.

Use it to review ML plans and configurations, verify framework behaviour and hyperparameters, and support findings with documentation references.

It helps catch incorrect settings, imports, parameters, or calculations before they waste compute time or cause deployment problems.

ml-verify — Skill for Claude Code by Leeroo-AI

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.

Any agent

npx skills add Leeroo-AI/superml --skill ml-verify

Clone the repo

git clone --depth 1 https://github.com/Leeroo-AI/superml

Made for: Claude Code.

Or install superml, the plugin that ships this one along with the rest of its 7 skills, 1 agent, 1 hook, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/leeroo-ai/superml/ml-verify.svg)](https://agentmods.dev/skills/leeroo-ai/superml/ml-verify)

Your own site

<a href="https://agentmods.dev/skills/leeroo-ai/superml/ml-verify"><img src="https://agentmods.dev/badge/skills/leeroo-ai/superml/ml-verify.svg" alt="Measured on agentmods" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,964 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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.03964
Opus 5	$0.00015	$0.01982
Sonnet 5	$0.00006	$0.00793
Haiku 4.5	$0.00003	$0.00396

Measured 7d ago against content hash a3c0fc385ee2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ml-verify 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.

skills/ml-verify/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ML Verification

Catch mistakes before they waste GPU hours. Verify configs, code, and math against documented framework behavior.

Grounding

Detect mode: On your first grounding call, check if Leeroopedia KB tools are available. If they return results, use KB mode. If unavailable or auth fails, use Web mode.

KB mode: Call verify_code_math / query_hyperparameter_priors / review_plan. Cite as [PageID].

Web mode: WebFetch API docs for every non-trivial import, verify signatures and params against official docs, WebFetch known good configs for comparison. Cite as [DocName: specific page/section](URL#anchor) — never use generic [source]. The link text MUST name the document and section (e.g., [HF PEFT: LoRA Conceptual Guide](https://huggingface.co/docs/peft/main/en/conceptual_guides/lora)). Start response with: > Grounding: Web mode — citations from official docs.

Web mode URL registry:

HF PEFT LoRA guide: https://huggingface.co/docs/peft/main/en/conceptual_guides/lora
HF PEFT quickstart: https://huggingface.co/docs/peft/main/en/quicktour
HF Transformers TrainingArguments: https://huggingface.co/docs/transformers/main/en/main_classes/trainer#transformers.TrainingArguments
HF TRL SFTTrainer: https://huggingface.co/docs/trl/main/en/sft_trainer
HF TRL SFTConfig: https://huggingface.co/docs/trl/main/en/sft_trainer#trl.SFTConfig
DeepSpeed: https://www.deepspeed.ai/docs/config-json
vLLM: https://docs.vllm.ai
PyTorch: https://pytorch.org/docs/stable

The Iron Law

NO TRAINING RUN WITHOUT VERIFICATION FIRST

An hour of verification saves days of debugging failed runs. Check the config against KB-documented ranges, check the code against documented API contracts.

Phases

Phase 1: Check Against Documentation

KB mode:

Call the appropriate KB tools:

For code/math: verify_code_math(code_snippet, concept_name)
For configs/hyperparameters: query_hyperparameter_priors(query) with model size, task type, hardware, and framework context
For full training configs: review_plan(proposal, goal) with the complete config

Read the full file on GitHub · 199 lines

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.

7d ago First seen · 199 lines · 29 tokens per session scan A a3c0fc385ee2

Subscribe to this mod's changes

ml-verify is a skill published in the GitHub repository Leeroo-AI/superml (194 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 3,964 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.

Data and AI LLM Testing ai coding-agent-skills coding-agents ml plugin

dataset-evaluation

Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says "is my dataset okay", "evaluate my data", "check my training data", "I have my own data", or before starting any fine-tuning job. Detects file format, checks schema compliance against the selected model…

awslabs/agent-plugins · 93 tokens

pn-rag-evaluation

Evaluate retrieval-augmented generation pipelines — golden sets, automated metrics (incl. RAGAS-style), human rubrics, regression gates in CI. Use when building or changing RAG (chunks, embeddings, rerankers, prompts) and need quality proof, not vibes.

perniemann/pnCore · 62 tokens

evaluating-llms-harness

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

NousResearch/hermes-agent · 29 tokens

ml-verify