ml-feedback-ladder

ml-feedback-ladder is a skill for Claude Code from pengzhangzhi/superpowers-ml. It costs 40 tokens per session (1,233 once invoked), scanned A, original, MIT.

A staged checking plan for a machine-learning experiment. It orders checks from cheap local sanity tests to the full study, with each stage required before spending more time or computing resources.

In plain words
What is it for?
Use it when planning how to verify one ML experiment. It helps define what each check tests, what evidence proves it passed, and when to continue or stop.
Why use it?
Ordinary software tests may only show that an ML code path runs; they do not prove the method works. Early gates help find errors before expensive GPU or cluster jobs.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the superpowers-ml plugin — 17 skills, 1 hook shipped together

Good fit Use it when planning how to verify one ML experiment. It helps define what each check tests, what evidence proves it passed, and when to continue or stop.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pengzhangzhi/superpowers-ml/ml-feedback-ladder
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 pengzhangzhi/superpowers-ml --skill ml-feedback-ladder
Clone the repo
git clone --depth 1 https://github.com/pengzhangzhi/superpowers-ml

Made for: Claude Code.

Or install superpowers-ml, the plugin that ships this one along with the rest of its 17 skills, 1 hook.

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 ml-feedback-ladder

README.md
[![agentmods](https://agentmods.dev/badge/skills/pengzhangzhi/superpowers-ml/ml-feedback-ladder/github.svg)](https://agentmods.dev/skills/pengzhangzhi/superpowers-ml/ml-feedback-ladder)
Your own site
<a href="https://agentmods.dev/skills/pengzhangzhi/superpowers-ml/ml-feedback-ladder"><img src="https://agentmods.dev/badge/skills/pengzhangzhi/superpowers-ml/ml-feedback-ladder/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 ml-feedback-ladder

Your own site · 80×15
<a href="https://agentmods.dev/skills/pengzhangzhi/superpowers-ml/ml-feedback-ladder"><img src="https://agentmods.dev/badge/skills/pengzhangzhi/superpowers-ml/ml-feedback-ladder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,233 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.01233
Opus 5 $0.00020 $0.00616
Sonnet 5 $0.00008 $0.00247
Haiku 4.5 $0.00004 $0.00123

Measured 11d ago against content hash 9c10e43727ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ml-feedback-ladder 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 11d 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-feedback-ladder/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ML Feedback Ladder

Overview

In normal software, a passing test suite can mean the code works. In ML research, passing tests only show the code PATH might run - they do NOT show the method works. You need STAGED EMPIRICAL verification, ordered cheapest-to-expensive, where every cheap check GATES the expensive cluster/GPU jobs below it.

This skill OWNS the canonical ladder. Design the rungs for ONE specific experiment with your human partner before launching anything.

Core principle: Cheap checks gate expensive jobs. Never spend a slow rung to find a bug a fast rung would have caught.

Upstream: the experiment, metric, and protocol come from superpowers-ml:ml-experiment-design. Downstream: the ladder you design here becomes verification steps in superpowers-ml:writing-plans, and the final rung hands off to superpowers-ml:ml-result-review.

The Ladder

Each rung names what it CHECKS, the ARTIFACT that proves it passed, and rough COST. Cost is relative - a rung is "expensive" if it consumes a scheduled GPU/cluster job.

Rung Checks Proof artifact Cost
R0 Experiment card / protocol defined: question, locked primary metric, baseline, decision rule The experiment card itself minutes, no compute
R1 Code / import / config / static sanity: it imports, config parses, paths resolve, seeds set Clean import + config dump + linter seconds, dev node
R2 Shape / dtype / device / one-batch forward+backward: loss is finite, gradients flow Logged shapes/dtypes/device + one non-NaN loss + non-zero grads seconds-minutes, dev node
R3 Tiny overfit: a handful of examples driven to ~zero loss (or memorized) Loss curve collapsing to near-zero on the tiny set minutes, dev node / 1 GPU
R4 Real launcher smoke run: the ACTUAL launch path (local GPU or cluster smoke job) starts, checkpoints, logs, resumes - on tiny data/steps Launcher exits 0, checkpoint written, logs/metrics emitted one short job
R5 Short pilot / early signal: real data, real config, truncated budget; metric is moving the right way and is stable Early metric curve vs. baseline on the locked metric a fraction of a full run
R6 Full run / full study: the locked protocol at full budget, seeds/sweeps as specified Complete metrics across all planned seeds/conditions the expensive job(s)
R7 Result review / decision memo: compare to baseline under the locked primary metric, decide Decision memo (handed to superpowers-ml:ml-result-review) analysis time

Read the full file on GitHub · 72 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.

  1. 11d ago First seen · 72 lines · 40 tokens per session scan A 9c10e43727ef

Subscribe to this mod's changes

ml-feedback-ladder is a skill published in the GitHub repository pengzhangzhi/superpowers-ml (8 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 1,233 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 2026-08-31.

Related

Other skills, from other repositories

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…

NVIDIA/physicsnemo · 124 tokens

pysr

Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.

astroautomata/PySR · 61 tokens

cellxgene-census-query

Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…

PharMolix/OpenBioMed · 105 tokens

ml-mlip-nvalchemi

GPU-accelerated batched inference for MACE, MatGL (TensorNet/M3GNet/CHGNet), and FairChem MLIPs using NValchemi, enabling parallel static, relax, and MD workflows across multiple structures simultaneously.

learningmatter-mit/AtomisticSkills · 59 tokens

ml-committee-uncertainty

Quantify prediction uncertainty of MACE MLIPs using committee (ensemble) models; flag high-uncertainty structures for DFT verification.

learningmatter-mit/AtomisticSkills · 36 tokens

ml-mace-finetune

Fine-tune MACE machine learning interatomic potentials on custom datasets.

learningmatter-mit/AtomisticSkills · 21 tokens