experiment-pipeline

experiment-pipeline is a skill for Claude Code from AI4Scientist/nano-scientist. It costs 129 tokens per session (3,709 once invoked), scanned A, original, no licence file.

A four-stage workflow for carrying out machine-learning experiments, from reproducing a baseline to testing a new method and its individual parts.

In plain words
What is it for?
Use it for baseline reproduction, parameter tuning, proposed-method testing, and ablation studies, with support for saved prior strategies.
Why use it?
It provides checkpoints and limits for each stage, helping prevent tuning or validation from becoming unstructured.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it for baseline reproduction, parameter tuning, proposed-method testing, and ablation studies, with support for saved prior strategies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ai4scientist/nano-scientist/experiment-pipeline
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 AI4Scientist/nano-scientist --skill experiment-pipeline
Clone the repo
git clone --depth 1 https://github.com/AI4Scientist/nano-scientist

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 experiment-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai4scientist/nano-scientist/experiment-pipeline/github.svg)](https://agentmods.dev/skills/ai4scientist/nano-scientist/experiment-pipeline)
Your own site
<a href="https://agentmods.dev/skills/ai4scientist/nano-scientist/experiment-pipeline"><img src="https://agentmods.dev/badge/skills/ai4scientist/nano-scientist/experiment-pipeline/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 experiment-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai4scientist/nano-scientist/experiment-pipeline"><img src="https://agentmods.dev/badge/skills/ai4scientist/nano-scientist/experiment-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,709 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 unknown 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 $0.00129 $0.03709
Opus 5 $0.00064 $0.01854
Sonnet 5 $0.00026 $0.00742
Haiku 4.5 $0.00013 $0.00371

Measured 11d ago against content hash 8ef64425246d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

experiment-pipeline 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/experiment-pipeline/SKILL.md · 260 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 260 lines · 129 tokens per session scan A 8ef64425246d

Subscribe to this mod's changes

experiment-pipeline is a skill published in the GitHub repository AI4Scientist/nano-scientist (127 stars, last pushed 3mo ago), with no licence file. It adds 129 tokens to every session and 3,709 once invoked, about $0.0006 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 skills, from other repositories

pyvene-interventions

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

OpenLAIR/dr-claw · 46 tokens

nnsight-remote-interpretability

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

OpenLAIR/dr-claw · 59 tokens

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

OpenLAIR/dr-claw · 58 tokens

transformer-lens-interpretability

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

OpenLAIR/dr-claw · 52 tokens

inno-experiment-dev

Creates implementation plan, writes project code with judge feedback loop, and submits final experiment run. Use after code-survey in both Idea and Plan branches.

OpenLAIR/dr-claw · 36 tokens

mamba-architecture

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (dstate=16) and Mamba-2 (dstate=128, multi-head). Models 130M-2.8B on HuggingFace.

OpenLAIR/dr-claw · 81 tokens