auto-experiment

auto-experiment is a skill for Codex from Xiangyue-Zhang/auto-deep-researcher-24x7. It costs 20 tokens per session (1,597 once invoked), scanned A, original, Apache-2.0.

An automated loop for running deep-learning experiments on a GPU project. It reads the project brief and past results, plans and tests code changes, starts training, reviews the results, and repeats.

In plain words
What is it for?
Use it to try research hypotheses, run GPU training jobs, monitor their progress, and decide whether to continue, change direction, or report findings.
Why use it?
It removes the need to manually plan, launch, monitor, and record each experiment. The saved logs and memory keep the work connected across cycles.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; positional $N argument; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/my_project/workspace.

Good fit Use it to try research hypotheses, run GPU training jobs, monitor their progress, and decide whether to continue, change direction, or report findings.

Compare 6 skills from other repositories ↓
About the project

Auto Deep Researcher 24x7 is an autonomous AI agent that runs and monitors deep learning experiments continuously. Researchers use it to automate experiment execution, including hyperparameter tuning and GPU or Slurm-based workloads. The catalogue add-ons provide agents, skills, and instructions for operating the experiment workflow.

Xiangyue-Zhang/auto-deep-researcher-24x7 · 1,291 stars · on GitHub · arxiv.org

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Codex.

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 auto-experiment

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiangyue-zhang/auto-deep-researcher-24x7/auto-experiment/github.svg)](https://agentmods.dev/skills/xiangyue-zhang/auto-deep-researcher-24x7/auto-experiment)
Your own site
<a href="https://agentmods.dev/skills/xiangyue-zhang/auto-deep-researcher-24x7/auto-experiment"><img src="https://agentmods.dev/badge/skills/xiangyue-zhang/auto-deep-researcher-24x7/auto-experiment/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 auto-experiment

Your own site · 80×15
<a href="https://agentmods.dev/skills/xiangyue-zhang/auto-deep-researcher-24x7/auto-experiment"><img src="https://agentmods.dev/badge/skills/xiangyue-zhang/auto-deep-researcher-24x7/auto-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,597 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 $0.00020 $0.01597
Opus 5 $0.00010 $0.00798
Sonnet 5 $0.00004 $0.00319
Haiku 4.5 $0.00002 $0.00160

Measured 13d ago against content hash 28bdf2fe05f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

auto-experiment 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.

skills/auto-experiment/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

auto-experiment

Launch an autonomous experiment agent that runs your deep learning experiments 24/7.

What This Does

This skill starts a THINK → EXECUTE → REFLECT loop that:

  1. Reads your PROJECT_BRIEF.md to understand the research goal
  2. Analyzes previous results in MEMORY_LOG.md
  3. Plans the next experiment (hypothesis + success criteria)
  4. Implements code changes and runs a mandatory dry-run
  5. Launches GPU training via nohup (tracks PID)
  6. Monitors at zero LLM cost (only kill -0 PID + tail log + nvidia-smi)
  7. Wakes up when training finishes to analyze results
  8. Updates memory and decides: iterate, pivot, or report
  9. Repeats

Usage

Claude Code: /auto-experiment
Claude Code: /auto-experiment --project /path/to/my_project --gpu 0
Claude Code: /auto-experiment --project . --max-cycles 5
Codex: $auto-experiment

Prerequisites

The project directory must contain:

PROJECT_BRIEF.md (required)

A frozen reference describing your research goal. Example:

# Goal
Train a ViT-B/16 on ImageNet to reach 78%+ top-1 accuracy.

# Codebase
- Training: train.py
- Config: configs/vit_base.yaml
- Data: /data/imagenet/

# Constraints
- GPU 0-3 available (use DDP)
- Max 90 epochs per run
- Report val accuracy after each run

# Current Best
- ResNet-50 baseline: 76.1%

config.yaml (optional)

Override default agent settings:

agent:
  provider: "anthropic"    # or "openai" / "claude_cli" / "codex_cli"
  model: "claude-sonnet-4-6"
  base_url: ""             # optional compatible endpoint override
  api_key_env: ""          # optional custom key env var
  auth_token_env: ""       # optional custom bearer token env var
  max_cycles: -1          # -1 = unlimited
  max_steps_per_cycle: 3  # max sub-agent dispatches per cycle
  cooldown_interval: 300  # 5 min smart polling

memory:
  brief_max_chars: 3000
  log_max_chars: 2000

monitor:
  poll_interval: 900      # check every 15 min during training
  zero_llm: true

experiment:
  mandatory_dry_run: true

Read the full file on GitHub · 177 lines

Files

What ships with it

1 file 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. 13d ago First seen · 177 lines · 20 tokens per session scan A 28bdf2fe05f6

Subscribe to this mod's changes

auto-experiment is a skill published in the GitHub repository Xiangyue-Zhang/auto-deep-researcher-24x7 (1,291 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,597 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.

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

torch-geometric

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.

synthetic-sciences/openscience · 41 tokens

esm

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…

synthetic-sciences/openscience · 86 tokens

structure-prediction

Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.

synthetic-sciences/openscience · 42 tokens

ai-research-reproduction

Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted…

lllllllama/RigorPilot-Skills · 136 tokens

single-cell-multi-omics-analysis-scvi

Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…

PharMolix/OpenBioMed · 94 tokens