ai-scaling-laws

ai-scaling-laws is a skill for Codex from vasilyu1983/AI-Agents-public. It costs 42 tokens per session (4,023 once invoked), scanned A, original, MIT.

A guide to choosing the size of an AI model and the amount of training data it should use. It explains research-based rules connecting model parameters, training tokens, and computing capacity.

In plain words
What is it for?
Estimating model size, training-token budgets, compute allocation, and the tradeoff between training more data and keeping a larger model.
Why use it?
It helps avoid spending too much computing capacity on an oversized model or too little training data, or making the opposite tradeoff.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Good fit Estimating model size, training-token budgets, compute allocation, and the tradeoff between training more data and keeping a larger model.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vasilyu1983/ai-agents-public/ai-scaling-laws
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 vasilyu1983/AI-Agents-public --skill ai-scaling-laws
Clone the repo
git clone --depth 1 https://github.com/vasilyu1983/AI-Agents-public

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 ai-scaling-laws

README.md
[![agentmods](https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-scaling-laws/github.svg)](https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ai-scaling-laws)
Your own site
<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ai-scaling-laws"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-scaling-laws/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 ai-scaling-laws

Your own site · 80×15
<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ai-scaling-laws"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-scaling-laws.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,023 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 $0.00042 $0.04023
Opus 5 $0.00021 $0.02011
Sonnet 5 $0.00008 $0.00805
Haiku 4.5 $0.00004 $0.00402

Measured 13d ago against content hash c7c58f8f4c7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-scaling-laws 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.

frameworks/shared-skills/skills/ai-scaling-laws/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Scaling Laws — Compute-Optimal Sizing Skill

Functional reference for pre-training researchers and engineers who need to reason cold about compute, token, and parameter tradeoffs. Covers Kaplan et al. (2020), Chinchilla / Hoffmann et al. (2022), GPT-3 sizing, over-training for inference efficiency, and the mechanics of budget allocation for a from-scratch run.

This is a standard interview probe. Know the key ratios and be ready to work through a concrete sizing calculation without a lookup.

Quick Reference

Concept Formula / Heuristic Notes
Compute budget C ≈ 6 N D N = non-embedding params, D = training tokens; approximate, constant ≈6 accounts for forward + backward
Chinchilla-optimal ratio D ≈ 20 × N From Hoffmann et al. 2022; holds compute constant
Kaplan (2020) ratio D ≈ 1.7–2 × N (roughly) Pre-Chinchilla; model-heavy. Difference from Chinchilla is methodological (FLOP counting, warmup, optimizer tuning), not simply "wrong" — see post-Chinchilla ref
Optimal N given C N* ≈ (C / 120)^0.5 Approximate; from Chinchilla Table A3
Optimal D given C D* ≈ (C / 0.3)^0.5 Paired with above; verify against Hoffmann et al. Table A3 numbers
Over-training (Llama-style) D ≫ 20 × N Trades higher training loss for cheaper inference; standard for deployed open models. Llama 3 8B: 15T tokens ≈ 1,875 tok/param (dense example). Llama 4 (2025) is the current MoE example — apply the ratio to activated, not total, params
GPT-3 (175B) training tokens ~300B tokens 175B params × ~1.7 tok/param (Kaplan-era; undercooked by Chinchilla standard)
Chinchilla (70B) training tokens ~1.4T tokens 70B × 20; compute-matched to GPT-3 but smaller and more accurate
GPT-2 (124M) repro budget ≈1–3 B tokens minimum See worked example below
Published fit constants α≈0.336, β≈0.283 Corrected by Besiroglu et al. 2024 to α≈0.35, β≈0.37 — original fit had convergence/rounding errors

Read the full file on GitHub · 196 lines

Files

What ships with it

6 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. 13d ago First seen · 196 lines · 42 tokens per session scan A c7c58f8f4c7b

Subscribe to this mod's changes

ai-scaling-laws is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 10d ago), licensed MIT. It adds 42 tokens to every session and 4,023 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 skills, from other repositories

scvi-tools

Deep learning for single-cell analysis using scvi-tools. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome RNA+ATAC analysis with MultiVI, (5) spatial transcriptomics…

Shoko-official/Claude-Science-System-Prompts · 193 tokens

experiment-bridge

A workflow tool that turns a research experiment plan into implemented code, deployed runs on GPUs, and initial results. It connects planning, code review, execution, and result collection.

raja21068/AutoResearch · 74 tokens

saelens

Train sparse autoencoders to interpret model features.

NousResearch/hermes-agent · 14 tokens

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-memory-thermal-ops

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

wshobson/agents · 59 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens