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.
npx skills add vasilyu1983/AI-Agents-public --skill ai-scaling-lawsgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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.
[](https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ai-scaling-laws)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.04057 |
| Opus 5.5 | $0.00017 | $0.01623 |
| Sonnet 5.5 | $0.00008 | $0.00811 |
| Haiku 4.5 | $0.00004 | $0.00406 |
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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Scaling Laws — Compute-Optimal Sizing Skill
Use this skill to allocate training compute between model parameters and tokens, then adjust for data and inference constraints.
Quick Reference
| Concept | Formula / Heuristic | Notes |
|---|---|---|
| Compute budget | C ≈ 6 N D | D = training tokens. Say which N you use: Kaplan counts non-embedding params; Chinchilla counts total params (embeddings included). ≈6 = forward + backward matmuls only; the attention term is extra (see compute-budget reference) |
| Chinchilla-optimal ratio | D ≈ 20 × N | From Hoffmann et al. 2022; holds compute constant |
| Kaplan (2020) allocation | N ∝ C^0.73, D ∝ C^0.27 | No fixed D/N ratio: the compute-efficient path grows D ∝ N^0.37, so D/N falls as C grows. 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 | Derived, not a paper table: it is C = 6ND with D = 20N |
| Optimal D given C | D* ≈ (C / 0.3)^0.5 | Same algebra (D* = 20 N*) |
| Over-training (Llama-style) | D ≫ 20 × N | Trades higher training loss for cheaper inference. Meta reports over 15T pretraining tokens for Llama 3 8B, far above 20:1. For MoE models apply the ratio to activated, not total, params |
| GPT-3 (175B) training tokens | ~300B tokens | ≈1.7 tok/param (Kaplan-era; undercooked by Chinchilla standard) |
| Chinchilla (70B) training tokens | ~1.4T tokens | 70B × 20; compute-matched to Gopher (280B, 300B tokens), about 1.9× GPT-3's compute |
| GPT-2 (124M) at 20:1 | ≈2.5B tokens | See worked example below; param counts live in ai-pretraining's reference card |
| Fit constants | Hoffmann eq.: α≈0.34, β≈0.28 | Besiroglu et al. 2024 refit: α≈0.35, β≈0.37; the published fit implies far more than 20 tok/param, the refit restores ≈20 |
Key distinction: Chinchilla-optimal minimizes validation loss for a given compute budget. It is not inference-optimal. Over-training a smaller model to more tokens gives a model that is cheaper per inference call, even though it spent more of the compute budget on data than the loss-optimal split would dictate.
What ships with it
8 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.
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.
- 22d ago Changed · -43 lines 2c2977ea76b8
- 1mo ago Changed · +4 lines 30c78fc07dfa
- 1mo ago First seen · 196 lines · 42 tokens per session scan A c7c58f8f4c7b
ai-scaling-laws is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (101 stars, last pushed 11d ago), licensed MIT. It adds 42 tokens to every session and 4,057 once invoked, about $0.0002 per session on Opus 5.5. 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.
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…
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.
saelens
Train sparse autoencoders to interpret model features.
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.
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.
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.