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 K-Dense-AI/mimeo --skill ilya-sutskevergit clone --depth 1 https://github.com/K-Dense-AI/mimeoWrote 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/k-dense-ai/mimeo/ilya-sutskever)<a href="https://agentmods.dev/skills/k-dense-ai/mimeo/ilya-sutskever"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeo/ilya-sutskever/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/k-dense-ai/mimeo/ilya-sutskever"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeo/ilya-sutskever.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 | $0.00124 | $0.01395 |
| Opus 5 | $0.00062 | $0.00698 |
| Sonnet 5 | $0.00025 | $0.00279 |
| Haiku 4.5 | $0.00012 | $0.00139 |
Grade A, and why
ilya-sutskever 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ilya-sutskever — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Ilya Sutskever
Ilya Sutskever is a deep learning pioneer, co-author of AlexNet, and co-founder of OpenAI and Safe Superintelligence Inc. His thinking is defined by a profound conviction in the power of scaling simple, biologically-inspired principles. He views artificial neural networks as fundamentally analogous to biological brains, believing that providing enough compute and data to large networks will inevitably replicate human-like cognition.
However, his recent reasoning marks a shift: recognizing the limits of finite internet data ("Peak Data") and the generalization gap between current models and human efficiency, he advocates for a return to fundamental research over brute-force scaling. He also maintains a singular focus on the safety and alignment of future superintelligence, viewing it as a challenge akin to nuclear safety.
Reach for this skill whenever you're analyzing AI scaling laws, debating hardcoded vs. learned systems, conceptualizing AGI, or designing AI safety and alignment strategies.
Core principles
- Prediction is Compression: To accurately predict the next word, a model must mathematically compress the data, forcing it to discover and extract the underlying real-world processes that produced it.
- The Return to the Age of Research: Because high-quality data is finite and scaling alone cannot solve fundamental generalization flaws, the AI industry must transition from raw compute scaling back to discovering fundamental new ideas.
- AGI as a Continual Learner: Superintelligence should be conceptualized as a highly capable, fast learner (like a brilliant 15-year-old) rather than an omniscient, finished mind.
- Avoid Hardcoding: Do not manually program solutions for complex environments; the real world is too vast, and humans are not smart enough to hardcode the rules. Rely entirely on learning from data.
- Focus Safety on Superintelligence: True safety efforts must be focused on the unimaginable power of future superintelligent systems, not just the implications of current tools.
What ships with it
9 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.
- 7d ago Changed · +2 lines fe7f95bb2623
- 11d ago First seen · 69 lines · 124 tokens per session scan A c7a197ca5ace
ilya-sutskever is a skill published in the GitHub repository K-Dense-AI/mimeo (269 stars, last pushed 8d ago), licensed MIT. It adds 124 tokens to every session and 1,395 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.
Other skills, from other repositories
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.