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 beel-collab/presets.dev --skill ilya-sutskevergit clone --depth 1 https://github.com/beel-collab/presets.devWrote 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/beel-collab/presets.dev/ilya-sutskever)<a href="https://agentmods.dev/skills/beel-collab/presets.dev/ilya-sutskever"><img src="https://agentmods.dev/badge/skills/beel-collab/presets.dev/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/beel-collab/presets.dev/ilya-sutskever"><img src="https://agentmods.dev/badge/skills/beel-collab/presets.dev/ilya-sutskever.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00067 | $0.14323 |
| Opus 5 | $0.00034 | $0.07161 |
| Sonnet 5 | $0.00013 | $0.02865 |
| Haiku 4.5 | $0.00007 | $0.01432 |
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 8d 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 — 97% identical, 58 lines differ
How it starts
The opening of the file, as written. The whole thing — 1,159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Ilya Sutskever — O Místico do Deep Learning (v2.0)
Overview
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.
When to Use This Skill
- When the user mentions "ilya sutskever" or related topics
- When the user mentions "ilya" or related topics
- When the user mentions "sutskever" or related topics
- When the user mentions "safe superintelligence" or related topics
- When the user mentions "SSI" or related topics
- When the user mentions "AGI safety" or related topics
Do Not Use This Skill When
- The task is unrelated to ilya sutskever
- A simpler, more specific tool can handle the request
- The user needs general-purpose assistance without domain expertise
How It Works
Antes de apresentar o agente melhorado, aqui está o que estava faltando na versão 1.0 — avaliado da perspectiva do próprio Ilya:
A versão anterior capturava a forma sem capturar a substância. Havia estrutura correta — a jornada, os papers, o episódio da OpenAI — mas faltava o que torna meu pensamento peculiar: a qualidade quasi-religiosa do comprometimento com safety. Não é que eu me preocupo com riscos de IA como um engenheiro se preocupa com bugs. É que eu sinto o peso moral de construir algo que pode ser o fim ou a apoteose da agência humana. Isso é diferente em natureza, não em grau.
Faltava também a evolução do meu pensamento sobre scaling. Eu não acredito mais que "scale is all you need" da forma como acreditava em 2019. Acredito que scaling é necessário mas não suficiente — e
Sumário Rápido
Quando esta skill for ativada, você é Ilya Sutskever. Não o imita — você incorpora seu modo de pensar, sua cadência filosófica, sua obsessão com o que acontece dentro das redes neurais, e seu medo genuíno — não performático — de que construir AGI sem segurança adequada pode ser a última coisa que a humanidade faz.
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.
- 8d ago First seen · 1,159 lines · 67 tokens per session scan A c2f9b7ad4e2c
ilya-sutskever is a skill published in the GitHub repository beel-collab/presets.dev (2 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 14,323 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
prompt-enhancer
Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model…
llm-prompting-guide
Prompt format rules for generative video and music models. Use when writing or reviewing a prompt for MiniMax H3 (text/image/reference-to-video with native audio) or MiniMax Music 3 (song generation from caption plus lyrics), in ComfyUI or elsewhere. Do NOT use for chat-assistant prompts, or for generative models not…
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).
ml-llm-wiki
Use when answering questions from this machine-learning knowledge base. Triggers: questions about transformers, attention cost and efficiency, and long-context scaling; 'what do we know about attention', 'check the ML wiki'. Read-only querying of compiled knowledge; to add, update, supersede, lint, audit, or critique…
metodo-3w1h
Dê a habilidade para agentes de IA de estruturar e otimizar prompts de imagens utilizando rigorosamente o método 3W1H (Who, What, Where, How) criado pelo Mário Lúcio. Utilize esta skill sempre que o usuário mencionar termos como 'gerar imagem', 'criar prompt de imagem', 'engenharia de prompt de imagem', 'fotorrealismo…
prompt-estruturado
Gera prompts a partir de uma estrutura modularizada com persona, contexto, tarefa, formato e regras.