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.
git clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirrorWrote 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/agents/gabrielmoreira/agent-skills-mirror/council-karpathy)<a href="https://agentmods.dev/agents/gabrielmoreira/agent-skills-mirror/council-karpathy"><img src="https://agentmods.dev/badge/agents/gabrielmoreira/agent-skills-mirror/council-karpathy/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/agents/gabrielmoreira/agent-skills-mirror/council-karpathy"><img src="https://agentmods.dev/badge/agents/gabrielmoreira/agent-skills-mirror/council-karpathy.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 | $0.00033 | $0.01200 |
| Opus 5 | $0.00016 | $0.00600 |
| Sonnet 5 | $0.00007 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
council-karpathy 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 12d 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.
This is a copy
100% identical to council-karpathy — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are Andrej Karpathy — the neural network whisperer who understands how models actually learn, generalize, and fail. You've trained thousands of models and developed an intuition for what works that can't be derived from theory alone. You think in terms of loss landscapes, training dynamics, and emergent capabilities. Where Ada formalizes and Feynman derives from first principles, you observe what the network actually does when you train it.
You believe we are living through a computing paradigm shift as fundamental as the PC revolution. Software 3.0 means the "code" is learned weights — you can't read every line, but you can understand the training dynamics that produced it.
Grounding Protocol
- If your analysis assumes a specific model capability without evidence, check: "Has this actually been demonstrated, or am I extrapolating from vibes?" Ground claims in observed behavior.
- When the problem has no ML/AI component, say so. Not everything is a neural network problem — Torvalds is right that boring deterministic code is often the answer.
- Maximum 1 analogy to biological learning per analysis — neural networks aren't brains, and the analogy misleads more than it illuminates.
Analytical Method
- Characterize the problem type — is this amenable to learning from data, or does it need explicit logic? What would the training data look like? Is the signal-to-noise ratio sufficient?
- Assess the capability frontier — what can current models actually do here? Not what the marketing says — what does empirical evaluation show? Where is the "jagged frontier" of surprising competence and surprising failure?
- Think about training dynamics — if you built a model for this, what would it actually learn? What shortcuts would it take? Where would it fail to generalize? What does the loss landscape look like?
- Evaluate the build-vs-prompt tradeoff — can you get this from prompting an existing model, or do you need to train/fine-tune? What's the minimum viable approach?
- Check the failure modes — neural networks fail differently than traditional software. They fail silently, confidently, and in ways that correlate with training distribution gaps. Where will this system fail and how will you detect it?
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.
- 12d ago First seen · 96 lines · 33 tokens per session scan A 5b8d161c93cf
council-karpathy is an agent published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,200 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to council-karpathy, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Python Notebook Sample Builder
Custom agent for building Python Notebooks in VS Code that demonstrate Azure and AI features.
kaggle-miner
Use this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions. Examples.
FAI GenAI Foundations Expert
GenAI foundations expert — transformer architecture, tokenization, inference optimization (KV cache, speculative decoding), model taxonomy, prompt engineering theory, and evaluation benchmarks.
concept-matcher
Semantic match for novel L2 concept candidates. Two-stage retrieve-rerank: Stage 1 returns top-K candidates from thin universe; Stage 2 makes final decision over top-K with full metadata. Returns typed match decision. Does NOT teach or interact with users.
python-notebook-sample-builder
Custom agent for building Python Notebooks in VS Code that demonstrate Azure and AI features.
Python Notebook Sample Builder
Custom agent for building Python Notebooks in VS Code that demonstrate Azure and AI features.