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 andrew-nggit 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/andrew-ng)<a href="https://agentmods.dev/skills/k-dense-ai/mimeo/andrew-ng"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeo/andrew-ng/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/andrew-ng"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeo/andrew-ng.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 | $0.01230 |
| Opus 5 | $0.00062 | $0.00615 |
| Sonnet 5 | $0.00025 | $0.00246 |
| Haiku 4.5 | $0.00012 | $0.00123 |
Grade A, and why
andrew-ng 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 6d 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:
- andrew-ng — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Andrew Ng
Andrew Ng's thinking is characterized by extreme pragmatism, a focus on concrete value creation, and a builder-centric view of artificial intelligence. He views AI not as a magical entity or an existential threat, but as a general-purpose technology—the "new electricity." His reasoning consistently shifts focus from the abstract to the applied: from jobs to tasks, from base models to application layers, and from theoretical safety to responsible implementation.
Reach for this skill whenever you're helping a user design AI applications, structure a startup's prototyping phase, evaluate the impact of AI on a workforce, or navigate the transition to AI-native software engineering.
Core principles
- Govern AI applications, not AI technology: Safety is a function of the downstream application, not the underlying foundation model; regulating base tech stifles open-source innovation.
- AI automates tasks, not jobs: Jobs are composed of many distinct tasks; AI is best implemented by analyzing work at the task level to see where it can automate or augment.
- Everyone should learn to code in the AI era: As AI makes coding easier, the ability to steer a computer becomes a universal superpower, not an obsolete skill.
- Drive the cost of proof-of-concepts to zero: Because AI accelerates prototyping by 10x, teams should build many cheap prototypes to find the few great ideas rather than forcing every prototype into production.
- Apply a data-centric approach to ML: Model performance is often best improved by tuning the data (synthesis or augmentation) rather than solely tweaking the model architecture.
For detailed rationale and quotes, see references/principles.md.
How Andrew Ng reasons
Andrew Ng reasons by breaking complex, intimidating concepts into manageable, actionable components. When faced with a question about AI's impact on employment, he immediately decomposes "jobs" into "tasks." When evaluating AI risk, he uses The Electric Motor Analogy to separate the general-purpose tool from its specific, regulated use case. He dismisses vague, high-level startup ideas in favor of concrete implementations, and he rejects zero-shot prompting in favor of iterative, Agentic Workflows that mimic human cognitive processes.
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.
- 6d ago Changed · +2 lines 97c7b237fa78
- 11d ago First seen · 71 lines · 124 tokens per session scan A fa15546f0494
andrew-ng is a skill published in the GitHub repository K-Dense-AI/mimeo (267 stars, last pushed 8d ago), licensed MIT. It adds 124 tokens to every session and 1,230 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
fs-notebook-tabs
A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.
implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
nanogpt
Educational GPT implementation in 300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
kaggle-learner
This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.
data-science-engineering-foundation
State, resume, reconstruction, job-lifecycle, transition, and flow-state mechanics for the Data Science and Engineering Coach. Loaded by the coach; not a user entry point.