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/mimeographs --skill andrew-nggit clone --depth 1 https://github.com/K-Dense-AI/mimeographsWrote 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/mimeographs/andrew-ng)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/andrew-ng"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/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/mimeographs/andrew-ng"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/andrew-ng.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 | $0.00124 | $0.01148 |
| Opus 5 | $0.00062 | $0.00574 |
| Sonnet 5 | $0.00025 | $0.00230 |
| Haiku 4.5 | $0.00012 | $0.00115 |
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 11d 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 andrew-ng — 2 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 — 71 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
60 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.
- _workspace/agents_output.e584bd6c.json 10.0 KB
- _workspace/clustered_corpus.e584bd6c.json 24 KB
- _workspace/critique_agents.json 3.4 KB
- _workspace/critique_agents.md 3.0 KB
- _workspace/critique_skill.json 3.8 KB
- _workspace/critique_skill.md 3.4 KB
- _workspace/discovery/books.json 9.9 KB
- _workspace/discovery/essays.json 9.7 KB
- _workspace/discovery/frameworks.json 11 KB
- _workspace/discovery/interviews.json 11 KB
- _workspace/discovery/letters.json 8.1 KB
- _workspace/discovery/papers.json 11 KB
- _workspace/discovery/podcasts.json 10 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 28 KB
- _workspace/discovery/talks.json 8.6 KB
- _workspace/distilled/src_001.e584bd6c.json 554 B
- _workspace/distilled/src_002.e584bd6c.json 2.7 KB
- _workspace/distilled/src_004.e584bd6c.json 520 B
- _workspace/distilled/src_005.e584bd6c.json 599 B
- _workspace/distilled/src_008.e584bd6c.json 1.4 KB
- _workspace/distilled/src_009.e584bd6c.json 3.8 KB
- _workspace/distilled/src_013.e584bd6c.json 7.8 KB
- _workspace/distilled/src_014.e584bd6c.json 5.3 KB
- _workspace/distilled/src_015.e584bd6c.json 385 B
- _workspace/distilled/src_016.e584bd6c.json 5.9 KB
- _workspace/distilled/src_018.e584bd6c.json 369 B
- _workspace/distilled/src_021.e584bd6c.json 9.2 KB
- _workspace/distilled/src_023.e584bd6c.json 364 B
- _workspace/distilled/src_025.e584bd6c.json 456 B
- _workspace/distilled/src_027.e584bd6c.json 553 B
- _workspace/distilled/src_028.e584bd6c.json 1.6 KB
- _workspace/distilled/src_030.e584bd6c.json 1.3 KB
- _workspace/distilled/src_031.e584bd6c.json 580 B
- _workspace/distilled/src_038.e584bd6c.json 353 B
- _workspace/distilled/src_039.e584bd6c.json 624 B
- _workspace/distilled/src_045.e584bd6c.json 614 B
- _workspace/distilled/src_046.e584bd6c.json 645 B
- _workspace/distilled/src_049.e584bd6c.json 3.1 KB
- _workspace/distilled/src_052.e584bd6c.json 5.7 KB
- _workspace/distilled/src_055.e584bd6c.json 979 B
- _workspace/quote_verification.json 17 KB
- _workspace/quote_verification.md 1.3 KB
- _workspace/raw/src_001.json 3.1 KB
- _workspace/raw/src_002.json 2.5 KB
- _workspace/raw/src_004.json 7.2 KB
- _workspace/raw/src_005.json 1.6 KB
- _workspace/raw/src_008.json 3.1 KB
- _workspace/raw/src_009.json 5.2 KB
- _workspace/raw/src_013.json 24 KB
- _workspace/raw/src_014.json 11 KB
- _workspace/raw/src_015.json 466 B
- _workspace/raw/src_016.json 11 KB
- _workspace/raw/src_018.json 448 B
- _workspace/raw/src_021.json 47 KB
- _workspace/raw/src_023.json 6.0 KB
- _workspace/raw/src_025.json 1.8 KB
- _workspace/raw/src_027.json 15 KB
- _workspace/raw/src_028.json 14 KB
- _workspace/raw/src_030.json 2.0 KB
- _workspace/raw/src_031.json 1.6 KB
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.
- 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/mimeographs (123 stars, last pushed 23d ago), licensed MIT. It adds 124 tokens to every session and 1,148 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to andrew-ng, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.