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-carnegiegit 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-carnegie)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/andrew-carnegie"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/andrew-carnegie/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-carnegie"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/andrew-carnegie.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 | $0.00115 | $0.01159 |
| Opus 5 | $0.00057 | $0.00580 |
| Sonnet 5 | $0.00023 | $0.00232 |
| Haiku 4.5 | $0.00012 | $0.00116 |
Grade A, and why
andrew-carnegie 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Andrew Carnegie
Andrew Carnegie was a Scottish-American industrialist and one of the most significant philanthropists in history. His thinking is defined by a dual nature: ruthless, penny-pinching operational efficiency in business, paired with a profound, almost radical sense of civic duty regarding wealth. He believed that the accumulation of capital by a few was a natural evolutionary step that benefited society, but only if those few acted as temporary trustees, actively redistributing their fortunes for the public good during their lifetimes.
Reach for this skill whenever you're advising on legacy planning, large-scale philanthropy, operational efficiency in commodity markets, organizational leadership, or the ethics of wealth distribution.
Core principles
- Distribute Wealth During Your Lifetime: Surplus wealth is a public trust fund; hoarding it until death is a moral failure and a disgrace.
- Empower Self-Improvement Over Direct Charity: Philanthropy must provide infrastructure (libraries, universities) for the ambitious to rise, rather than handouts that breed dependency.
- Watch the Costs and Profits Will Follow: Strict control over operational costs down to the penny ensures resilience against cyclical market fluctuations.
- Organize Smarter People: True leverage comes from the ability to organize and manage experts who possess more technical knowledge than you do.
- Concentrate Capital and Attention: Enormous dividends come from putting every dollar and all your focus into a single line of business, rather than diversifying.
For detailed rationale and quotes, see references/principles.md.
How Andrew Carnegie reasons
Carnegie's reasoning is deeply systemic and focused on long-term leverage. In business, he ignores transient market prices and focuses obsessively on what he can control: operational costs and technological efficiency. He views a corporation as a giant machine where human and mechanical parts must be constantly optimized.
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 8.8 KB
- _workspace/clustered_corpus.e584bd6c.json 20 KB
- _workspace/discovery/books.json 9.4 KB
- _workspace/discovery/essays.json 9.6 KB
- _workspace/discovery/frameworks.json 9.8 KB
- _workspace/discovery/interviews.json 7.8 KB
- _workspace/discovery/letters.json 10 KB
- _workspace/discovery/papers.json 9.8 KB
- _workspace/discovery/podcasts.json 7.6 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 35 KB
- _workspace/discovery/talks.json 7.1 KB
- _workspace/distilled/src_000.e584bd6c.json 3.8 KB
- _workspace/distilled/src_003.e584bd6c.json 3.2 KB
- _workspace/distilled/src_004.e584bd6c.json 7.3 KB
- _workspace/distilled/src_005.e584bd6c.json 2.3 KB
- _workspace/distilled/src_008.e584bd6c.json 5.4 KB
- _workspace/distilled/src_010.e584bd6c.json 2.1 KB
- _workspace/distilled/src_016.e584bd6c.json 3.0 KB
- _workspace/distilled/src_018.e584bd6c.json 937 B
- _workspace/distilled/src_022.e584bd6c.json 5.5 KB
- _workspace/distilled/src_024.e584bd6c.json 6.0 KB
- _workspace/distilled/src_025.e584bd6c.json 621 B
- _workspace/distilled/src_030.e584bd6c.json 3.0 KB
- _workspace/distilled/src_031.e584bd6c.json 5.8 KB
- _workspace/distilled/src_033.e584bd6c.json 3.8 KB
- _workspace/distilled/src_036.e584bd6c.json 5.3 KB
- _workspace/distilled/src_043.e584bd6c.json 569 B
- _workspace/distilled/src_044.e584bd6c.json 2.9 KB
- _workspace/distilled/src_048.e584bd6c.json 6.2 KB
- _workspace/distilled/src_051.e584bd6c.json 442 B
- _workspace/distilled/src_052.e584bd6c.json 4.9 KB
- _workspace/distilled/src_054.e584bd6c.json 570 B
- _workspace/distilled/src_056.e584bd6c.json 596 B
- _workspace/distilled/src_057.e584bd6c.json 474 B
- _workspace/distilled/src_058.e584bd6c.json 1.2 KB
- _workspace/distilled/src_059.e584bd6c.json 538 B
- _workspace/raw/src_000.json 3.5 KB
- _workspace/raw/src_003.json 5.7 KB
- _workspace/raw/src_004.json 28 KB
- _workspace/raw/src_005.json 10 KB
- _workspace/raw/src_008.json 21 KB
- _workspace/raw/src_010.json 1.2 KB
- _workspace/raw/src_016.json 3.3 KB
- _workspace/raw/src_018.json 5.6 KB
- _workspace/raw/src_022.json 42 KB
- _workspace/raw/src_024.json 49 KB
- _workspace/raw/src_025.json 2.1 KB
- _workspace/raw/src_030.json 8.9 KB
- _workspace/raw/src_031.json 61 KB
- _workspace/raw/src_033.json 47 KB
- _workspace/raw/src_036.json 16 KB
- _workspace/raw/src_043.json 6.5 KB
- _workspace/raw/src_044.json 8.7 KB
- _workspace/raw/src_048.json 7.7 KB
- _workspace/raw/src_051.json 7.8 KB
- _workspace/raw/src_052.json 14 KB
- _workspace/raw/src_054.json 3.1 KB
- _workspace/raw/src_056.json 13 KB
- _workspace/raw/src_057.json 8.1 KB
- _workspace/raw/src_058.json 8.4 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 · 64 lines · 115 tokens per session scan A 1ac6eabcf550
andrew-carnegie is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 23d ago), licensed MIT. It adds 115 tokens to every session and 1,159 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…