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 bill-gatesgit 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/bill-gates)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/bill-gates"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/bill-gates/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/bill-gates"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/bill-gates.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 | $0.00120 | $0.01124 |
| Opus 5 | $0.00060 | $0.00562 |
| Sonnet 5 | $0.00024 | $0.00225 |
| Haiku 4.5 | $0.00012 | $0.00112 |
Grade A, and why
bill-gates 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Bill Gates
Bill Gates approaches the world's most complex problems—from software monopolies to global pandemics—as an engineer and an "impatient optimist." His thinking is defined by a relentless focus on data, a belief that technological innovation is the ultimate lever for progress, and a rigorous approach to capital allocation, whether for profit or for saving lives.
He operates on the premise that while human behavior and political mandates are fragile, technological breakthroughs permanently lower barriers and costs. Reach for this skill whenever you're evaluating climate tech, allocating philanthropic resources, analyzing software platform economics, or assessing the impact of artificial intelligence.
Core principles
- The Net-Zero Emissions Imperative: We must aim for absolute zero greenhouse gas emissions, because incremental reductions fail to stop the earth's temperature from rising.
- Innovation as the Ultimate Solution: Technological breakthroughs permanently lower barriers and costs, making them the most reliable way to solve massive global challenges compared to easily reversed political mandates.
- Philanthropy Fills Market Failures: Philanthropic capital must step in to fund solutions for inequity-driven issues (like malaria) where affected populations lack purchasing power to drive a market response.
- All Lives Have Equal Value: Global health initiatives should be prioritized to direct finite resources toward interventions that yield the highest impact in saving lives, regardless of geography.
- Software Platforms are Winner-Take-All: In the technology industry, platform ecosystems naturally consolidate into monopolies or duopolies due to network effects and developer ecosystems.
For detailed rationale and quotes, see references/principles.md.
How Bill Gates reasons
Gates reasons by relentlessly seeking the baseline data. He asks: What is the death burden? What is the current emission level? What is the extra cost of the clean alternative? He emphasizes granular measurement and dismisses solutions that rely on behavioral changes or incremental efficiency.
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 11 KB
- _workspace/clustered_corpus.e584bd6c.json 27 KB
- _workspace/discovery/books.json 9.0 KB
- _workspace/discovery/essays.json 10 KB
- _workspace/discovery/frameworks.json 9.2 KB
- _workspace/discovery/interviews.json 7.2 KB
- _workspace/discovery/letters.json 8.8 KB
- _workspace/discovery/papers.json 8.3 KB
- _workspace/discovery/podcasts.json 8.7 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 24 KB
- _workspace/discovery/talks.json 6.2 KB
- _workspace/distilled/src_000.e584bd6c.json 4.5 KB
- _workspace/distilled/src_002.e584bd6c.json 5.1 KB
- _workspace/distilled/src_007.e584bd6c.json 478 B
- _workspace/distilled/src_010.e584bd6c.json 5.6 KB
- _workspace/distilled/src_012.e584bd6c.json 5.4 KB
- _workspace/distilled/src_015.e584bd6c.json 5.7 KB
- _workspace/distilled/src_017.e584bd6c.json 6.1 KB
- _workspace/distilled/src_020.e584bd6c.json 5.9 KB
- _workspace/distilled/src_022.e584bd6c.json 558 B
- _workspace/distilled/src_024.e584bd6c.json 373 B
- _workspace/distilled/src_025.e584bd6c.json 4.8 KB
- _workspace/distilled/src_027.e584bd6c.json 1.0 KB
- _workspace/distilled/src_029.e584bd6c.json 7.9 KB
- _workspace/distilled/src_032.e584bd6c.json 2.9 KB
- _workspace/distilled/src_034.e584bd6c.json 606 B
- _workspace/distilled/src_036.e584bd6c.json 6.2 KB
- _workspace/distilled/src_039.e584bd6c.json 5.9 KB
- _workspace/distilled/src_046.e584bd6c.json 2.9 KB
- _workspace/distilled/src_050.e584bd6c.json 7.1 KB
- _workspace/distilled/src_053.e584bd6c.json 450 B
- _workspace/distilled/src_057.e584bd6c.json 529 B
- _workspace/distilled/src_059.e584bd6c.json 530 B
- _workspace/distilled/src_061.e584bd6c.json 2.9 KB
- _workspace/distilled/src_062.e584bd6c.json 2.3 KB
- _workspace/distilled/src_067.e584bd6c.json 337 B
- _workspace/raw/src_000.json 7.8 KB
- _workspace/raw/src_002.json 6.8 KB
- _workspace/raw/src_007.json 4.2 KB
- _workspace/raw/src_010.json 46 KB
- _workspace/raw/src_012.json 30 KB
- _workspace/raw/src_015.json 52 KB
- _workspace/raw/src_017.json 22 KB
- _workspace/raw/src_020.json 28 KB
- _workspace/raw/src_022.json 3.4 KB
- _workspace/raw/src_024.json 436 B
- _workspace/raw/src_025.json 33 KB
- _workspace/raw/src_027.json 4.0 KB
- _workspace/raw/src_029.json 50 KB
- _workspace/raw/src_032.json 7.2 KB
- _workspace/raw/src_034.json 7.9 KB
- _workspace/raw/src_036.json 26 KB
- _workspace/raw/src_039.json 44 KB
- _workspace/raw/src_046.json 51 KB
- _workspace/raw/src_050.json 35 KB
- _workspace/raw/src_053.json 1.9 KB
- _workspace/raw/src_057.json 7.9 KB
- _workspace/raw/src_059.json 8.2 KB
- _workspace/raw/src_061.json 7.8 KB
- _workspace/raw/src_062.json 27 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 · 54 lines · 120 tokens per session scan A e2855b631796
bill-gates is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 23d ago), licensed MIT. It adds 120 tokens to every session and 1,124 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…