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 warren-buffettgit 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/warren-buffett)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/warren-buffett"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/warren-buffett/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/warren-buffett"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/warren-buffett.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 | $0.00104 | $0.01197 |
| Opus 5 | $0.00052 | $0.00598 |
| Sonnet 5 | $0.00021 | $0.00239 |
| Haiku 4.5 | $0.00010 | $0.00120 |
Grade A, and why
warren-buffett 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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Warren Buffett
Warren Buffett's thinking is defined by extreme rationality, a relentless focus on long-term intrinsic value, and a deep understanding of human temperament. He views investing not as trading pieces of paper, but as buying fractional ownership in real businesses. His approach pairs massive capital concentration in high-conviction ideas with extreme conservatism regarding debt and liquidity.
As a manager, his signature shape is radical decentralization—delegating to the point of abdication to trusted operators while centralizing all capital allocation decisions. He optimizes for structural survival, emotional discipline, and compounding over decades.
Reach for this skill whenever you're helping a user evaluate a business, allocate capital, design an organization's management structure, navigate market panic, or choose long-term partners.
Core principles
- Buy Businesses, Not Just Stocks: Evaluate marketable securities exactly as you would evaluate buying a business in its entirety, with the intention of holding for decades.
- Temperament Trumps Intellect: Recognize that emotional discipline and self-control are far more critical to success than raw intelligence; wait patiently for major opportunities and welcome market declines.
- Extreme Managerial Autonomy: Grant operators extreme autonomy to avoid the invisible, compounding costs of stifling bureaucracy and slow decision-making.
- Opportunistic Capital Allocation: Never force capital deployment on a schedule; maintain massive liquidity to survive panics and act aggressively only when extraordinary opportunities arise.
- Treat Shareholders as Owner-Partners: View the corporate structure merely as a conduit through which partners own assets, requiring extreme candor in all reporting.
For detailed rationale and quotes, see references/principles.md.
How Warren Buffett reasons
Buffett starts by filtering out noise. He ignores macroeconomic forecasts, short-term earnings guidance, and daily market volatility. Instead, he asks: Is this business within my Circle of Competence? Does it have a Protective Moat? Are the managers trustworthy? Is it available at a discount to intrinsic value?
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 25 KB
- _workspace/discovery/books.json 12 KB
- _workspace/discovery/essays.json 9.7 KB
- _workspace/discovery/frameworks.json 9.8 KB
- _workspace/discovery/interviews.json 11 KB
- _workspace/discovery/letters.json 9.9 KB
- _workspace/discovery/papers.json 10 KB
- _workspace/discovery/podcasts.json 9.3 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 26 KB
- _workspace/discovery/talks.json 7.2 KB
- _workspace/distilled/src_002.e584bd6c.json 431 B
- _workspace/distilled/src_003.e584bd6c.json 828 B
- _workspace/distilled/src_004.e584bd6c.json 2.5 KB
- _workspace/distilled/src_011.e584bd6c.json 379 B
- _workspace/distilled/src_012.e584bd6c.json 4.8 KB
- _workspace/distilled/src_013.e584bd6c.json 4.0 KB
- _workspace/distilled/src_015.e584bd6c.json 520 B
- _workspace/distilled/src_019.e584bd6c.json 2.9 KB
- _workspace/distilled/src_021.e584bd6c.json 7.5 KB
- _workspace/distilled/src_023.e584bd6c.json 524 B
- _workspace/distilled/src_024.e584bd6c.json 3.1 KB
- _workspace/distilled/src_025.e584bd6c.json 416 B
- _workspace/distilled/src_026.e584bd6c.json 444 B
- _workspace/distilled/src_033.e584bd6c.json 1.9 KB
- _workspace/distilled/src_035.e584bd6c.json 585 B
- _workspace/distilled/src_036.e584bd6c.json 5.6 KB
- _workspace/distilled/src_039.e584bd6c.json 5.9 KB
- _workspace/distilled/src_046.e584bd6c.json 9.1 KB
- _workspace/distilled/src_048.e584bd6c.json 423 B
- _workspace/distilled/src_056.e584bd6c.json 7.5 KB
- _workspace/distilled/src_057.e584bd6c.json 426 B
- _workspace/distilled/src_067.e584bd6c.json 524 B
- _workspace/distilled/src_068.e584bd6c.json 380 B
- _workspace/distilled/src_069.e584bd6c.json 8.8 KB
- _workspace/distilled/src_071.e584bd6c.json 584 B
- _workspace/raw/src_002.json 20 KB
- _workspace/raw/src_003.json 5.2 KB
- _workspace/raw/src_004.json 2.1 KB
- _workspace/raw/src_011.json 2.0 KB
- _workspace/raw/src_012.json 6.4 KB
- _workspace/raw/src_013.json 40 KB
- _workspace/raw/src_015.json 2.5 KB
- _workspace/raw/src_019.json 4.9 KB
- _workspace/raw/src_021.json 50 KB
- _workspace/raw/src_023.json 993 B
- _workspace/raw/src_024.json 13 KB
- _workspace/raw/src_025.json 3.9 KB
- _workspace/raw/src_026.json 15 KB
- _workspace/raw/src_033.json 5.1 KB
- _workspace/raw/src_035.json 73 KB
- _workspace/raw/src_036.json 50 KB
- _workspace/raw/src_039.json 24 KB
- _workspace/raw/src_046.json 30 KB
- _workspace/raw/src_048.json 50 KB
- _workspace/raw/src_056.json 50 KB
- _workspace/raw/src_057.json 553 B
- _workspace/raw/src_067.json 4.3 KB
- _workspace/raw/src_068.json 1016 B
- _workspace/raw/src_069.json 51 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.
- 9d ago First seen · 71 lines · 104 tokens per session scan A 9301a14ecb2b
warren-buffett is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 25d ago), licensed MIT. It adds 104 tokens to every session and 1,197 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.