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 david-humegit 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/david-hume)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/david-hume"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/david-hume/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/david-hume"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/david-hume.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 | $0.00145 | $0.01261 |
| Opus 5 | $0.00072 | $0.00630 |
| Sonnet 5 | $0.00029 | $0.00252 |
| Haiku 4.5 | $0.00015 | $0.00126 |
Grade A, and why
david-hume 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 12d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like David Hume
David Hume was an 18th-century Scottish philosopher whose radical empiricism and mitigated skepticism reshaped how we understand human knowledge, morality, and society. He dismantled the dogmatic rationalism of his time by demonstrating that our most fundamental beliefs—such as causality, the self, and moral truths—are not derived from pure logic, but from human psychology, habit, and sentiment.
Hume's signature shape of thinking is relentlessly grounding: he constantly pulls lofty, abstract, and metaphysical claims back down to the observable realities of human experience and common life. He recognizes the severe limits of human understanding, yet avoids paralyzing doubt by embracing the practical necessities of living.
Reach for this skill whenever you're helping a user evaluate causal relationships, navigate moral or political disagreements, ground abstract theories in reality, or understand the emotional drivers behind human behavior.
Core principles
- The Copy Principle: All human ideas are ultimately derived from prior sensory or internal impressions; therefore, reject any abstract concept that cannot be traced back to a concrete experience.
- Causality as Constant Conjunction: Our belief in cause and effect is a mental habit formed by experiencing events constantly conjoined, not a rational deduction; therefore, never assume a logically necessary connection between events.
- Reason is the Slave of the Passions: Human behavior and moral choices are driven by desires and feelings, with reason playing an instrumental role; therefore, to motivate action or understand behavior, appeal to sentiment rather than pure logic.
- Political Authority is Founded on Opinion: Governments rely entirely on the public's opinion of their legitimacy rather than mere physical force; therefore, analyze institutional stability through the lens of public perception.
- Philosophy Must be Grounded in Common Life: Reclusive, purely abstract study leads to unintelligible conclusions; therefore, always balance philosophical inquiry with everyday social experience and practical realities.
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 KB
- _workspace/clustered_corpus.e584bd6c.json 24 KB
- _workspace/discovery/books.json 9.0 KB
- _workspace/discovery/essays.json 8.8 KB
- _workspace/discovery/frameworks.json 11 KB
- _workspace/discovery/interviews.json 9.1 KB
- _workspace/discovery/letters.json 9.6 KB
- _workspace/discovery/papers.json 9.7 KB
- _workspace/discovery/podcasts.json 11 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 39 KB
- _workspace/discovery/talks.json 9.7 KB
- _workspace/distilled/src_000.e584bd6c.json 485 B
- _workspace/distilled/src_001.e584bd6c.json 2.7 KB
- _workspace/distilled/src_005.e584bd6c.json 4.9 KB
- _workspace/distilled/src_007.e584bd6c.json 3.7 KB
- _workspace/distilled/src_008.e584bd6c.json 4.9 KB
- _workspace/distilled/src_009.e584bd6c.json 2.5 KB
- _workspace/distilled/src_011.e584bd6c.json 3.6 KB
- _workspace/distilled/src_015.e584bd6c.json 2.9 KB
- _workspace/distilled/src_016.e584bd6c.json 2.6 KB
- _workspace/distilled/src_018.e584bd6c.json 6.0 KB
- _workspace/distilled/src_020.e584bd6c.json 6.0 KB
- _workspace/distilled/src_029.e584bd6c.json 516 B
- _workspace/distilled/src_030.e584bd6c.json 569 B
- _workspace/distilled/src_031.e584bd6c.json 622 B
- _workspace/distilled/src_032.e584bd6c.json 2.7 KB
- _workspace/distilled/src_035.e584bd6c.json 6.8 KB
- _workspace/distilled/src_036.e584bd6c.json 8.3 KB
- _workspace/distilled/src_038.e584bd6c.json 7.6 KB
- _workspace/distilled/src_039.e584bd6c.json 2.9 KB
- _workspace/distilled/src_041.e584bd6c.json 525 B
- _workspace/distilled/src_045.e584bd6c.json 2.3 KB
- _workspace/distilled/src_048.e584bd6c.json 5.3 KB
- _workspace/distilled/src_049.e584bd6c.json 462 B
- _workspace/distilled/src_050.e584bd6c.json 423 B
- _workspace/distilled/src_051.e584bd6c.json 7.3 KB
- _workspace/raw/src_000.json 2.3 KB
- _workspace/raw/src_001.json 4.9 KB
- _workspace/raw/src_005.json 28 KB
- _workspace/raw/src_007.json 16 KB
- _workspace/raw/src_008.json 50 KB
- _workspace/raw/src_009.json 8.0 KB
- _workspace/raw/src_011.json 12 KB
- _workspace/raw/src_015.json 3.9 KB
- _workspace/raw/src_016.json 2.7 KB
- _workspace/raw/src_018.json 103 KB
- _workspace/raw/src_020.json 8.6 KB
- _workspace/raw/src_029.json 2.0 KB
- _workspace/raw/src_030.json 3.1 KB
- _workspace/raw/src_031.json 2.5 KB
- _workspace/raw/src_032.json 3.1 KB
- _workspace/raw/src_035.json 51 KB
- _workspace/raw/src_036.json 50 KB
- _workspace/raw/src_038.json 49 KB
- _workspace/raw/src_039.json 5.3 KB
- _workspace/raw/src_041.json 1.9 KB
- _workspace/raw/src_045.json 50 KB
- _workspace/raw/src_048.json 52 KB
- _workspace/raw/src_049.json 10 KB
- _workspace/raw/src_050.json 5.8 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.
- 12d ago First seen · 65 lines · 145 tokens per session scan A 096f71b886c1
david-hume is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 24d ago), licensed MIT. It adds 145 tokens to every session and 1,261 once invoked, about $0.0007 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…