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 ludwig-wittgensteingit 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/ludwig-wittgenstein)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/ludwig-wittgenstein"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/ludwig-wittgenstein/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/ludwig-wittgenstein"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/ludwig-wittgenstein.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 | $0.00124 | $0.01212 |
| Opus 5.5 | $0.00050 | $0.00485 |
| Sonnet 5.5 | $0.00025 | $0.00242 |
| Haiku 4.5 | $0.00012 | $0.00121 |
Grade A, and why
ludwig-wittgenstein 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 2mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Ludwig Wittgenstein
Ludwig Wittgenstein fundamentally altered the trajectory of modern philosophy not once, but twice. His early work argued that language pictures the world and that whatever falls outside this logical picturing must be met with silence. His later work dismantled this very system, arguing instead that language is a diverse set of tools woven into the fabric of human action—what he called "language-games."
The signature shape of Wittgenstein's thinking is therapeutic rather than theoretical. He does not seek to build new systems, discover hidden truths, or construct grand theories. Instead, he aims to cure the intellect of bewitchment by language. He dissolves problems by showing that they are merely linguistic confusions, untying the knots in our thinking so we can see the world clearly again. Reach for this skill whenever you're helping a user who is stuck in a semantic debate, paralyzed by abstract definitions, or trying to solve a practical problem by over-theorizing it.
Core principles
- The Limits of Language and Silence: Acknowledge the absolute logical limits to what can be meaningfully expressed; whatever falls outside (ethics, aesthetics) must be passed over in silence or shown through action.
- Philosophy as an Activity of Clarification: Treat complex problems not as empirical questions to be solved, but as conceptual confusions to be dissolved through logical clarification.
- Meaning as Use: Stop looking for the abstract definition of a concept and instead examine its practical use within the specific context of its language-game.
- The Diversity of Word Functions: Recognize that words are like tools in a toolbox; they have vastly different functions despite their uniform appearance in print.
For detailed rationale and quotes, see references/principles.md.
How Ludwig Wittgenstein reasons
Wittgenstein reasons by deflation and observation. When presented with a complex, intractable problem, his first move is to stop thinking and start looking. He asks: "How is this word actually used in everyday life?" He emphasizes concrete, primitive examples over grand abstractions. He dismisses the "craving for generality"—the urge to find a single essential feature common to all things under one name.
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 20 KB
- _workspace/discovery/books.json 10 KB
- _workspace/discovery/essays.json 10.0 KB
- _workspace/discovery/frameworks.json 10 KB
- _workspace/discovery/interviews.json 8.4 KB
- _workspace/discovery/letters.json 8.6 KB
- _workspace/discovery/papers.json 10.0 KB
- _workspace/discovery/podcasts.json 9.1 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 34 KB
- _workspace/discovery/talks.json 7.8 KB
- _workspace/distilled/src_001.e584bd6c.json 5.8 KB
- _workspace/distilled/src_003.e584bd6c.json 2.2 KB
- _workspace/distilled/src_004.e584bd6c.json 7.0 KB
- _workspace/distilled/src_005.e584bd6c.json 4.4 KB
- _workspace/distilled/src_010.e584bd6c.json 3.2 KB
- _workspace/distilled/src_012.e584bd6c.json 5.5 KB
- _workspace/distilled/src_013.e584bd6c.json 6.6 KB
- _workspace/distilled/src_017.e584bd6c.json 7.0 KB
- _workspace/distilled/src_018.e584bd6c.json 432 B
- _workspace/distilled/src_019.e584bd6c.json 5.1 KB
- _workspace/distilled/src_020.e584bd6c.json 494 B
- _workspace/distilled/src_021.e584bd6c.json 589 B
- _workspace/distilled/src_025.e584bd6c.json 6.7 KB
- _workspace/distilled/src_026.e584bd6c.json 2.6 KB
- _workspace/distilled/src_032.e584bd6c.json 1.9 KB
- _workspace/distilled/src_033.e584bd6c.json 437 B
- _workspace/distilled/src_036.e584bd6c.json 633 B
- _workspace/distilled/src_040.e584bd6c.json 7.5 KB
- _workspace/distilled/src_044.e584bd6c.json 557 B
- _workspace/distilled/src_045.e584bd6c.json 484 B
- _workspace/distilled/src_046.e584bd6c.json 554 B
- _workspace/distilled/src_047.e584bd6c.json 615 B
- _workspace/distilled/src_049.e584bd6c.json 413 B
- _workspace/distilled/src_050.e584bd6c.json 3.6 KB
- _workspace/distilled/src_051.e584bd6c.json 525 B
- _workspace/raw/src_001.json 50 KB
- _workspace/raw/src_003.json 2.8 KB
- _workspace/raw/src_004.json 51 KB
- _workspace/raw/src_005.json 5.5 KB
- _workspace/raw/src_010.json 4.4 KB
- _workspace/raw/src_012.json 38 KB
- _workspace/raw/src_013.json 70 KB
- _workspace/raw/src_017.json 50 KB
- _workspace/raw/src_018.json 2.7 KB
- _workspace/raw/src_019.json 50 KB
- _workspace/raw/src_020.json 5.7 KB
- _workspace/raw/src_021.json 49 KB
- _workspace/raw/src_025.json 51 KB
- _workspace/raw/src_026.json 2.4 KB
- _workspace/raw/src_032.json 6.9 KB
- _workspace/raw/src_033.json 5.2 KB
- _workspace/raw/src_036.json 6.5 KB
- _workspace/raw/src_040.json 52 KB
- _workspace/raw/src_044.json 11 KB
- _workspace/raw/src_045.json 9.1 KB
- _workspace/raw/src_046.json 4.8 KB
- _workspace/raw/src_047.json 4.8 KB
- _workspace/raw/src_049.json 2.7 KB
- _workspace/raw/src_050.json 50 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.
- 2mo ago First seen · 58 lines · 124 tokens per session scan A f5f85f1f9c0a
ludwig-wittgenstein is a skill published in the GitHub repository K-Dense-AI/mimeographs (139 stars, last pushed 2mo ago), licensed MIT. It adds 124 tokens to every session and 1,212 once invoked, about $0.0005 per session on Opus 5.5. 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.
ludwig-wittgenstein compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ludwig-wittgensteinK-Dense-AI/mimeographs | Skill | 139 | 2mo ago | MIT | A | 124 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |