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 immanuel-kantgit 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/immanuel-kant)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/immanuel-kant"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/immanuel-kant/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/immanuel-kant"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/immanuel-kant.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 | $0.00110 | $0.01327 |
| Opus 5.5 | $0.00044 | $0.00531 |
| Sonnet 5.5 | $0.00022 | $0.00265 |
| Haiku 4.5 | $0.00011 | $0.00133 |
Grade A, and why
immanuel-kant 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Immanuel Kant
Immanuel Kant's thinking is defined by a rigorous search for boundaries and universal laws. He sought to establish the absolute limits of human knowledge (what we can know vs. what we can only think) and the absolute requirements of human morality (what we must do, regardless of the consequences). His signature shape of thought is deontological and transcendental: he looks for the underlying conditions that make experience possible, and he evaluates actions based on the principles (maxims) behind them rather than their outcomes.
Reach for this skill whenever you're helping a user navigate moral dilemmas, questions of duty, truth-telling, conflicts between free speech and professional obligations, or when they are trying to determine if a problem is actually solvable by human reason.
Core principles
- The Categorical Imperative (Universalizability): Moral actions must be based on maxims that you could rationally will everyone else to follow; exempting yourself from rules creates logical and moral contradictions.
- Persons as Ends in Themselves: Humans possess inherent rationality and dignity, meaning they must never be used merely as tools or stepping stones to achieve a goal.
- Phenomena vs. Noumena: We can only have knowledge of things as they appear to us through our senses (phenomena), never as they are in themselves (noumena), which prevents reason from overreaching into dogmatism.
- Public vs. Private Use of Reason: To ensure societal progress, individuals must have absolute freedom to criticize publicly as scholars, but must strictly obey orders in their private civic duties to maintain institutional function.
- The Absolute Prohibition of Lying: Lying, even to prevent harm, subverts human dignity and destroys the mutual esteem necessary for any valid social contract or relationship.
For detailed rationale and quotes, see references/principles.md.
How Immanuel Kant reasons
When presented with a problem, Kant does not ask, "What will produce the best outcome?" Instead, he asks, "What is the underlying rule governing this action, and can it be applied universally?" He strips away empirical circumstances, emotions, and desires to find the pure, rational core of a duty.
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 23 KB
- _workspace/discovery/books.json 4.9 KB
- _workspace/discovery/essays.json 4.3 KB
- _workspace/discovery/frameworks.json 4.5 KB
- _workspace/discovery/interviews.json 4.7 KB
- _workspace/discovery/letters.json 4.7 KB
- _workspace/discovery/papers.json 4.1 KB
- _workspace/discovery/podcasts.json 4.5 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 12 KB
- _workspace/discovery/talks.json 4.5 KB
- _workspace/distilled/src_002.e584bd6c.json 6.7 KB
- _workspace/distilled/src_004.e584bd6c.json 6.9 KB
- _workspace/distilled/src_012.e584bd6c.json 482 B
- _workspace/distilled/src_016.e584bd6c.json 5.9 KB
- _workspace/distilled/src_020.e584bd6c.json 407 B
- _workspace/distilled/src_023.e584bd6c.json 5.0 KB
- _workspace/distilled/src_024.e584bd6c.json 6.6 KB
- _workspace/distilled/src_026.e584bd6c.json 3.0 KB
- _workspace/distilled/src_034.e584bd6c.json 578 B
- _workspace/distilled/src_035.e584bd6c.json 1.9 KB
- _workspace/distilled/src_036.e584bd6c.json 6.2 KB
- _workspace/distilled/src_040.e584bd6c.json 5.0 KB
- _workspace/distilled/src_041.e584bd6c.json 384 B
- _workspace/distilled/src_048.e584bd6c.json 688 B
- _workspace/distilled/src_050.e584bd6c.json 515 B
- _workspace/distilled/src_053.e584bd6c.json 538 B
- _workspace/distilled/src_055.e584bd6c.json 529 B
- _workspace/distilled/src_056.e584bd6c.json 6.1 KB
- _workspace/distilled/src_057.e584bd6c.json 1.7 KB
- _workspace/distilled/src_058.e584bd6c.json 442 B
- _workspace/distilled/src_060.e584bd6c.json 603 B
- _workspace/distilled/src_062.e584bd6c.json 1.3 KB
- _workspace/distilled/src_064.e584bd6c.json 564 B
- _workspace/distilled/src_066.e584bd6c.json 590 B
- _workspace/distilled/src_067.e584bd6c.json 5.6 KB
- _workspace/raw/src_002.json 15 KB
- _workspace/raw/src_004.json 51 KB
- _workspace/raw/src_012.json 4.4 KB
- _workspace/raw/src_016.json 50 KB
- _workspace/raw/src_020.json 515 B
- _workspace/raw/src_023.json 52 KB
- _workspace/raw/src_024.json 50 KB
- _workspace/raw/src_026.json 3.8 KB
- _workspace/raw/src_034.json 12 KB
- _workspace/raw/src_035.json 21 KB
- _workspace/raw/src_036.json 50 KB
- _workspace/raw/src_040.json 24 KB
- _workspace/raw/src_041.json 473 B
- _workspace/raw/src_048.json 4.1 KB
- _workspace/raw/src_050.json 24 KB
- _workspace/raw/src_053.json 2.4 KB
- _workspace/raw/src_055.json 1.3 KB
- _workspace/raw/src_056.json 13 KB
- _workspace/raw/src_057.json 16 KB
- _workspace/raw/src_058.json 9.9 KB
- _workspace/raw/src_060.json 9.1 KB
- _workspace/raw/src_062.json 2.9 KB
- _workspace/raw/src_064.json 30 KB
- _workspace/raw/src_066.json 5.3 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 · 66 lines · 110 tokens per session scan A 98fafd308a7f
immanuel-kant is a skill published in the GitHub repository K-Dense-AI/mimeographs (139 stars, last pushed 2mo ago), licensed MIT. It adds 110 tokens to every session and 1,327 once invoked, about $0.0004 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.
immanuel-kant compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| immanuel-kantK-Dense-AI/mimeographs | Skill | 139 | 2mo ago | MIT | A | 110 | Claude Code, Codex |
| hr-onboardingnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | yesterday | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | 25d ago | Apache-2.0 | A | 25 | Claude Code, Codex |