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 hannah-arendtgit 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/hannah-arendt)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/hannah-arendt"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/hannah-arendt/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/hannah-arendt"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/hannah-arendt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium YARA Match · line 10 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00128 | $0.01305 |
| Opus 5.5 | $0.00051 | $0.00522 |
| Sonnet 5.5 | $0.00026 | $0.00261 |
| Haiku 4.5 | $0.00013 | $0.00130 |
Grade A, and why
hannah-arendt 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Hannah Arendt
Hannah Arendt was a political theorist who sought to understand the unprecedented horrors of the 20th century with "eyes unclouded by philosophy." Unlike traditional philosophers who often harbored a hostility toward human action in favor of solitary contemplation, Arendt centered her thought on the public realm, human plurality, and the capacity for individuals to begin something entirely new.
Her signature intellectual move is dismantling abstract, deterministic explanations for human behavior and replacing them with a fierce focus on concrete reality, individual responsibility, and the active process of thinking. She recognized that the greatest evils are rarely committed by sociopaths or ideological fanatics, but by ordinary people who simply fail to stop and think about what they are doing.
Reach for this skill whenever you're helping a user navigate bureaucratic complicity, evaluate political power dynamics, assess moral responsibility in complex systems, or find agency in seemingly deterministic situations.
Core principles
- The Banality of Evil as Thoughtlessness: Monstrous deeds are often committed by ordinary people who lack firm ideological convictions but simply fail to stop and think about their actions outside of routine procedures.
- Human Plurality as the Condition of Political Life: Action and politics require distinct individuals interacting with one another; if humans were endlessly reproducible repetitions of the same model, action would be an unnecessary luxury.
- Power vs. Violence: Power arises only when people act in concert through persuasion and consent, whereas violence is fundamentally instrumental and relies on coercion.
- Concrete Defense of Identity: When attacked as a member of a specific group, you must defend yourself concretely as a member of that group, not with abstract universal concepts.
- Preservation of Factual Truth: Factual truths must be told and protected, regardless of whose political interests they might offend, because they form the shared reality of the world.
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 12 KB
- _workspace/clustered_corpus.e584bd6c.json 31 KB
- _workspace/discovery/books.json 10.0 KB
- _workspace/discovery/essays.json 10 KB
- _workspace/discovery/frameworks.json 8.7 KB
- _workspace/discovery/interviews.json 7.6 KB
- _workspace/discovery/letters.json 8.5 KB
- _workspace/discovery/papers.json 7.8 KB
- _workspace/discovery/podcasts.json 9.9 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 27 KB
- _workspace/discovery/talks.json 8.8 KB
- _workspace/distilled/src_003.e584bd6c.json 7.0 KB
- _workspace/distilled/src_007.e584bd6c.json 597 B
- _workspace/distilled/src_009.e584bd6c.json 7.6 KB
- _workspace/distilled/src_011.e584bd6c.json 7.3 KB
- _workspace/distilled/src_014.e584bd6c.json 7.2 KB
- _workspace/distilled/src_019.e584bd6c.json 6.7 KB
- _workspace/distilled/src_021.e584bd6c.json 6.4 KB
- _workspace/distilled/src_022.e584bd6c.json 1.3 KB
- _workspace/distilled/src_023.e584bd6c.json 6.4 KB
- _workspace/distilled/src_024.e584bd6c.json 7.8 KB
- _workspace/distilled/src_026.e584bd6c.json 1.3 KB
- _workspace/distilled/src_030.e584bd6c.json 1.0 KB
- _workspace/distilled/src_031.e584bd6c.json 424 B
- _workspace/distilled/src_034.e584bd6c.json 8.0 KB
- _workspace/distilled/src_036.e584bd6c.json 3.1 KB
- _workspace/distilled/src_037.e584bd6c.json 696 B
- _workspace/distilled/src_038.e584bd6c.json 3.9 KB
- _workspace/distilled/src_044.e584bd6c.json 1.4 KB
- _workspace/distilled/src_047.e584bd6c.json 1.2 KB
- _workspace/distilled/src_050.e584bd6c.json 3.1 KB
- _workspace/distilled/src_052.e584bd6c.json 6.4 KB
- _workspace/distilled/src_054.e584bd6c.json 1.1 KB
- _workspace/distilled/src_056.e584bd6c.json 369 B
- _workspace/distilled/src_057.e584bd6c.json 7.0 KB
- _workspace/distilled/src_058.e584bd6c.json 484 B
- _workspace/raw/src_003.json 50 KB
- _workspace/raw/src_007.json 3.6 KB
- _workspace/raw/src_009.json 51 KB
- _workspace/raw/src_011.json 49 KB
- _workspace/raw/src_014.json 51 KB
- _workspace/raw/src_019.json 47 KB
- _workspace/raw/src_021.json 30 KB
- _workspace/raw/src_022.json 4.7 KB
- _workspace/raw/src_023.json 17 KB
- _workspace/raw/src_024.json 56 KB
- _workspace/raw/src_026.json 2.3 KB
- _workspace/raw/src_030.json 6.8 KB
- _workspace/raw/src_031.json 477 B
- _workspace/raw/src_034.json 50 KB
- _workspace/raw/src_036.json 14 KB
- _workspace/raw/src_037.json 435 B
- _workspace/raw/src_038.json 51 KB
- _workspace/raw/src_044.json 5.3 KB
- _workspace/raw/src_047.json 420 B
- _workspace/raw/src_050.json 31 KB
- _workspace/raw/src_052.json 51 KB
- _workspace/raw/src_054.json 4.4 KB
- _workspace/raw/src_056.json 5.7 KB
- _workspace/raw/src_057.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 · 63 lines · 128 tokens per session scan A 6c460e8851ab
hannah-arendt is a skill published in the GitHub repository K-Dense-AI/mimeographs (139 stars, last pushed 2mo ago), licensed MIT. It adds 128 tokens to every session and 1,305 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.
hannah-arendt compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hannah-arendtK-Dense-AI/mimeographs | Skill | 139 | 2mo ago | MIT | A | 128 | 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 |