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 elizabeth-anscombegit 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/elizabeth-anscombe)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/elizabeth-anscombe"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/elizabeth-anscombe/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/elizabeth-anscombe"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/elizabeth-anscombe.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 | $0.00113 | $0.01136 |
| Opus 5.5 | $0.00045 | $0.00454 |
| Sonnet 5.5 | $0.00023 | $0.00227 |
| Haiku 4.5 | $0.00011 | $0.00114 |
Grade A, and why
elizabeth-anscombe 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Elizabeth Anscombe
Elizabeth Anscombe was a formidable British analytic philosopher who fundamentally reshaped action theory and virtue ethics. Her signature intellectual move is demanding clarity on the philosophy of psychology before allowing any moral judgments to proceed. She refuses to evaluate whether an action is "right" or "wrong" until she has precisely defined what the action is, under what description it is intentional, and what institutional facts make it intelligible.
Anscombe is fiercely anti-consequentialist. She rejects the modern tendency to weigh human lives in utilitarian calculus, insisting that the objective structure of an action matters more than the agent's private "direction of intention" or desired outcomes.
Reach for this skill whenever you're analyzing moral dilemmas, ethical trade-offs, questions of culpability, or the nature of human intention and agency.
Core principles
- Moral Philosophy Requires Psychology: Suspend moral judgments until you have an adequate philosophy of psychology; you cannot evaluate an action without understanding motive and intention.
- Abandon Secular 'Moral Oughts': Drop terms like "moral obligation" in secular contexts, as they are meaningless survivals of a divine law framework and only exert unjustified psychological force.
- Absolute Prohibition on Murder: Never choose to kill the innocent as a means to an end, regardless of the consequences; the objective structure of the act cannot be excused by "good" ends.
- Action Under a Description: Evaluate human actions based on specific descriptions, because an action might be intentional under one description (pumping water) but not another (poisoning the inhabitants).
For detailed rationale and quotes, see references/principles.md.
How Elizabeth Anscombe reasons
Anscombe begins by interrogating the action itself. She asks, "Why are you doing that?" to determine if an action is intentional under a specific description. She dismisses vague, "thin" moral concepts like "right" and "wrong," preferring "thick" descriptive concepts like "just," "unjust," or "cowardly." She completely rejects the idea that a good outcome can retroactively justify an intrinsically evil act.
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 21 KB
- _workspace/discovery/books.json 10.0 KB
- _workspace/discovery/essays.json 11 KB
- _workspace/discovery/frameworks.json 11 KB
- _workspace/discovery/interviews.json 10 KB
- _workspace/discovery/letters.json 9.6 KB
- _workspace/discovery/papers.json 9.1 KB
- _workspace/discovery/podcasts.json 7.9 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 30 KB
- _workspace/discovery/talks.json 5.6 KB
- _workspace/distilled/src_001.e584bd6c.json 1.5 KB
- _workspace/distilled/src_003.e584bd6c.json 5.7 KB
- _workspace/distilled/src_005.e584bd6c.json 3.6 KB
- _workspace/distilled/src_009.e584bd6c.json 1.3 KB
- _workspace/distilled/src_010.e584bd6c.json 7.5 KB
- _workspace/distilled/src_011.e584bd6c.json 5.6 KB
- _workspace/distilled/src_012.e584bd6c.json 6.3 KB
- _workspace/distilled/src_018.e584bd6c.json 4.2 KB
- _workspace/distilled/src_021.e584bd6c.json 2.0 KB
- _workspace/distilled/src_022.e584bd6c.json 5.6 KB
- _workspace/distilled/src_023.e584bd6c.json 1.2 KB
- _workspace/distilled/src_024.e584bd6c.json 1.7 KB
- _workspace/distilled/src_026.e584bd6c.json 2.7 KB
- _workspace/distilled/src_028.e584bd6c.json 608 B
- _workspace/distilled/src_034.e584bd6c.json 8.7 KB
- _workspace/distilled/src_036.e584bd6c.json 5.8 KB
- _workspace/distilled/src_037.e584bd6c.json 536 B
- _workspace/distilled/src_038.e584bd6c.json 419 B
- _workspace/distilled/src_039.e584bd6c.json 5.9 KB
- _workspace/distilled/src_042.e584bd6c.json 373 B
- _workspace/distilled/src_045.e584bd6c.json 567 B
- _workspace/distilled/src_047.e584bd6c.json 447 B
- _workspace/distilled/src_048.e584bd6c.json 1.7 KB
- _workspace/distilled/src_049.e584bd6c.json 3.7 KB
- _workspace/distilled/src_050.e584bd6c.json 6.2 KB
- _workspace/raw/src_001.json 3.7 KB
- _workspace/raw/src_003.json 49 KB
- _workspace/raw/src_005.json 20 KB
- _workspace/raw/src_009.json 28 KB
- _workspace/raw/src_010.json 37 KB
- _workspace/raw/src_011.json 54 KB
- _workspace/raw/src_012.json 36 KB
- _workspace/raw/src_018.json 53 KB
- _workspace/raw/src_021.json 768 B
- _workspace/raw/src_022.json 35 KB
- _workspace/raw/src_023.json 4.5 KB
- _workspace/raw/src_024.json 2.0 KB
- _workspace/raw/src_026.json 14 KB
- _workspace/raw/src_028.json 1.5 KB
- _workspace/raw/src_034.json 51 KB
- _workspace/raw/src_036.json 49 KB
- _workspace/raw/src_037.json 3.0 KB
- _workspace/raw/src_038.json 8.9 KB
- _workspace/raw/src_039.json 52 KB
- _workspace/raw/src_042.json 1.5 KB
- _workspace/raw/src_045.json 5.2 KB
- _workspace/raw/src_047.json 5.8 KB
- _workspace/raw/src_048.json 12 KB
- _workspace/raw/src_049.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.
- 2mo ago First seen · 55 lines · 113 tokens per session scan A 565e783dfd00
elizabeth-anscombe is a skill published in the GitHub repository K-Dense-AI/mimeographs (139 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 1,136 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.
elizabeth-anscombe compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| elizabeth-anscombeK-Dense-AI/mimeographs | Skill | 139 | 2mo ago | MIT | A | 113 | 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 | 24d ago | Apache-2.0 | A | 25 | Claude Code, Codex |