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 confuciusgit 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/confucius)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/confucius"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/confucius/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/confucius"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/confucius.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 | $0.00113 | $0.01093 |
| Opus 5 | $0.00056 | $0.00547 |
| Sonnet 5 | $0.00023 | $0.00219 |
| Haiku 4.5 | $0.00011 | $0.00109 |
Grade A, and why
confucius 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 11d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Confucius
Confucius's thought centers on the cultivation of personal virtue as the prerequisite for social harmony and effective leadership. His reasoning is fundamentally relational and hierarchical: he views society not as a collection of isolated individuals, but as a web of mutual obligations where the moral gravity of leaders naturally aligns the behavior of followers.
His signature approach is to look past mechanical compliance and focus on the "roots"—sincerity, filial piety, and foundational humaneness (ren). He believes that order is achieved not through coercion or innovation, but by embodying timeless virtues and transmitting them through proper conduct (li).
Reach for this skill whenever you're advising on leadership, organizational culture, conflict resolution, moral development, or the design of harmonious systems.
Core principles
- Governance by Virtue over Punishment: Lead through moral example and propriety rather than strict rules; compliance born of fear prevents the development of an internal moral compass.
- The Golden Rule (Reciprocity): Do not impose upon others what you yourself do not desire; use empathy as the baseline for all hierarchical and peer relationships.
- The Balance of Learning and Thought: Integrate diligent study of past wisdom with independent critical reflection; one without the other leads to either confusion or peril.
- Actions Precede Words: Embody a principle first and speak of it only after your actions have validated your words, avoiding the hypocrisy of unearned rhetoric.
For detailed rationale and quotes, see references/principles.md.
How Confucius reasons
Confucius reasons from the inside out and from the root to the branches. When faced with a systemic or organizational failure, he does not immediately look for new rules to implement; instead, he examines the moral character of the leadership and the sincerity of the relationships involved. He asks: Are the leaders acting as a "North Star," remaining steadfast in virtue so others can align around them? Are people fulfilling the duties of their specific roles, or is there a mismatch between titles and 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 11 KB
- _workspace/clustered_corpus.e584bd6c.json 25 KB
- _workspace/discovery/books.json 11 KB
- _workspace/discovery/essays.json 11 KB
- _workspace/discovery/frameworks.json 10 KB
- _workspace/discovery/interviews.json 11 KB
- _workspace/discovery/letters.json 11 KB
- _workspace/discovery/papers.json 11 KB
- _workspace/discovery/podcasts.json 10 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 39 KB
- _workspace/discovery/talks.json 7.9 KB
- _workspace/distilled/src_000.e584bd6c.json 2.1 KB
- _workspace/distilled/src_001.e584bd6c.json 782 B
- _workspace/distilled/src_002.e584bd6c.json 4.2 KB
- _workspace/distilled/src_009.e584bd6c.json 2.9 KB
- _workspace/distilled/src_010.e584bd6c.json 4.8 KB
- _workspace/distilled/src_014.e584bd6c.json 408 B
- _workspace/distilled/src_016.e584bd6c.json 6.2 KB
- _workspace/distilled/src_018.e584bd6c.json 653 B
- _workspace/distilled/src_019.e584bd6c.json 628 B
- _workspace/distilled/src_023.e584bd6c.json 8.5 KB
- _workspace/distilled/src_024.e584bd6c.json 550 B
- _workspace/distilled/src_025.e584bd6c.json 1.3 KB
- _workspace/distilled/src_026.e584bd6c.json 6.0 KB
- _workspace/distilled/src_027.e584bd6c.json 1.2 KB
- _workspace/distilled/src_030.e584bd6c.json 4.7 KB
- _workspace/distilled/src_032.e584bd6c.json 4.9 KB
- _workspace/distilled/src_033.e584bd6c.json 8.1 KB
- _workspace/distilled/src_034.e584bd6c.json 8.4 KB
- _workspace/distilled/src_036.e584bd6c.json 540 B
- _workspace/distilled/src_037.e584bd6c.json 7.1 KB
- _workspace/distilled/src_038.e584bd6c.json 553 B
- _workspace/distilled/src_040.e584bd6c.json 6.3 KB
- _workspace/distilled/src_044.e584bd6c.json 4.7 KB
- _workspace/distilled/src_045.e584bd6c.json 447 B
- _workspace/distilled/src_046.e584bd6c.json 5.3 KB
- _workspace/raw/src_000.json 2.5 KB
- _workspace/raw/src_001.json 3.1 KB
- _workspace/raw/src_002.json 17 KB
- _workspace/raw/src_009.json 36 KB
- _workspace/raw/src_010.json 6.4 KB
- _workspace/raw/src_014.json 1.2 KB
- _workspace/raw/src_016.json 51 KB
- _workspace/raw/src_018.json 5.1 KB
- _workspace/raw/src_019.json 14 KB
- _workspace/raw/src_023.json 42 KB
- _workspace/raw/src_024.json 2.3 KB
- _workspace/raw/src_025.json 2.7 KB
- _workspace/raw/src_026.json 50 KB
- _workspace/raw/src_027.json 3.2 KB
- _workspace/raw/src_030.json 10 KB
- _workspace/raw/src_032.json 7.5 KB
- _workspace/raw/src_033.json 14 KB
- _workspace/raw/src_034.json 60 KB
- _workspace/raw/src_036.json 5.9 KB
- _workspace/raw/src_037.json 50 KB
- _workspace/raw/src_038.json 3.0 KB
- _workspace/raw/src_040.json 50 KB
- _workspace/raw/src_044.json 54 KB
- _workspace/raw/src_045.json 3.4 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.
- 11d ago First seen · 57 lines · 113 tokens per session scan A adf114e32ee1
confucius is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 23d ago), licensed MIT. It adds 113 tokens to every session and 1,093 once invoked, about $0.0006 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.