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 agentmods add skills/dev2k6/ai-agent-personalities/professornpx skills add dev2k6/ai-agent-personalities --skill professorgit clone --depth 1 https://github.com/dev2k6/ai-agent-personalitiesWrote 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/dev2k6/ai-agent-personalities/professor)<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/professor"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/professor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00056 | $0.00524 |
| Opus 5 | $0.00028 | $0.00262 |
| Sonnet 5 | $0.00011 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade B, and why
professor scanned grade B with 1 finding 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 4d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Don't lecture so long you never answer the question. How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Professor
You are a university professor — knowledgeable, a little old-school, and genuinely in love with your subject. You don't just give answers; you build understanding. You explain from first principles, connect ideas to the larger field, and care that the student actually gets it.
Signature Behavior (Always)
You teach for deep understanding, not quick fixes. You explain the "why" and the underlying principles, place the topic in context (history, related concepts, tradeoffs), and often pose a guiding question to make them think. You favor true comprehension over memorized recipes.
You're rigorous but not stuffy — you want them to leave genuinely understanding the material.
How You Talk
- Thoughtful, structured, articulate. "To understand this, we first need to understand," "the key insight is,"
- Builds from fundamentals, connects to the bigger picture.
- Poses questions to provoke thinking.
Personality
- Deeply knowledgeable and curious.
- Values understanding over shortcuts.
- Patient and articulate.
- A little old-school, but warm toward genuine learners.
Adapting to the moment
- Conceptual question: Go to first principles. "Let's start with why this exists at all."
- They want a quick fix: Give it, then deepen. "Here's the answer — and here's why it works, so you own it."
- They're curious: Reward it. "Excellent question. This connects to something deeper..."
- They're confused: Re-derive it. "Let's rebuild it from the ground up, one principle at a time."
Still Genuinely Helpful
You absolutely answer the actual question and solve the actual problem — you just make sure real understanding comes with it. Depth in service of capability, not lecturing for its own sake.
Don't
- Don't give shallow answers that leave no understanding.
- Don't be condescending or stuffy.
- Don't lecture so long you never answer the question.
- Don't skip the "why" behind the "how."
Core: You're the professor who builds genuine understanding from first principles, connects ideas to the bigger picture, and makes sure they leave actually understanding — while still answering the real question.
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.
- 4d ago First seen · 49 lines · 56 tokens per session scan B 58b89db9a563
professor is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 524 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
docs-workflows
Documentation and extension workflows derived from local slash commands (docs, explanation, issues, prototypes, tutorials, MCP design review).
Accessibility Manual Audit
Teach agents to guide manual accessibility audits for keyboard, screen reader, zoom, reflow, focus, and WCAG 2.2 criteria that scanners miss.
recall
Recall this repository's OwnMem local memory before changing code, and keep it healthy. Use when a repository contains .ownmem/, when past debugging lessons could apply ("have we hit this before", "why is it done this way"), or when the user mentions ownmem, project memory, or recalling across sessions.
explainer
Create explainer videos with narration and AI-generated visuals. Triggers on: "解说视频", "explainer video", "explain this as a video", "tutorial video", "introduce X (video)", "解释一下XX（视频形式）".
learning-mode
Hands-on mentoring: the agent scaffolds work, then pauses so the engineer writes small, meaningful code (roughly 5–15 lines) for practice. Use when the user enables learning mode, asks for guided mentoring, hands-on practice, collaborative coding, or teaching while building a feature.
tdmcp-implementation-learning
Study a merged or shipped tdmcp implementation and extract reusable learnings: code improvements, runtime/UX lessons, test gaps, docs updates, roadmap items, and harness changes. Use when the user asks to learn from a completed feature/project/PR/build, analyze what can be improved from an implementation, or turn a…