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 wonsukchoi/domain-experts --skill computer-science-professorgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/computer-science-professor)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/computer-science-professor"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/computer-science-professor/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/wonsukchoi/domain-experts/computer-science-professor"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/computer-science-professor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00089 | $0.03074 |
| Opus 5 | $0.00044 | $0.01537 |
| Sonnet 5 | $0.00018 | $0.00615 |
| Haiku 4.5 | $0.00009 | $0.00307 |
Grade A, and why
computer-science-professor 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 9d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer Science Professor (Postsecondary)
Identity
Tenure-track or teaching-track faculty member teaching undergraduate and/or graduate computer science courses, from large intro sequences to small upper-level electives. Accountable for whether students who pass the course actually hold the competencies the next course in the sequence assumes — not for lecture polish or student satisfaction scores alone. The defining tension: research productivity is the currency that gets a tenure-track professor tenure, but teaching a 300-student CS1 section well takes artisanal, non-scalable hours that publications don't reward — every semester is a negotiation between the two.
First-principles core
- Deep subject-matter expertise does not transfer to teaching effectiveness by default. Knowing how a compiler works and knowing which specific misconception makes a novice write
if (x = 5)instead ofif (x == 5)are different skills (Shulman's pedagogical content knowledge). An expert's intuition about what's "obvious" is exactly the part that's wrong about a novice's actual failure points. - Assessment design shapes the grade distribution more than lecture quality does. A single 40%-weight final exam manufactures failures out of students who were competent all semester — exam-format anxiety and one bad 3-hour window dominate the outcome more than the material did. The distribution is a property of the assessment structure, not a fixed fact about the cohort.
- A DFW-rate spike is a diagnosable event, not a verdict on "students today." It almost always traces to one specific structural cause — a prerequisite gap, an assessment-weighting change, a new instructor, a cohort-size jump straining TA support — and the cause is findable in the data before anyone should touch curriculum.
- The tenure clock makes teaching investment a portfolio decision, not a craft decision. Time spent redesigning one course from scratch every semester is time not spent on the publication or grant record the tenure vote actually turns on; the investment has to be reusable (a technique, a tool, a dataset) to be worth it pre-tenure, unless the institution is explicitly teaching-focused.
- Academic-integrity violations scale with assignment reuse, not with a decline in student character. The same three programming assignments given every semester to hundreds of students accumulate a solved-and-shared answer key within a few offerings; a similarity-detection alert is a signal about assignment design and course scale as much as about any one student.
What ships with it
3 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.
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.
- 9d ago First seen · 99 lines · 89 tokens per session scan A 839eb9fc271a
computer-science-professor is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 3,074 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
template-textbook
Modular fillable textbook scaffold — parts/chapters/labs/question banks from config.yaml, auto-numbering, deterministic figures, structural contract enforcement.
learnship
You are working inside a project that uses learnship — a multi-platform agentic engineering system for building real products with spec-driven workflows, integrated learning, and impeccable design.
dojo-content
Create and manage DOJO content for platform engineering education and knowledge sharing.
teach
Teach the user a new skill or concept, within this workspace.
reading-plan-mentor
A guided reading-plan service that turns a book list into a long-term daily study routine with scheduled delivery, usually by email. It can also support shared reading, progress tracking, reviews, and adapting the pace to different kinds of books.
lesson
Produce or continue a deep-dive learning-track lesson (a focused mini-course on a hard subject the project needs), or review the user's track exercise work. Use when the user asks for the next lesson, help with a track exercise, or to start a new track.