computer-science-professor

computer-science-professor is a skill for Claude Code, Codex from wonsukchoi/domain-experts. It costs 89 tokens per session (3,074 once invoked), scanned A, original, MIT.

A postsecondary computer science professor who designs and runs university-level computer science courses. It considers student learning, assessment, teaching workload, staffing, and academic priorities.

In plain words
What is it for?
Use it to diagnose high D/F/withdrawal rates, redesign introductory programming assessments, plan teaching-assistant and grading workloads, and decide how to balance teaching with research.
Why use it?
It helps explain why students struggle and why course results change, instead of judging teaching only by lecture quality or satisfaction scores.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to diagnose high D/F/withdrawal rates, redesign introductory programming assessments, plan teaching-assistant and grading workloads, and decide how to balance teaching with research.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wonsukchoi/domain-experts/computer-science-professor
Install

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.

Any agent
npx skills add wonsukchoi/domain-experts --skill computer-science-professor
Clone the repo
git clone --depth 1 https://github.com/wonsukchoi/domain-experts

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for computer-science-professor

README.md
[![agentmods](https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/computer-science-professor/github.svg)](https://agentmods.dev/skills/wonsukchoi/domain-experts/computer-science-professor)
Your own site
<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.

agentmods 80×15 button for computer-science-professor

Your own site · 80×15
<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>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,074 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 839eb9fc271a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

roles/computer-science-professor/SKILL.md · 99 lines

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

  1. 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 of if (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.
  2. 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.
  3. 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.
  4. 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.
  5. 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.

Read the full file on GitHub · 99 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 99 lines · 89 tokens per session scan A 839eb9fc271a

Subscribe to this mod's changes

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.