penn-course-mcp: Skill for Claude Code

.claude/skills/penn-course-planning/SKILL.md

penn-course-planning is a skill for Claude Code from grantdehoog/penn-course-mcp. It costs 87 tokens per session (1,542 once invoked), scanned A, original, MIT.

A course-planning assistant for the University of Pennsylvania, using the university's course catalogue and course-review data. It helps compare classes and build a weekly timetable.

In plain words
What is it for?
Use it to find Penn courses, read ratings and written reviews, compare difficulty or workload, check time conflicts and assemble a weekly schedule.
Why use it?
It removes the need to search several course pages manually and helps spot timetable clashes before choosing classes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is grantdehoog/penn-course-mcp's own configuration. It tells Claude Code how to work on penn-course-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything penn-course-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to grantdehoog/penn-course-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/grantdehoog/penn-course-mcp/main/.claude/skills/penn-course-planning/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/grantdehoog/penn-course-mcp

Made for: Claude Code.

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 penn-course-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/grantdehoog/penn-course-mcp/penn-course-planning/github.svg)](https://agentmods.dev/skills/grantdehoog/penn-course-mcp/penn-course-planning)
Your own site
<a href="https://agentmods.dev/skills/grantdehoog/penn-course-mcp/penn-course-planning"><img src="https://agentmods.dev/badge/skills/grantdehoog/penn-course-mcp/penn-course-planning/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 penn-course-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/grantdehoog/penn-course-mcp/penn-course-planning"><img src="https://agentmods.dev/badge/skills/grantdehoog/penn-course-mcp/penn-course-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,542 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 $0.00087 $0.01542
Opus 5 $0.00044 $0.00771
Sonnet 5 $0.00017 $0.00308
Haiku 4.5 $0.00009 $0.00154

Measured 10d ago against content hash abb857c2bd2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

penn-course-planning 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 10d 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.

.claude/skills/penn-course-planning/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Penn course planning

This skill drives the penn-course MCP server (tools are named search_courses, get_course_details, etc.). It talks to the public Penn Courses / Penn Course Review API, so data is real and current. No auth is required for catalog data and aggregate ratings.

Detailed reviews are enabled on this setup: a logged-in Penn session cookie (PENN_COURSES_SESSION_COOKIE) is configured, so get_course_reviews returns full per-instructor written reviews — not just aggregates. Call get_current_semester to confirm (reviews_enabled: true). The session cookie expires periodically (logout / Penn timeout); when it lapses, get_course_reviews silently falls back to public aggregates and reports auth_status: unauthenticated — that's the cue to refresh the cookie, not a bug.

Conventions (read first)

  • Course codes: SUBJECT-NUMBER, e.g. CIS-1200, MATH-1400, ECON-0100. Always hyphenated and uppercase. If the user writes "CIS 120" or "cis120", normalize to CIS-1200 (Penn moved to 4-digit codes; CIS-120CIS-1200, CIS-160CIS-1600).
  • Section ids: course code + 3-digit section, e.g. CIS-1200-001.
  • Semester: term code like 2026C (A=spring, B=summer, C=fall). Omit the semester argument to use the current term; call get_current_semester first if unsure.
  • Ratings scale: roughly 0–4. Higher course_quality / instructor_quality is better; lower difficulty and work_required mean a lighter course. Some courses are unrated (null) — say so rather than treating null as 0.
  • Meeting times come back already formatted as HH:MM ranges with day codes M T W R F (R = Thursday). Don't re-parse Penn's raw HH.MM encoding yourself.

Tools at a glance

Goal Tool
Current term + auth status get_current_semester
Find courses by keyword/code search_courses
Full course info + sections get_course_details
Just the sections/meeting times list_course_sections (filters: open_only, activity)
Aggregate ratings get_course_ratings
Detailed PCR reviews get_course_reviews (falls back to aggregates if unauthenticated)
Courses with an attribute / Gen-Ed find_courses_by_attribute
Courses fulfilling a requirement find_courses_by_requirement
Do these sections clash? check_schedule_conflicts
Build a weekly schedule build_schedule
Rank by quality/difficulty/workload recommend_courses (sort_by=...)
Side-by-side comparison compare_courses
List your saved PCP schedules list_schedules (requires auth)
Save a schedule to penncourseplan.com save_schedule (requires auth — writes to your account)
Delete a saved schedule delete_schedule (requires auth)

Read the full file on GitHub · 100 lines

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. 10d ago First seen · 100 lines · 87 tokens per session scan A abb857c2bd2d

Subscribe to this mod's changes

penn-course-planning is a skill published in the GitHub repository grantdehoog/penn-course-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,542 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 2026-08-31.

Related

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".

nexu-io/open-design · 62 tokens

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…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

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.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

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.

xr843/Master-skill · 274 tokens