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 Aaryan-Kapoor/degreeworks-cli --skill skillgit clone --depth 1 https://github.com/Aaryan-Kapoor/degreeworks-cliWrote 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/aaryan-kapoor/degreeworks-cli/skill)<a href="https://agentmods.dev/skills/aaryan-kapoor/degreeworks-cli/skill"><img src="https://agentmods.dev/badge/skills/aaryan-kapoor/degreeworks-cli/skill/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/aaryan-kapoor/degreeworks-cli/skill"><img src="https://agentmods.dev/badge/skills/aaryan-kapoor/degreeworks-cli/skill.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 | $0.00081 | $0.02202 |
| Opus 5 | $0.00041 | $0.01101 |
| Sonnet 5 | $0.00016 | $0.00440 |
| Haiku 4.5 | $0.00008 | $0.00220 |
Grade A, and why
degreeworks 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 8d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KSU DegreeWorks — Schedule Planning & Degree Audit
You have access to the dw CLI, which pulls strictly read-only data from a
KSU student's DegreeWorks degree audit and course catalog. Your headline job:
build the student's exact next semester — pick real sections that fit their
constraints (credit load, no-early-classes, work days, campus, prof preferences),
with CRNs, days/times, instructors, and open seats, every prerequisite verified —
using the 8-phase protocol below. It also answers degree-progress and
remaining-requirement questions, but scheduling is the point.
Quick Reference
# Auth
dw login # opens a browser for KSU SSO — student logs in normally
dw login --headless # silently refresh from the saved browser session
dw whoami # student identity + token expiry (works even when expired)
# Diagnosis
dw doctor # setup/auth/API state with the exact next command to run
dw --json doctor # machine-readable
# Academic state
dw progress # % to graduation, per-requirement progress bars
dw remaining # every course still needed, grouped by requirement
dw completed # completed + in-progress courses, grouped by term, with grades
dw completed --transfers # include transfer credits
dw audit # full degree-audit tree with per-rule status
# Courses
dw course CS 3305 # description, parsed prereqs, and scheduled sections
dw course MATH 2202 # (DISCIPLINE NUMBER)
# Full snapshot (best for AI)
dw --md dump # everything: progress + in-progress + completed + remaining
dw --md dump --shallow # quick: progress + in-progress only
Global flags go before the subcommand: dw --md course CS 3305. Use --md
(markdown, best for AI) or --json (structured) whenever you process output.
Decision Tree
- Simple informational question ("what's my GPA?", "am I registered for MATH 2202?",
"how many credits left?") → run one
dwcommand and answer. No protocol needed. - Plan a semester / pick courses / build a schedule / "am I on track to graduate?" → follow the 8-phase Schedule Planning Protocol below, exactly. Do not skip phases, do not substitute memory for CLI verification, do not assume constraints.
- Auth error or unclear state → run
dw doctor(ordw whoami) and follow the recovery step it names.
What ships with it
2 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.
- 8d ago First seen · 192 lines · 81 tokens per session scan A 12d4376ff4da
degreeworks is a skill published in the GitHub repository Aaryan-Kapoor/degreeworks-cli (3 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 2,202 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.
Other skills, from other repositories
gws-classroom
Google Classroom: Manage classes, rosters, and coursework.
get-rep-call-feedback
Use when the user wants evidence-backed coaching for one rep's calls, especially by comparing the rep with peer examples to identify repeatable best practices, specific upgrade moments, and practical next-call language.
review-rep-call-trends
Use when the user wants to understand how a sales or customer-facing rep's call behavior is changing over time. Produce an evidence-backed trend readout with improvements, regressions, stable patterns, coaching actions, and calls to re-listen.
recipe-create-classroom-course
Create a Google Classroom course and invite students.
tutorial
Interactive tutorial teaching Ouroboros hands-on.
learn-everything
Turn an uploaded PDF, paper, book chapter, document, URL, or user-provided topic into a structured, interactive learning course. Use when the user wants to learn, study, understand, master, review, or practice a subject chapter by chapter; asks for a tutorial or curriculum from source material; wants exercises…