degreeworks-cli: Skill for Claude Code

.claude/skills/degreeworks/SKILL.md

degreeworks is a skill for Claude Code from Aaryan-Kapoor/degreeworks-cli. It costs 81 tokens per session (524 once invoked), scanned A, original, MIT.

A planning method for KSU students that uses their DegreeWorks audit and course catalogue to build a verified next-semester schedule. DegreeWorks is a university system showing academic progress, requirements, and registration information.

In plain words
What is it for?
Use it to check academic progress, find real course sections and times, verify prerequisites, and plan a semester.
Why use it?
It helps avoid choosing unavailable sections, missing prerequisites, or building a schedule that conflicts with the student's actual degree progress.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is Aaryan-Kapoor/degreeworks-cli's own configuration. It tells Claude Code how to work on degreeworks-cli 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 degreeworks-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Aaryan-Kapoor/degreeworks-cli. 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/Aaryan-Kapoor/degreeworks-cli/main/.claude/skills/degreeworks/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Aaryan-Kapoor/degreeworks-cli

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 degreeworks

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaryan-kapoor/degreeworks-cli/degreeworks/github.svg)](https://agentmods.dev/skills/aaryan-kapoor/degreeworks-cli/degreeworks)
Your own site
<a href="https://agentmods.dev/skills/aaryan-kapoor/degreeworks-cli/degreeworks"><img src="https://agentmods.dev/badge/skills/aaryan-kapoor/degreeworks-cli/degreeworks/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 degreeworks

Your own site · 80×15
<a href="https://agentmods.dev/skills/aaryan-kapoor/degreeworks-cli/degreeworks"><img src="https://agentmods.dev/badge/skills/aaryan-kapoor/degreeworks-cli/degreeworks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 524 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 $0.00081 $0.00524
Opus 5 $0.00041 $0.00262
Sonnet 5 $0.00016 $0.00105
Haiku 4.5 $0.00008 $0.00052

Measured 11d ago against content hash 83c4528e0871, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 11d 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/degreeworks/SKILL.md · 32 lines

What it actually says

DegreeWorks Skill

You have access to the read-only dw CLI which pulls KSU DegreeWorks data. Use it to help the student understand their academic progress and plan future semesters.

Before anything else: read AGENTS.md

Your first action when this skill is invoked is to read AGENTS.md in the project root. It contains:

  • The full 8-phase Schedule Planning Protocol — follow it exactly when the student asks you to plan a semester, pick courses, or build a schedule
  • The complete dw command reference with every flag
  • Auth recovery procedures, config env vars, grade codes, and read-only safety rules

AGENTS.md is the single source of truth for this project and is shared across every agent harness. It supersedes anything you think you remember about the CLI.

Quick decision tree

  • Student asks a simple informational question (e.g. "what's my GPA?", "am I registered for MATH 2202?") → run one dw command and answer. No protocol needed.
  • Student asks to plan a semester, pick courses, or build a schedule → follow the 8-phase protocol in AGENTS.md exactly. Do not skip phases, do not substitute memory for CLI verification, do not assume constraints.
  • Auth errors or unclear statedw whoami first, then follow the recovery procedure in AGENTS.md.

Why read AGENTS.md instead of embedding the instructions here

There is one source of truth so agent instructions don't drift across harnesses. CLAUDE.md imports AGENTS.md at session start (so it's already in context in Claude Code), and this skill explicitly reads it too — both because skills can be invoked inside forked subagent contexts where CLAUDE.md may not be loaded, and so that any update to AGENTS.md is picked up immediately without needing to touch this file.

Do not add instructions here. Update AGENTS.md in the project root.

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. 11d ago First seen · 32 lines · 81 tokens per session scan A 83c4528e0871

Subscribe to this mod's changes

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 524 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.