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 aaditsingh07/ucla-soc-mcp --skill schedule-planninggit clone --depth 1 https://github.com/aaditsingh07/ucla-soc-mcpWrote 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/aaditsingh07/ucla-soc-mcp/schedule-planning)<a href="https://agentmods.dev/skills/aaditsingh07/ucla-soc-mcp/schedule-planning"><img src="https://agentmods.dev/badge/skills/aaditsingh07/ucla-soc-mcp/schedule-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.
<a href="https://agentmods.dev/skills/aaditsingh07/ucla-soc-mcp/schedule-planning"><img src="https://agentmods.dev/badge/skills/aaditsingh07/ucla-soc-mcp/schedule-planning.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 | $0.00049 | $0.01550 |
| Opus 5 | $0.00024 | $0.00775 |
| Sonnet 5 | $0.00010 | $0.00310 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
schedule-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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UCLA Schedule Planning
Overview
Guided workflow for planning a UCLA student's class schedule for one term, ending in a rendered mock-schedule artifact. Core principle: verify, don't assume — the term, the student's requirements, every prerequisite, and every conflict get an explicit check, and the student confirms anything the data cannot.
Uses the ucla-soc MCP tools (list_terms, search_courses, get_course_details, get_class_detail, get_course_description, parse_degree_audit, estimate_walk_time, list_buildings). All schedule data is the public Schedule of Classes — unofficial and subject to registrar change.
Create a todo for each step below and work them in order. Steps 2 and 3 may be asked in one message; nothing else merges.
Step 1 — Confirm the term
Call list_terms. Infer the term being planned from today's date (students usually plan the next term; the registrar's SoC default term is marked in the output). Explicitly state the inference and get confirmation — e.g. "It's early August 2026, so I'll assume you're planning Fall 2026 — is that right?" If the date or context leaves the term genuinely ambiguous, ask instead of inferring.
Step 2 — Ask what they want or need to take
Ask whether they have specific courses they want or need this term: required courses, courses of interest, a target unit load. Record answers; do not skip this step even though the degree audit in Step 3 will also suggest courses.
Step 3 — Get course history and remaining requirements (DAR)
Request a Degree Audit Report with these exact instructions to the student:
- Go to dars.ucla.edu and sign in.
- Run a new audit for your program and open it (the Audit Results tab).
- Press Ctrl+S (Cmd+S on Mac) in your browser and save it as an HTML file (single file or complete webpage).
- Tell me the saved file's path (or drag the file into the chat).
Parse it with parse_degree_audit (use status_filter: "unfulfilled" first, then widen as needed). If the student can't or won't provide a DAR, ask for course history plus remaining requirements in any form (pasted transcript, typed list) before continuing.
What ships with it
1 file 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.
- 10d ago First seen · 81 lines · 49 tokens per session scan A 03d51fc2fc25
schedule-planning is a skill published in the GitHub repository aaditsingh07/ucla-soc-mcp (0 stars, last pushed 1mo ago), licensed Unlicense. It adds 49 tokens to every session and 1,550 once invoked, about $0.0002 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
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".
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…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
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.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
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.