agentmods.dev

study

study is a skill for Claude Code from lsh1215/oh-my-study-with-me. It costs 43 tokens per session (3,112 once invoked), scanned A, original, MIT.

A guided study workflow based on first-principles reasoning, source reading, Socratic questions, and checking understanding. TDD here means type-based verification, where ideas are tested against their category or kind.

In plain words
What is it for?
It helps select and read a source, break it into sections, identify core principles, discuss them through questions, and continue from saved study progress.
Why use it?
It turns a book, article, code repository, or video into an interactive learning session instead of only producing a summary.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the oh-my-study-with-me plugin — 6 skills, 1 hook shipped together

not rated 8repo 6mo ago A scan 43 tokens original MIT

Good fit It helps select and read a source, break it into sections, identify core principles, discuss them through questions, and continue from saved study progress.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lsh1215/oh-my-study-with-me/study
View source ↗ lsh1215/oh-my-study-with-me sanghun-plugin.vercel.app
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 lsh1215/oh-my-study-with-me --skill study
Clone the repo
git clone --depth 1 https://github.com/lsh1215/oh-my-study-with-me

Made for: Claude Code.

Or install oh-my-study-with-me, the plugin that ships this one along with the rest of its 6 skills, 1 hook.

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 study

README.md
[![agentmods](https://agentmods.dev/badge/skills/lsh1215/oh-my-study-with-me/study/github.svg)](https://agentmods.dev/skills/lsh1215/oh-my-study-with-me/study)
Your own site
<a href="https://agentmods.dev/skills/lsh1215/oh-my-study-with-me/study"><img src="https://agentmods.dev/badge/skills/lsh1215/oh-my-study-with-me/study/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 study

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsh1215/oh-my-study-with-me/study"><img src="https://agentmods.dev/badge/skills/lsh1215/oh-my-study-with-me/study.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,112 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 $0.00043 $0.03112
Opus 5 $0.00022 $0.01556
Sonnet 5 $0.00009 $0.00622
Haiku 4.5 $0.00004 $0.00311

Measured 9d ago against content hash 0a45b5830a2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

study 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.

skills/study/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Study - First Principles Study Skill

Argument Parsing

  • No argument → start from source selection
  • [book name keyword] → start that book immediately (PDF flow)
  • [URL] → fetch and study the URL content (web/GitHub/YouTube flow)
  • continue → resume previous study session (refer to progress file)

Argument: $ARGUMENTS

Phase 0: Source Selection

Detect the source type from the argument or user input:

URL Detection

  • Web article URL (any http/https not matching below) → Web flow
  • GitHub URL (github.com/{owner}/{repo}) → GitHub flow
  • YouTube URL (youtube.com/watch or youtu.be/) → YouTube flow (best-effort)
  • No URL detected → check for book/PDF keywords, or ask the user

Web Article Flow

  1. Use WebFetch to retrieve the article content.
  2. Extract the article structure (headings, sections).
  3. Show the structure to the user and ask which section(s) to focus on.
  4. Proceed to Phase 1 with the selected section content.

GitHub Repo Flow

  1. Use WebFetch to fetch the README.
  2. Use gh CLI or WebFetch to get the repo structure (directory tree, key files).
  3. Show the repo overview to the user and ask what aspect to study (architecture, specific module, design patterns, etc.).
  4. Fetch the relevant source files for the chosen aspect.
  5. Proceed to Phase 1 with the fetched content.

YouTube Flow (Best-Effort)

  1. Use WebFetch to get the YouTube page content (title, description, any transcript info).
  2. If transcript content is available, use it as the study material.
  3. If only description is available, use it as a starting point and supplement with WebSearch on the topic.
  4. Proceed to Phase 1 with whatever content was extracted.

Book/PDF Flow (Existing Behavior)

  1. Show the list of subfolders and PDF files under 책 목록/.
  2. When the user selects a book, read the front pages (1–10) of the PDF to extract the table of contents.
  3. Show the table of contents and ask the user which chapter to start from.

Phase 1: Content Reading + Core Principle Extraction

Read the full file on GitHub · 302 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. 9d ago First seen · 302 lines · 0 tokens per session scan A 0a45b5830a2f

Subscribe to this mod's changes

study is a skill published in the GitHub repository lsh1215/oh-my-study-with-me (8 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 3,112 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.

Learning and teaching
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