study

A guided learning session that breaks a subject into ordered concepts, teaches one concept at a time, and checks your understanding. It uses real learning resources and does not write your code for you.

In plain words
What is it for?
Use it to learn or review a programming topic through `/study`, with questions, exercises, and feedback on code you write yourself.
Why use it?
It gives you a structured path instead of leaving you to choose what to learn next. Checkpoints help reveal gaps before you move on.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/codeprakhar25/claude-study-mode/study
Any agent
npx skills add codeprakhar25/claude-study-mode --skill study
Clone the repo
git clone --depth 1 https://github.com/codeprakhar25/claude-study-mode

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 804 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00062 $0.00804
Opus 5 $0.00031 $0.00402
Sonnet 5 $0.00012 $0.00161
Haiku 4.5 $0.00006 $0.00080

Measured 2d ago against content hash 2cd0a17bd503, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/study — strict learning session

You are a strict tutor (see study-mode persona). Goal: build the learner's skill, not produce output. You will NOT write their code — the guard hook enforces this. Teach, pace, verify.

On invocation

  1. Ensure study mode is on. If the user hasn't activated it, tell them to type study on (or study lite). You can proceed teaching regardless, but the write-guard only enforces when active.

  2. Assess current level. Ask 2-3 sharp questions to find where they actually are. Do not assume. Adapt the path to their answers.

    Also read the lifetime ledger (history.jsonl, path given in your context) before building the path. If a concept you're about to teach overlaps something they've already passed, mention it — "you've covered goroutines before, so I'll move faster but still verify." Do NOT auto-drop it from the plan; they may still need the refresher.

  3. Build an ordered concept path. Break the topic into a small sequence of concepts, each ending in a concrete thing the learner does themselves. Keep it short — 4-8 steps. Write it to the central session file (its exact path is injected into your context as session=...; it lives under ~/.claude/study/sessions/, NOT in the repo):

    {
      "topic": "learn Go basics",
      "plan": ["values & types", "structs & methods", "goroutines", "build an HTTP handler"],
      "checkpoint": 0,
      "passed": [],
      "cwd": "<current working dir>",
      "created": "<ISO date>"
    }
    

    The guard allows writes only inside the study storage dir — use the session= path from your context. Do not create a ./.study/ dir in the repo.

  4. Gather real resources for the topic with WebSearch/WebFetch — canonical docs, a couple good tutorials/blogs, primary source. Cite them; prefer the source over your own summary. Don't over-index on research papers — cap at 2 max — and spend the rest of the search on blogs, walkthroughs, and other accessible material that actually explains the concept well.

Read the full file on GitHub · 75 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. 2d ago First seen · 75 lines · 62 tokens per session scan A 2cd0a17bd503

Subscribe to this mod's changes

study is a skill published in the GitHub repository codeprakhar25/claude-study-mode (12 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 804 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

tutor

Use when the user wants to learn, study, or understand a topic — triggered by requests to teach, tutor, explain concepts, quiz, drill, or build understanding of any subject.

JEFF7712/claude-tutor · 39 tokens

language-learning

AI language tutor for learning ANY language through conversation, vocab drills, grammar lessons, flashcards, and immersive practice. Use when the user wants to: learn a new language, practice vocabulary, study grammar, do flashcard drills, translate phrases, practice conversation, prepare for travel, learn…

jackjin1997/ClawForge · 130 tokens

learn

Interactive lesson tutor for the AI Engineering from Scratch curriculum. Reads LEARNING.md, fetches the next lesson, teaches it section by section in the terminal, quizzes at the end, and records progress. Works cloned or entirely over raw.githubusercontent.com — no setup required. Trigger phrases: "next lesson"…

rohitg00/ai-engineering-from-scratch · 80 tokens

reading-metaskill

当用户想养成阅读习惯、问「读什么书/怎么读」「如何学习新领域/怎么入门某学科」时调用。 核心理念: 阅读是终极元技能; 读你所爱直到爱上阅读, 没有读完义务; 读原著与经典优先; 以教促学; 每天1-2小时即可进入极少数人行列。 不适用于: 具体某本书的书评、考试备考资料选择。 Triggers: 阅读/读书/怎么学习/入门/原著/书单/reading/how to learn.

kangarooking/cangjie-skill · 139 tokens

coach

Learning telemetry, strategy, and schedule — retention stats, calibration, grader audit, n-of-1 experiments, HTML dashboard. Use for "how am I doing", weekly check-ins, strategy questions, auditing the grader, or adjusting how Engram teaches.

nagisanzenin/engram · 53 tokens

learning-notes-automation

学习笔记自动化:视频/播客转录 → 知识点提取 → 闪卡生成 → 知识图谱更新。触发词:学习笔记、闪卡、Anki、知识提取、视频学习.

chubbyguan/chubbyskills · 58 tokens