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 agentmods add skills/codeprakhar25/claude-study-mode/studynpx skills add codeprakhar25/claude-study-mode --skill studygit clone --depth 1 https://github.com/codeprakhar25/claude-study-modeWhat 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 | $0.00062 | $0.00804 |
| Opus 5 | $0.00031 | $0.00402 |
| Sonnet 5 | $0.00012 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00080 |
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.
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
-
Ensure study mode is on. If the user hasn't activated it, tell them to type
study on(orstudy lite). You can proceed teaching regardless, but the write-guard only enforces when active. -
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. -
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. -
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.
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.
- 2d ago First seen · 75 lines · 62 tokens per session scan A 2cd0a17bd503
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.
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.
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…
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"…
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.
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.
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.