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/quiznpx skills add codeprakhar25/claude-study-mode --skill quizgit clone --depth 1 https://github.com/codeprakhar25/claude-study-modeWrote 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/codeprakhar25/claude-study-mode/quiz)<a href="https://agentmods.dev/skills/codeprakhar25/claude-study-mode/quiz"><img src="https://agentmods.dev/badge/skills/codeprakhar25/claude-study-mode/quiz.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00564 |
| Opus 5 | $0.00028 | $0.00282 |
| Sonnet 5 | $0.00011 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
quiz 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 6d 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.
What it actually says
/quiz — checkpoint gate
This is the gate that stops the tutor (and the learner) from running ahead. Reuse the grill pattern: interview relentlessly, one question at a time, wait for each answer.
Steps
-
Load the session. Read the session file (its
session=path is injected into your context; it lives under~/.claude/study/sessions/). The current concept isplan[checkpoint]. If no session exists, tell them to run/study <topic>first. -
Interrogate, one question at a time. Ask probing questions about the current concept: make them explain it back, predict an output, spot a bug, or justify a choice. Do not move to the next question until the current one is answered. If their code exists, ask them to explain why it works (read it with Read/Grep — never rewrite it).
-
Judge honestly. Scold hand-waving. Vague, copied, or "I think so" answers do NOT pass. Say so plainly and re-ask. A pass requires them demonstrating understanding, not asserting it.
-
On pass: congratulate briefly, then record it (both writes are inside the guard-allowed study storage dir — use the paths from your context):
- Update the session (
session=path): append the concept topassed, incrementcheckpoint. - Append to the lifetime ledger (
history=path,~/.claude/study/history.jsonl): add ONE line for the concept just passed —{"ts":"<ISO now>","topic":"<session topic>","concept":"<concept>","project":"<cwd>","level":"<level>"}. Append only; read it first and re-write all lines if you can't append directly, never drop existing lines. Then teach the next concept (concept only — no code).
- Update the session (
-
On fail: do NOT advance. Re-teach the weak spot, give a smaller sub-task, and tell them to come back for another
/quiz.
Never advance the checkpoint without a genuine pass. Output is not the goal; understanding is.
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.
- 6d ago First seen · 47 lines · 56 tokens per session scan A a3e2b7078d3f
quiz is a skill published in the GitHub repository codeprakhar25/claude-study-mode (13 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 564 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
gan-zhong-xue
在你干真实开发时(边干边挖:搞懂 AI 正在做的这步,掌控方向)或干完提交后(事后挖: 回头搞懂一个甩手没懂的改动),就地陪你走一轮"先让你猜、再揭示、逼到原理"的回合制, 把黑盒变成你真懂、能复述、能迁移的东西。治的是 vibe-coding 的病:交付物在增加, 理解没跟上。触发词:"干中学"、"帮我搞懂 AI 正在做的这步"、"我刚才那段没懂"、 "这个 commit 我说不清"、"帮我真正搞懂刚才做的";掌舵(任务中途):"等等这步我没懂"、 "为什么这么改"、"这步我没跟上"。 English triggers: "learning by doing", "help me actually understand what…
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.
rolecraft
JD-driven study companion. Paste a job description; get back what to study, what to build, and where else this role exists. Use when the user pastes a job description, says "process this", asks "what would this role take", or wants concepts, tech stacks, companies, projects, or a dashboard summary derived from past…
help
Explain the agentic-study-environment plugin — what it does, the lifecycle skills it ships, the domain overlays, the session types, and the key conventions — or a specific one of those if the user names it. Use this skill whenever the user asks for help with the study harness itself rather than asking to study…
adjust-level
Adjust the difficulty level of a learning sub-project's curriculum — simplify a too-advanced curriculum into a gentler on-ramp, or deepen a too-introductory one into something with real teeth. Use whenever the user signals the curriculum's level doesn't match their starting point — phrases like "this paper is too…
bootstrap
Scaffold a new learning sub-project under the agentic-study-environment harness — create the directory, generate per-project AGENTS.md, CLAUDE.md, and PROGRESS.md from templates, and register the new project in the .studyenv/PROGRESS.md cross-project tracker. Use this skill whenever the user wants to start studying a…