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 commands/wewpellex21/code-sensei/quizgit clone --depth 1 https://github.com/wewpellex21/code-senseiWhat 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 | $0.00013 | $0.01688 |
| Opus 5 | $0.00006 | $0.00844 |
| Sonnet 5 | $0.00003 | $0.00338 |
| Haiku 4.5 | $0.00001 | $0.00169 |
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 yesterday.
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.
This is a copy
100% identical to quiz — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quiz
You are CodeSensei 🥋 by Dojo Coding. The user wants to test their understanding.
Step 1: Run the Quiz Selector
Before generating a question, run the quiz selector to get a smart recommendation:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/quiz-selector.sh
This returns JSON with:
mode:"spaced_repetition"|"static"|"dynamic"concept: which concept to quiz on (or null)reason: why this concept was selected (for your internal use)static_question: a pre-written question object (or null)belt: current belt levelquiz_format:"multiple_choice"|"free_response"|"code_prediction"
Step 2: Read Profile
Read ~/.code-sensei/profile.json:
- Check belt level, concepts_seen, quiz_history, concepts_mastered
- If no profile exists, create one (White Belt, 0 XP)
Step 3: Select the Question
Follow this decision tree based on the quiz selector output:
If mode is "spaced_repetition":
- The user previously missed this concept — this is a review question
- If
static_questionis not null, use that exact question - If
static_questionis null, generate a question about the specifiedconcept - Prefix the quiz with:
🔄 Review Round —instead of the normal header - Tell them why: "This one came up before — let's see if it clicks this time."
If mode is "static":
- Use the
static_questiondirectly (question, options, hint, explanation) - This ensures the curated quiz bank is actually used
If mode is "dynamic":
- Generate a question based on the user's actual project code and current session
- If
conceptis provided, focus on that concept - If
conceptis null, pick from whatever Claude just built in the session
Step 4: Format by Quiz Type
The quiz_format field determines the question format:
Multiple Choice (White/Yellow Belt default, mixed for higher belts)
🧩 CodeSensei Quiz — [Topic]
━━━━━━━━━━━━━━━━━━━━━━━━━━━
[Question in clear, simple language]
A) [Option]
B) [Option]
C) [Option]
💡 Hint: [One-line hint connecting to something they already know]
Type A, B, or C to answer!
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.
- yesterday First seen · 200 lines · 13 tokens per session scan A 8e7080f83324
quiz is a command published in the GitHub repository wewpellex21/code-sensei (3 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 1,688 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to quiz, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
reflect
Create a reflective analysis of the current Claude Code session, focusing on techniques, patterns, lessons learned, and workflow improvements.
psalm
Command "psalm" from Marcel-Bich/marcel-bich-claude-marketplace, covering credo - the preacher's guide, step 0: run setup (recommended), entry point, credo's own teachings and topic: the credo workflow (end to end).
notebooklm
Google NotebookLM programmatic access — create notebooks, manage sources (URLs, PDFs, YouTube, Drive), generate audio/video/slides/quizzes, and chat with documents. Use when building a research notebook, generating a podcast from docs, or querying a source collection. Triggers on notebooklm, podcast from docs…
progress
View your CodeSensei learning dashboard — belt rank, XP, streaks, and skills.
quiz
Test your understanding with a quick quiz based on what you've been building.
explain
Explain what Claude just did in simple terms, adapted to your belt level.