quiz

quiz is a command for Claude Code from gkaria/vibe-learn. It costs 21 tokens per session (825 once invoked), scanned B, original, MIT.

A learning check that asks recall questions about what was built during a coding session. It can also track whether concepts are solid or need review across sessions.

In plain words
What is it for?
Reviewing session changes, answering questions about the work, recording solid or shaky knowledge, and identifying concepts that are due for later review.
Why use it?
It turns a completed coding session into a review exercise, so developers can find gaps in their understanding instead of only relying on memory.

Command for Claude Code

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 commands/gkaria/vibe-learn/quiz
Clone the repo
git clone --depth 1 https://github.com/gkaria/vibe-learn

Made for: Claude Code.

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 quiz

README.md
[![agentmods](https://agentmods.dev/badge/commands/gkaria/vibe-learn/quiz.svg)](https://agentmods.dev/commands/gkaria/vibe-learn/quiz)
Your own site
<a href="https://agentmods.dev/commands/gkaria/vibe-learn/quiz"><img src="https://agentmods.dev/badge/commands/gkaria/vibe-learn/quiz.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 825 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00021 $0.00825
Opus 5 $0.00010 $0.00413
Sonnet 5 $0.00004 $0.00165
Haiku 4.5 $0.00002 $0.00082

Measured 5d ago against content hash 03d4e14cd83c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

quiz scanned grade B with 1 finding 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

2. The install directory this project's hooks point at: read the vibe-learn hook command from `.claude/settings.local.json` (or `~/.claude/settings.json`) — it ends in `<install-dir>/scripts/bootstrap.sh`, and `knowledge
.claude/commands/quiz.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read .vibe-learn/session-log.jsonl to understand what happened in this session. Read .vibe-learn/knowledge.json if it exists (the cross-session knowledge ledger).

Knowledge helper: to read or update the ledger, use the knowledge.sh helper via Bash — never hand-edit the JSON. Locate it in this order:

  1. ~/.vibe-learn/scripts/knowledge.sh (global install)
  2. The install directory this project's hooks point at: read the vibe-learn hook command from .claude/settings.local.json (or ~/.claude/settings.json) — it ends in <install-dir>/scripts/bootstrap.sh, and knowledge.sh sits in the same directory
  3. scripts/knowledge.sh in the vibe-learn repo, if this project is the vibe-learn repo itself

If none of these exist, skip ledger updates and say so briefly at the end — the quiz itself still works.

Helper usage:

bash <helper> record <name> --label="<Human label>" --status=<solid|shaky> [--notes="<what was shaky>"]
bash <helper> due --days=14    # concepts due for review, as a JSON array
bash <helper> list             # full ledger

Read review_after_days and quiz_question_count from ~/.vibe-learn/config/knowledge-defaults.json if present (defaults: 14 and 5).

Parse $ARGUMENTS to determine the mode:


Mode: review

If $ARGUMENTS is review:

  1. Run the helper's due command to get concepts that are shaky or haven't been quizzed recently.
  2. If nothing is due, say so and offer a regular /quiz on this session instead.
  3. Otherwise pick up to the configured question count of due concepts (shakiest and oldest first) and quiz on those, following the question flow below. Ground questions in the current codebase — read the relevant files first.

Mode: <topic>

If $ARGUMENTS is anything else (a topic):

Quiz on that topic, drawing questions from this session's log if it touched the topic, otherwise from the ledger and the relevant source files.


Mode: plain quiz (no arguments)

Quiz on this session. Select 3–5 quizzable moments from the session log — decisions, patterns, dependencies added, failures that were fixed.

Read the full file on GitHub · 67 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. 5d ago First seen · 67 lines · 21 tokens per session scan B 03d4e14cd83c

Subscribe to this mod's changes

quiz is a command published in the GitHub repository gkaria/vibe-learn (54 stars, last pushed 8d ago), licensed MIT. It adds 21 tokens to every session and 825 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.