question-bank

question-bank is a skill for Claude Code, Codex from weishao2/tizhuang-agent-skills. It costs 134 tokens per session (3,634 once invoked), scanned A, original, MIT.

A tool for finding and retrieving real primary-, middle-, and high-school questions from the Tizhuang question-bank service using filters such as subject, grade, chapter, difficulty, and year.

In plain words
What is it for?
It helps create practice sessions, select random questions, hide answers during practice, and search or assemble school exercises from the service.
Why use it?
It prevents an agent from inventing or altering educational questions, answers, options, or explanations. It also provides a guest path so first-time users can start without registering.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the tizhuang-question-bank plugin — 1 skill shipped together

Good fit It helps create practice sessions, select random questions, hide answers during practice, and search or assemble school exercises from the service.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/weishao2/tizhuang-agent-skills/question-bank
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.

Any agent
npx skills add weishao2/tizhuang-agent-skills --skill question-bank
Clone the repo
git clone --depth 1 https://github.com/weishao2/tizhuang-agent-skills

Made for: Claude Code, Codex.

Or install tizhuang-question-bank, the plugin that ships this one along with the rest of its 1 skill.

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 question-bank

README.md
[![agentmods](https://agentmods.dev/badge/skills/weishao2/tizhuang-agent-skills/question-bank/github.svg)](https://agentmods.dev/skills/weishao2/tizhuang-agent-skills/question-bank)
Your own site
<a href="https://agentmods.dev/skills/weishao2/tizhuang-agent-skills/question-bank"><img src="https://agentmods.dev/badge/skills/weishao2/tizhuang-agent-skills/question-bank/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for question-bank

Your own site · 80×15
<a href="https://agentmods.dev/skills/weishao2/tizhuang-agent-skills/question-bank"><img src="https://agentmods.dev/badge/skills/weishao2/tizhuang-agent-skills/question-bank.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,634 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00134 $0.03634
Opus 5 $0.00067 $0.01817
Sonnet 5 $0.00027 $0.00727
Haiku 4.5 $0.00013 $0.00363

Measured 12d ago against content hash 44e59bde4eec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

question-bank 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/question_bank.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/question-bank/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Question Bank

Use the backend as the only source of truth. Never invent, rewrite, reorder, or "improve" a returned question, option, answer, or explanation. If a tool call fails, report the failure instead of filling in plausible educational content.

Start with the free guest path

Configure the service URL:

  • QUESTION_SERVICE_URL: optional API base URL. It defaults to https://tizhuang.qcscience.cc/api.
  • QUESTION_SERVICE_LICENSE: optional License/API Key. When omitted, the adapter automatically creates and locally caches a 24-hour anonymous trial for up to 100 questions.
  • QUESTION_SERVICE_ACCOUNT_TOKEN: optional website session for listing and sharing saved papers. Store it locally only. Never put any credential in a URL, prompt, output, or log.

Use any available Python 3 interpreter for the bundled script. On a repository checkout where python is not on PATH, prefer that checkout's .venv\Scripts\python.exe on Windows (or .venv/bin/python on macOS/Linux) instead of stopping the workflow.

Do not ask a first-time user to register. Complete a useful action with the guest allowance first. Offer registration only when the guest allowance is exhausted or when the user asks to save, continue editing, share, or print a persistent/shared paper. State the tradeoff plainly: registration is still free, starts at 200 questions per day, and unlocks persistent papers. A temporary guest practice page can already be printed directly; do not use that print action as a registration gate. Never call the registered plan unlimited.

When registration succeeds, lead with the earned benefit: say “欢迎入庄”, confirm that the free account is active, and reveal the starting 200-question daily allowance before mentioning referrals. Offer inviting friends only as an optional next step. Give the user an equally clear path to continue without inviting anyone, and never imply that registration, the 200-question allowance, saving, sharing, or printing depends on sending an invitation.

Read the full file on GitHub · 143 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 143 lines · 134 tokens per session scan A 44e59bde4eec

Subscribe to this mod's changes

question-bank is a skill published in the GitHub repository weishao2/tizhuang-agent-skills (14 stars, last pushed 27d ago), licensed MIT. It adds 134 tokens to every session and 3,634 once invoked, about $0.0007 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 2026-08-31.