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/ttguy0707/codojo/dojo-quiznpx skills add ttguy0707/codojo --skill dojo-quizgit clone --depth 1 https://github.com/ttguy0707/codojoWrote 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/ttguy0707/codojo/dojo-quiz)<a href="https://agentmods.dev/skills/ttguy0707/codojo/dojo-quiz"><img src="https://agentmods.dev/badge/skills/ttguy0707/codojo/dojo-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 | $0.00275 | $0.02324 |
| Opus 5 | $0.00138 | $0.01162 |
| Sonnet 5 | $0.00055 | $0.00465 |
| Haiku 4.5 | $0.00028 | $0.00232 |
Grade A, and why
dojo-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 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.
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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dojo-quiz — 知识检测
一句话定位:模块学完后用 3-5 道实战题验证用户是否真正理解,答错即时纠正,支持跳过。
何时使用
- ✅ S3 教学中某个模块所有知识点完成后(由 dojo-teach 自动触发)
- ✅ 用户主动说"考考我"、"测试一下"、"我学会了吗"
- ❌ 尚未完成任何知识点 → 提示"还没开始学习,先完成一些知识点再来测验"
- ❌ 用户正在 S1/S2 阶段 → 提示"评估/规划阶段不需要测验,S3 教学开始后会自动安排"
前置条件
<repo-root>/.codojo/schedule.md存在且至少有一个知识点状态为 ✅
跳过机制
用户有权跳过任何测验,不做任何惩罚或负面提示。
以下回复视为跳过(不区分大小写):
| 跳过确认词 | 语义 |
|---|---|
| "跳过"、"跳过测验" | 明确跳过 |
| "不用了"、"算了"、"不测了" | 婉拒 |
| "skip"、"pass" | 英文跳过 |
| "直接继续"、"下一个模块" | 跳过并继续 |
用户跳过时,AI 的回复应简短友好:
好的,跳过本模块测验。继续下一个模块——
然后无缝回到 dojo-teach 流程。不要说"建议你做一下测验"之类的劝导,用户说跳过就跳过。
跳过的测验在 schedule.md 学习日志中记录为:
- [2026-06-05 16:30] ⏭️ 模块 1 测验 - 用户选择跳过
工作流
Step 1:确定测验范围
确定要测验的模块:
- 自动触发时:测验刚完成的模块
- 手动触发时:读取 schedule.md,找到最近完成的模块(所有知识点为 ✅ 且尚未做过测验的模块)
如果用户手动触发但所有已完成模块都测过了,提示:
你已完成的模块都测验过了!继续学习新知识点,完成下一个模块后会自动安排测验。
Step 2:出题
根据该模块包含的知识点和涉及的项目代码,生成 3-5 道题目。
出题原则:
- 题目必须基于项目真实代码,不出脱离项目的通用理论题
- 题型多样化:代码理解题、改动预判题、Bug 定位题、概念关联题
- 难度递进:第 1 题容易(确认基础理解),后面逐步加深
- 每题简短明确,给出足够上下文(代码片段 + 文件路径)
题型示例:
**题型 A — 代码理解**
看这段代码(`src/service/OrderService.java` 第 42-55 行):
<代码片段>
问:这段代码的核心职责是什么?当 `status == null` 时会发生什么?
**题型 B — 改动预判**
如果把 `application.yml` 中的 `server.port` 从 8080 改成 9090,
除了端口变化外,还有哪些地方会受影响?
**题型 C — Bug 定位**
用户反馈"下单后库存没有减少",基于你对模块 2 的理解,
你会从哪个类的哪个方法开始排查?为什么?
**题型 D — 概念关联**
在本项目中,Controller 层和 Service 层的职责边界是什么?
举一个本项目中违反了这个边界的例子(如果有的话)。
Step 3:逐题交互
一次只出一道题,等用户回答后再出下一道。
出题格式:
---
📝 **模块 N 测验** (1/4)
<题目内容,含代码片段和文件路径>
---
💬 说出你的答案,或回复「跳过」跳过整个测验。
Step 4:即时点评
用户回答后,AI 立即点评:
-
答对:简短肯定 + 出下一题
✅ 正确!<一句话补充关键点> -
部分正确:肯定对的部分 + 补充遗漏
⚠️ 方向对了!<肯定的部分>。补充一点:<遗漏的关键点> -
答错:不批评,给出简短要点提示(2-3 句话),不展开完整讲解
❌ 不太对。关键点是:<简短解释核心概念,2-3 句话> 💡 可以回看 `task.md` 中的知识点 N.M 复习一下。
注意:答错时不要强制用户回到 S3 重学——只给提示和回看建议,用户自行决定是否复习。测验的目的是帮助用户发现盲区,不是设置关卡。
Step 5:测验总结
所有题目回答完毕后(或用户中途跳过时),输出简短总结:
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.
- 5d ago First seen · 215 lines · 275 tokens per session scan A f90a9edf800b
dojo-quiz is a skill published in the GitHub repository ttguy0707/codojo (58 stars, last pushed 2mo ago), licensed MIT. It adds 275 tokens to every session and 2,324 once invoked, about $0.0014 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
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
math-olympiad
Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any…
google-agents-cli-onboarding
Onboarding entrypoint for agents-cli in Agent Platform. It should be used when the user wants to "create a new agent", "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "evaluate an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs…
edu-math-tutorial
数学题分步讲解视频的领域知识。适用场景:(1) 用户给出一道数学题并要求做讲解/ 解题视频;(2) 用户说"讲解这道题"、"生成解题视频"、"make a math tutorial"; (3) 需要中文数学教学视频,涉及方程、公式或几何图形。本 skill 只提供领域 知识(题目拆解、讲解节奏、旁白文案规范、版式与 KaTeX 排版风格);画面、 配音与成片一律用 Creator 原生 Element 与工具从源头构建。.
comet-native
Comet Native 工作流。当用户明确调用 /comet-native、要求启动或恢复 Native change,或入口路由到 Native 时使用。.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session.