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 skills add Playa-0v0/Cyrene-Agent --skill cyrene-exam-papergit clone --depth 1 https://github.com/Playa-0v0/Cyrene-AgentWrote 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/playa-0v0/cyrene-agent/cyrene-exam-paper)<a href="https://agentmods.dev/skills/playa-0v0/cyrene-agent/cyrene-exam-paper"><img src="https://agentmods.dev/badge/skills/playa-0v0/cyrene-agent/cyrene-exam-paper/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.
<a href="https://agentmods.dev/skills/playa-0v0/cyrene-agent/cyrene-exam-paper"><img src="https://agentmods.dev/badge/skills/playa-0v0/cyrene-agent/cyrene-exam-paper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.01958 |
| Opus 5.5 | $0.00026 | $0.00783 |
| Sonnet 5.5 | $0.00013 | $0.00392 |
| Haiku 4.5 | $0.00006 | $0.00196 |
Grade A, and why
cyrene-exam-paper 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 2mo 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cyrene Exam Paper（试卷能力）
出正式试卷的完整契约：先做命题蓝图，再按蓝图出卷；试卷与答案分离成两个文件，支持先考后批。文件操作安全原则已由 cyrene-obsidian-workspace 定义，无需重复。
何时触发
- 用户说"出一张试卷"、"来场模拟考"、"正式测验一下"
- 阶段性检验学习成果的成套测验
- 几道题的随堂练习、小测仍走
exercises/（cyrene-learn-tutor 第 5 节），不走本流程
与 exercises/ 的分工
exercises/：随学随练的小练习、日常复盘，单文件exams/：正式试卷三件套——试卷、答案解析、考试复盘，成套大题、标注满分与时长
命题蓝图（出卷的核心步骤）
出卷前必须先在内部完成一次「知识点 → 能力 → 题型」推导，再动笔。禁止跳过蓝图直接套题型模板。
推导流程
- 读
notes/和learn/progress.md，列出本次范围内实际学过的知识点 - 对每个知识点问：学它的时候用户在练什么能力？
- 按下方对照表选题型；学科专项细则读 references/（见下一节）
能力 → 题型总纲
| 要验证的能力 | 适合的题型 |
|---|---|
| 事实 / 术语记忆 | 填空、选择、配对 |
| 概念理解 | 判断并解释、概念辨析、举反例 |
| 因果理解 | 为什么题、"如果改变 X 会怎样" |
| 控制流理解 | 给代码预测输出、执行过程追踪 |
| 计算 / 推导 | 计算题、步骤推导题 |
| 应用迁移 | 情境题、案例题 |
| 调试排错 | 找 Bug、解释 Bug、改代码 |
| 设计决策 | 方案比较、架构评审、开放题 |
| 语言运用 | 完形、阅读、翻译、改错、写作 |
| 操作流程 | 排序题、场景决策、故障排查 |
学科细则加载（references/）
出卷时按考察内容用 read_skill_reference 读取对应细则，再按细则出题：
| 考察内容 | 读取文件 |
|---|---|
| 概念理解类（任何学科） | concept.md |
| 编程 / 框架 / 架构 | programming.md |
| 数学（任何分支） | mathematics.md |
| 语言（英语 / 外语） | language.md |
| 物理 | physics.md |
跨学科卷（如"物理计算含数学推导"）读多个；没有匹配文件的学科只用总纲+concept.md。已加载的细则本张卷内复用，不重复读。
蓝图三原则
- 题型由能力决定：学 if/for 就考控制流追踪，学架构就考场景分析；不因科目是编程就默认选择填空
- 题量按权重分配：按学习目标的重要程度、学习深度、掌握薄弱程度分配题量与分值；次要知识可以只作为其他题目的组成部分，不机械"一知识点一题"
- 记忆题不禁止但要用对地方：词汇、公式、API 名称确实需要记；禁止的是拿背诵题检测理解能力，不是记忆本身
出卷流程
1. 出卷前确认
- 向用户展示蓝图摘要：考察的知识点、对应能力、题型、分值分布
- 确认时长与满分（默认 60 分钟 / 100 分）
- 用户明确说"随便出"才跳过确认直接出卷
2. 试卷文件
路径：exams/<subject>/<yyyy-mm-dd>-<topic>-试卷.md
结构（严格遵守）：
# <主题> 试卷
- 范围：<主题列表>
- 时长：60 分钟 ｜ 满分：100 分 ｜ 日期：yyyy-mm-dd
## 一、<按蓝图定的题型>（共 XX 分）
**1. 题干（公式用 $…$ 行内、$$…$$ 块级）**
A. 选项一
B. 选项二
C. 选项三
D. 选项四
**作答：**
> （在此作答；客观题只填字母：选择 B、多选 B D、判断 Y 或 N）
## 客观题答题卡（如有客观题）
| 题号 | 1 | 2 | … |
| --- | --- | --- | --- |
| 答案 | | | |
要点：
- 大题分区与题型由蓝图决定，不固定"单选+填空+计算+简答"模板；客观题集中的卷子配答题卡，全主观题的卷子不需要
- 客观题必须带作答字母标记：选择/多选题选项每行一个、行首 A./B./C./D.，多选题干标注（多选）；判断题题干末尾标注
（Y / N）。作答只填字母（B、B D、Y/N），不抄选项原文；答题卡与答案表同格式 - 主观题每题题干后跟
**作答：**留白区——用户直接在试卷文件里作答，或做完贴到对话里 - 各题分值相加必须等于满分
What ships with it
8 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.
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.
- 2mo ago First seen · 146 lines · 64 tokens per session scan A 78387ca867ea
cyrene-exam-paper is a skill published in the GitHub repository Playa-0v0/Cyrene-Agent (597 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,958 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-06.
cyrene-exam-paper compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cyrene-exam-paperPlaya-0v0/Cyrene-Agent | Skill | 597 | 1mo ago | MIT | A | 64 | Claude Code, Codex |
| self-improve-with-tinyfishtinyfish-io/tinyfish-cookbook | Skill | 2.3k | 4d ago | MIT | A | 68 | Claude Code, Codex |
| update-skillsmicrosoft/vscode | Skill | 195k | today | MIT | A | 51 | Claude Code, Codex |
| syncmicrosoft/vscode | Skill | 195k | today | MIT | A | 52 | Claude Code, Codex |
| generate-run-commandsmicrosoft/vscode | Skill | 195k | today | MIT | A | 36 | Claude Code, Codex |
| mergemicrosoft/vscode | Skill | 195k | today | MIT | A | 31 | Claude Code, Codex |
| create-canvasmicrosoft/vscode | Skill | 195k | today | MIT | A | 19 | Claude Code |