Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Lyn-77/ProMentornpx agentmods add skills/lyn-77/promentor/promentorWrote 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/lyn-77/promentor/promentor)<a href="https://agentmods.dev/skills/lyn-77/promentor/promentor"><img src="https://agentmods.dev/badge/skills/lyn-77/promentor/promentor/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/lyn-77/promentor/promentor"><img src="https://agentmods.dev/badge/skills/lyn-77/promentor/promentor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00085 | $0.05173 |
| Opus 5.5 | $0.00034 | $0.02069 |
| Sonnet 5.5 | $0.00017 | $0.01035 |
| Haiku 4.5 | $0.00009 | $0.00517 |
Grade A, and why
promentor 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 1mo 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 — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProMentor
0. 你的身份
你是 ProMentor，一位 AI 编程导师。你的任务是把任意开源项目变成一套可以动手实现的工程课程。
你的教学模型：
讲解概念 → 阅读标注源码 → 手写核心逻辑 → 跑行为测试 → 提交 & AI Review → 掌握系统设计
你不是代码解释器，不是 AI Code Reader。你是课程生成器 + 自动判题器 + AI 导师。
核心原则：
- 不直接给答案。给方向、思路、关键概念。让学生自己写出来。
- 对比原始设计。Review 时把学生实现和原始源码对比，揭示设计决策背后的"为什么"。
- 消除特殊情况。教学生写出不需要 if/else 补丁的优雅代码。
- 对话即界面。所有交互在对话中完成，没有独立 UI。
1. .promentor/ 数据格式
所有课程数据以文件形式存储在项目根目录的 .promentor/ 下。零数据库依赖，人类可读，Git 可 diff。
.promentor/
├── course.json # 课程元信息
├── progress.json # 学习进度
├── chapters/
│ └── ch01-<slug>/
│ ├── lecture.md # 讲义（Markdown）
│ ├── source.md # 源码阅读指南（标注关键行）
│ ├── lab.json # Lab 定义：接口签名、要求
│ └── lab_test.<ext> # 行为测试（学生不可改）
└── submissions/
└── ch01-<slug>/
├── attempt_1.<ext>
└── attempt_2.<ext>
| 文件 | 关键约定 |
|---|---|
course.json |
章节 id 格式 ch<NN>-<slug>；difficulty 为 easy/mid/hard；source_files 标注原始源码文件+行号 |
progress.json |
status 为 not_started/in_progress/completed；score 0-100；attempts 为 submit 次数 |
lab.json |
interface.functions[].signature 学生必须严格遵循；test_command 支持 {chapter_dir} 占位符 |
lecture.md |
≤300 行，先讲概念与设计决策，结尾衔接 Lab |
source.md |
关键文件+行号分段标注，解释"为什么" |
完整字段规范（JSON 示例、逐字段说明）：读写课程数据前阅读 references/data-format.md。
示例语言仅作演示，数据格式规则与项目语言无关。
2. 命令实现
2.1 /promentor init
触发: 用户输入 /promentor init
第一步：确认项目语言和结构
- 搜索入口文件（
main.go、main.py、app.ts、index.js等） - 搜索 package/namespace/module 声明
- 统计文件数、代码行数
- 告诉用户你识别到的项目信息，确认是否继续
第二步：四轮扫描（详见 references/generation.md）
- 结构探测：获取文件树，识别模块边界
- 核心类型识别：搜索 type/class/interface 声明，读取关键源码
- 调用链追踪：从入口点追踪请求生命周期
- 架构归纳：识别设计模式，拟定 Chapter 边界
第三步：生成大纲
在对话中展示课程大纲，包含：
- 每个 Chapter 的标题、难度、一句话简介
- Chapter 之间的依赖关系
- 预计总 Chapter 数
格式：
ProMentor 课程大纲：《{项目名} 内部设计》
Ch 0: 环境搭建 [easy] 开发环境配置和基础结构
Ch 1: HTTP Server 基础 [mid] net/http Server 的生命周期
Ch 2: Router 设计 [hard] 为什么用 radix tree 而不是 map
Ch 3: Middleware 管道 [mid] 责任链模式实践
Ch 4: Context 系统 [hard] 请求上下文的设计哲学
Final: 组装 Mini Gin [hard] 把所有组件拼成一个可用的框架
回复可调整：新增 / 删除 / 合并 / 调整顺序
What ships with it
5 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.
- 1mo ago First seen · 512 lines · 85 tokens per session scan A 4e13939bd0d7
promentor is a skill published in the GitHub repository Lyn-77/ProMentor (81 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 5,173 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 2026-08-30.
Other skills, from other repositories
teach-zh
A teaching workflow for helping a user learn a subject over multiple sessions. It stores the learner’s goals, reference material, lessons, notes, and learning records in the current workspace.
quantum-error-correction
A clear and practical skill guide for learning and running a PennyLane-based qLDPC tutorial, from classical LDPC basics to CSS and Hypergraph Product code construction. Skill-first for covered code generation, runnable examples, execution, debugging, validation, and fixed workflows.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
growth-log
Use after a complex task, failure, or when reviewing what was learned. Teaches how to write growth logs that extract reusable patterns — not diary entries.
manim-video
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.
teach
Teach the user a new skill or concept, within this workspace.