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-teachnpx skills add ttguy0707/codojo --skill dojo-teachgit 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-teach)<a href="https://agentmods.dev/skills/ttguy0707/codojo/dojo-teach"><img src="https://agentmods.dev/badge/skills/ttguy0707/codojo/dojo-teach.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 | $0.00342 | $0.03723 |
| Opus 5 | $0.00171 | $0.01861 |
| Sonnet 5 | $0.00068 | $0.00745 |
| Haiku 4.5 | $0.00034 | $0.00372 |
Grade A, and why
dojo-teach 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 4d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dojo-teach — S3 正式教学
一句话定位:按学习计划交互式教学,理论+实践并行,实时跟踪进度直到 100%。
何时使用
- ✅ S1 + S2 已完成,
task.md和schedule.md已存在 - ✅ 用户说"开始学习"、"继续学习"、"教我"、"下一个"
- ✅ 用户中断后重新回来继续学习
- ❌
open-questions.md不存在 → 转dojo-assess - ❌
task.md不存在 → 转dojo-plan - ❌ 用户想直接魔改项目 → 转
dojo-hack(需 S3 100% 完成)
前置条件
<repo-root>/.codojo/open-questions.md存在(S1 产出)<repo-root>/.codojo/task.md存在(S2 产出)<repo-root>/.codojo/schedule.md存在(S2 产出)
若前置条件不满足,提示用户并转到对应 skill。
确认词定义
以下同义词列表用于理论环节和实践环节的状态机判断:
| 环节 | 可接受的确认词 | 语义 |
|---|---|---|
| 理论 → 进入实践 | "理解"、"懂了"、"明白了"、"OK"、"好的"、"了解"、"get" | 用户确认理解理论 |
| 实践 → 进入下一知识点 | "完成"、"做完了"、"搞定"、"done"、"好了" | 用户确认完成实践 |
| 继续下一知识点 | "继续"、"下一个"、"next"、"go" | 用户确认继续学习 |
| 中断休息 | "休息"、"暂停"、"今天到这"、"先这样"、"停" | 用户选择中断 |
规则:用户回复的内容如果不在上述确认词列表中(即使看起来像确认),一律视为提问或反馈,进入答疑/辅导流程。
工作流
Step 1:读取进度,定位当前位置
读取 schedule.md,找到第一个状态为 ⚪(未开始)或 🔄(进行中)的知识点。
- 如果全部为 ✅ → 教学已完成,提示进入 S4
- 如果有 🔄 → 从该知识点的未完成环节继续(理论或实践)
- 如果有 ⚪ → 从该知识点的理论环节开始
向用户展示当前位置和总进度:
---
📊 **学习进度**: ██████░░░░ 58% (14/24 知识点)
📍 **当前位置**: 模块 3 - Spring Boot 自动配置
⏭️ **即将开始**: 理论讲解
---
Step 2:理论环节
读取 task.md 中当前知识点的理论要点和涉及文件,结合项目实际代码进行讲解。
讲解要求:
- 先说"为什么"(这个概念 / 技术存在的意义,解决什么问题)
- 再说"是什么"(核心原理,用类比辅助理解)
- 最后说"在本项目中怎么用的"(指向具体代码文件和行号)
- 内容长度控制在 300-500 字,不要信息过载
- 语言风格友好、耐心,适配零基础用户
- 引用代码时给出文件路径和关键代码片段(不超过 20 行)
讲解结束后固定输出:
---
📖 **理论环节** | <知识点名称>
📊 **学习进度**: ██████░░░░ 58%
💬 理解了回复「理解」,有疑问随时提问~
---
状态机规则(确认词见上方「确认词定义」):
- 用户回复理论确认词 → 进入 Step 3 实践环节
- 用户回复其他内容(提问) → 针对性解答,解答后再次提示"理解了回复「理解」"
- 不限答疑轮次,直到用户确认理解
Step 3:实践环节
根据 task.md 中当前知识点的实践任务,引导用户对项目代码做一个小改动。
实践任务设计要求:
- 改动必须小而具体(改 1-3 处代码即可)
- 必须基于项目真实代码(给出确切文件路径和行号)
- 改动完成后效果可验证(能编译 / 能运行 / 能看到变化)
- 给出清晰的步骤说明:打开哪个文件、找到哪一行、改成什么
任务布置格式:
---
🔧 **实践任务** | <知识点名称>
**目标**:<一句话说明做完能达到什么效果>
**步骤**:
1. 打开文件 `<路径>`
2. 找到第 XX 行:`<原代码片段>`
3. 修改为:`<新代码片段>`
4. <验证方式:如运行命令、刷新页面等>
**提示**:如果不确定怎么做,随时提问~
完成后回复「完成」。
---
状态机规则(确认词见上方「确认词定义」):
- 用户回复实践确认词 → 进入 Step 4 更新进度
- 用户回复其他内容(提问 / 报错) → 针对性解答和指导,解答后再次提示"完成后回复「完成」"
- 不限辅导轮次,直到用户确认完成
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.
- 4d ago First seen · 284 lines · 342 tokens per session scan A abf414bc2d13
dojo-teach is a skill published in the GitHub repository ttguy0707/codojo (57 stars, last pushed 2mo ago), licensed MIT. It adds 342 tokens to every session and 3,723 once invoked, about $0.0017 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
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。.
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
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。.
comet
Comet — OpenSpec + Superpowers dual-star development workflow. Start with /comet for automatic phase detection and dispatch to subcommands. Five phases: open → design → build → verify → archive.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session.
comet-hotfix
Comet 预设 —— 通过 open-build-verify-archive 短流程修复已有行为 bug。.