Borrowing it
Nothing to install: this file belongs to oryx-labs/oryxos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/oryx-labs/oryxos/main/.claude/skills/oryxos-lesson-dev/SKILL.mdgit clone --depth 1 https://github.com/oryx-labs/oryxosWrote 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/oryx-labs/oryxos/oryxos-lesson-dev)<a href="https://agentmods.dev/skills/oryx-labs/oryxos/oryxos-lesson-dev"><img src="https://agentmods.dev/badge/skills/oryx-labs/oryxos/oryxos-lesson-dev/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/oryx-labs/oryxos/oryxos-lesson-dev"><img src="https://agentmods.dev/badge/skills/oryx-labs/oryxos/oryxos-lesson-dev.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 | $0.00124 | $0.03351 |
| Opus 5 | $0.00062 | $0.01675 |
| Sonnet 5 | $0.00025 | $0.00670 |
| Haiku 4.5 | $0.00012 | $0.00335 |
Grade A, and why
oryxos-lesson-dev 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 9d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OryxOS 逐节开发 Skill
User Input
$ARGUMENTS
节号来自上面的输入。设计依据见 docs/class/Harness 设计：用门禁保证每个功能符合预期.md，流程原理见 docs/class/Spec-Kit 执行指导：从课件到代码（以第16节为例）.md——本 skill 是它们的可执行版本，条款以本文为准执行，不需要复读那两份文档给用户。
总纪律（贯穿全程）
能机器判的绝不留给人，机器判不了的绝不自行发挥。
- 硬门禁：测试、
mvn clean verify、存在性核对——不过不放行，不许绕。 - 软门禁：遇到下列任一情况，立即停下、向用户报告、等确认后继续，不得自行决定：
- 需要创建"本节交付物"清单之外的任何对外概念（public 类型、配置键、数据表、REST 路径、Profile 字段）；
- 需要修改任何已定字面量（类名、方法签名、配置键、表列名、端点路径）；
- 课件与
docs/TechnicalSolution.md冲突； - 需要修改前序节交付的公共接口（当节课件明确列为"改造点"的除外）；
- 第三方 API 在本地依赖中核实不到；
- 需要新增 plan 未列明的第三方依赖。
- 反作弊：不得删断言、
@Disabled、放宽阈值让测试变绿。实现错修实现；认为测试错，停下报告。未全绿不得宣称完成。 - 全程不自动 commit / push / 运行 package.sh，同步时机由用户决定。
第 0 步：输入校验与课型分流
解析节号 N，按下表分流；表外输入直接报错退出。
| N | 课型 | 处理 |
|---|---|---|
| 16,17,18,19,20,22,24,25,26,29,30 | 代码课 | 走完整流程（第 1~7 步） |
| 21,23 | 评审课 | 拒绝并说明：这节不产码，是下一节（22/24）的 specify 素材 |
| 27,28 | 串联课 | 特殊模式：不开新 feature，逐条执行该节课件的对账清单，并把对账固化成课件建议的 @Tag("integration") 测试类（27→HumanTriggerFlowIT；28→SchedulerFlowIT/RestartRecoveryIT），然后出报告 |
| 31 | Demo 课 | 特殊模式：按课件定义 weather-daily（走 30 节 API）与 daily-tech-digest（走手写文件）两个 Agent，完成调试对账与发布清单，不做常规模块开发 |
| 其他 | — | 报错：仅支持 16~31 |
第 1 步：H0 开工纪律——必读与依赖检查
- 读三样（用 Read 完整读，不凭记忆）：
- 当节课件：
docs/class/第{N}节*.md（glob 匹配）； docs/TechnicalSolution.md对应章节（映射表见下）；- 前序各代码课课件的"本节交付物"小节。
- 当节课件：
- 依赖存在性检查：对前序每节交付物清单里的核心类，在代码库里 grep/Glob 确认存在。任何缺失 → 停下报告"先做第 X 节"，不得跳节自造。
- 分支：确认当前在该节的 feature 分支上（speckit-specify 的 before_specify hook 会建分支；若 hook 未配置，手动
git checkout -b {NNN}-lesson{N}-<slug>），不在 main/主干上直接开发。
技术方案章节映射表：
| 节 | TechnicalSolution 章节 |
|---|---|
| 16 | §3（Provider）、§8.2（Profile）、§9.2（llm_calls） |
| 17 | §4（ReAct/AgentService/ProfileContext）、§8.3（ContextLoader）、§9.2（tool_invocations） |
| 18 | §8.4、§8.6（CLI）、§9.2（sessions） |
| 19 | §6.8（Notify） |
| 20 | §6.1~6.6（Tool/MCP） |
| 22 | §5（Memory） |
| 24 | §6.7（Sandbox） |
| 25 | §8.5（定时/会话身份） |
| 26 | §7（Web Service） |
| 29 | §11.1~11.2（Skill+Profile、运行时注册） |
| 30 | §11.3~11.4（AgentLifecycleService、/api/v1/agents） |
| 27/28/31 | §12（关键流程/两个 Demo） |
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.
- 9d ago First seen · 154 lines · 124 tokens per session scan A ad0e28ec6ea2
oryxos-lesson-dev is a skill published in the GitHub repository oryx-labs/oryxos (156 stars, last pushed today), licensed Apache-2.0. It adds 124 tokens to every session and 3,351 once invoked, about $0.0006 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
ai-tutor
Use when user asks to explain, break down, or help understand technical concepts (AI, ML, or other technical topics). Makes complex ideas accessible through plain English and narrative structure. Use the provided scripts to transcribe videos.
ai-engineering-curriculum
Use when structured AI engineering curriculum — 382 skills + 99 prompts across 20 phases covering ML, deep learning, LLMs, agents, and production systems. Use when learning AI, building AI skills,.
teach
Teach the user a topic, concept, or skill so they actually understand it and can do it themselves — not just hand over information. Use when the user asks to be taught, wants to learn or understand something, says they don't get a concept, asks you to explain so it sticks, or wants to be walked through how something…
interview-prep
Technical interview preparation expert for algorithms, system design, and behavioral questions.
baoyu-comic
A tool for creating educational comics from supplied text, files, links, or topics. It can cover explanations, biographies, and tutorials in different visual styles, tones, layouts, sizes, and languages.
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.