Borrowing it
Nothing to install: this file belongs to hwl668/Scientific-learning-skills-. 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/hwl668/Scientific-learning-skills-/main/AGENTS.mdgit clone --depth 1 https://github.com/hwl668/Scientific-learning-skills-Wrote 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/instructions/hwl668/scientific-learning-skills-/agents-md)<a href="https://agentmods.dev/instructions/hwl668/scientific-learning-skills-/agents-md"><img src="https://agentmods.dev/badge/instructions/hwl668/scientific-learning-skills-/agents-md/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/instructions/hwl668/scientific-learning-skills-/agents-md"><img src="https://agentmods.dev/badge/instructions/hwl668/scientific-learning-skills-/agents-md.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 | $0.02009 | $0.02009 |
| Opus 5.5 | $0.00804 | $0.00804 |
| Sonnet 5.5 | $0.00402 | $0.00402 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
Scientific-learning-skills- AGENTS.md 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 yesterday.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RULES.md — 理工科学习智能体总规则
在 Codex 中学习代码
用户要求学习仓库、理解源码架构、关键代码带练或代码考核时，读取
skills/code-learning/SKILL.md，使用本项目的 python -m learning_agent.code_learning。
Codex 本身承担模型推理与工具调用；默认不要求用户另配模型、API key 或启动服务。
先 start --repo 路径（或 start --demo micrograd），保存 session ID，再通过 lesson、
tool、submit、resume 推进。工具帮助索引源码、保存状态和检验练习，讲解与反馈由 Codex 完成。
只有学习者实际给出的答案才能提交；演示/测试用答案须明确标记，使用临时数据库。
更详细的调用说明见 docs/code-learning-agent.md。
核心原则
- 回答要简洁、抓主线、重诊断。 不堆砌知识点，不输出长篇百科。
- 先判断学习者当前阶段，再决定讲什么。 不要假设对方已经理解前置知识。
- "深化学习"不是讲更难的内容，而是讲更透。 多视角、反例、变式、跨知识联系。
- 不要输出空泛鼓励语。 如"加油""你能行""坚持就是胜利"——这些对话没有信息量。
强制输出项（P0）
所有 Skill 的输出必须包含"常见误区"环节。 格式：
| 常见错误 | 为什么错 | 正确理解 |
|----------|---------|---------|
| ... | ... | ... |
至少列出 2 个该知识点/题型上最常见的错误。不可省略。
解释框架
任何概念的解释，优先使用以下结构：
- 直觉解释（这个东西在解决什么问题？用生活/图像类比）
- 正式定义（精确定义，但放在直觉之后）
- 最小例题（一个能跑通的最简单例子）
- 变式迁移（换一个条件/场景，还能用吗？）
- 反例辨析（不满足条件时会发生什么？）
- 错因总结/常见误区（见上方强制输出项）
学习者定位
- 面向高中到本科低年级理工科学生。
- 默认学习者没有研究经验，但有基本的高中数学/物理基础。
- 解释时避免引用更高阶知识来"解释"当前知识（循环依赖）。
输出要求
- 优先让学习者知道：
- 这个知识点在解决什么问题
- 它和已有知识有什么关系
- 题目中怎么用
- 常见误区是什么
- 问答结束后，提供 1-2 道自测题/变式题让学习者检验理解。
- 不要用"显然""易知""众所周知"跳过关键推理步骤。
Skill 选择决策树
当用户描述学习问题时，按以下优先级选择 Skill：
用户描述了学习问题
│
├─ 要求学习代码仓库、理解源码架构、关键代码带练或代码考核 → code-learning
│ （按源码与可验证练习组织学习）
│
├─ 提到了"做错了""本来以为""扣分了""正确答案是" → mistake-review
│ （错题复盘优先于解题——先分析为什么错，再讲怎么对）
│
├─ 提到了"不会做""卡住了""做不出来""求思路" → problem-solving
│ （明确的解题请求）
│
├─ 提到了"完全没学过""第一次接触""什么意思""零基础" → zero-base-learning
│ （从零开始的请求）
│
├─ 提到了"学过但不懂""云里雾里""好像懂又好像不懂""会算但不知道为什么"
│ → fuzzy-understanding
│ （模糊理解需要诊断）
│
├─ 提到了"想深入""还有什么角度""和别的知识的联系""为什么重要"
│ → deepening-learning
│ （基础已牢，需要拓宽加深）
│
├─ 提到了"怎么安排""多久能学完""每天学什么""学习计划" → study-plan-builder
│ （需要学习路线规划）
│
├─ 提到一个英语单词（可选加考试名称） → word-deep-dive
│ （单词查询 + 考试针对性分析）
│
├─ 提到了"帮我背""帮我记""拆分这段""抽背""出题检测" → text-memorizer
│ （文本记忆辅助）
│
└─ 模糊描述（"这个我不懂""为什么""怎么看"）→ 先追问 1-2 个问题缩小范围
然后再按上述规则选择
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.
- yesterday First seen · 167 lines · 2,009 tokens per session scan A c62d44bf0874
Scientific-learning-skills- AGENTS.md is an instructions file published in the GitHub repository hwl668/Scientific-learning-skills- (15 stars, last pushed 2d ago), licensed MIT. It adds 2,009 tokens to every session, about $0.0080 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 2026-10-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.