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 instructions/mwangli/stock-trading/agents-mdgit clone --depth 1 https://github.com/mwangli/stock-tradingWrote 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/mwangli/stock-trading/agents-md)<a href="https://agentmods.dev/instructions/mwangli/stock-trading/agents-md"><img src="https://agentmods.dev/badge/instructions/mwangli/stock-trading/agents-md.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 5.1 | $0.04686 | $0.04686 |
| Opus 5 | $0.02343 | $0.02343 |
| Sonnet 5 | $0.00937 | $0.00937 |
| Haiku 4.5 | $0.00469 | $0.00469 |
Grade A, and why
stock-trading 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 6d 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
交互语言要求
- 强制使用中文:所有回答、思考过程、输出内容必须使用中文
- 代码除外:代码本身和特殊专有名词(如类名、方法名、API 名称)使用英文
- 展示思考过程:在回答问题时,需要展示分析和推理过程
补充强化(必须遵守)
- 不得直接粘贴英文原始输出:包括但不限于后台 Agent、外部文档、命令行输出等;如包含英文内容,必须先用中文进行归纳/翻译后再输出。
- 面向用户的最终输出必须中文:允许在代码块、类名/方法名/API 名称、URL、HTTP Header 等专有名词处使用英文。
- “展示思考过程”的边界:以“结论 → 证据 → 推理 → 验证步骤 → 规避方案”的结构化方式说明;避免输出无关的内部草稿或逐字推演。
AGENTS.md - AI 股票交易系统开发指南
项目结构
本项目采用前后端分离架构,包含以下两个主要部分:
stock-trading/
├── backend/ # Java Spring Boot 单体应用
│ ├── src/main/java/com/stock/
│ │ ├── config/ # 全局配置
│ │ ├── dataCollector/ # 数据采集
│ │ ├── modelService/ # AI 模型(LSTM、情感分析)
│ │ ├── strategyAnalysis/ # 策略分析
│ │ ├── tradingExecutor/ # 交易执行(含 job 调度)
│ │ ├── event/、handler/、logging/、service/
│ │ └── ...
│ └── pom.xml
│
├── frontend-v2/ # React + Vite 前端
│ ├── src/pages/、components/、layouts/、store/、locales/
│ ├── package.json、vite.config.ts
│ └── ...
│
├── models/sentiment/ # 情感模型(TorchScript,Git LFS)
├── docs/ # 文档(00~04 模块需求与设计)
├── .tmp/ # 临时文件(不提交)
├── docker-compose.yml
└── pom.xml
临时文件约定:项目根目录下的 .tmp/ 用于存放所有临时文件和中间脚本。Agent 生成的一次性脚本、临时输出、中间结果等均应放在此目录,且该目录已加入 .gitignore,不纳入版本控制。
构建与运行命令
Backend (Java/Maven)
工作目录: backend/
# 启动应用 (Spring Boot)
mvn spring-boot:run
# 构建打包 (跳过测试)
mvn clean package -DskipTests
# 编译代码
mvn compile
Frontend (React/Vite)
工作目录: D:\ai-stock-trading\frontend
# 安装依赖
npm install
# 启动开发服务器
npm run dev
# 构建生产版本
npm run build
# 代码检查 (Lint)
npm run lint
测试说明
本项目不维护自动化测试(无单元测试、集成测试)。原因与说明见 README - 关于测试。构建时使用 mvn package -DskipTests 跳过测试。
代码规范
Java (Backend)
- 版本: Java 17, Spring Boot 3.2.x
- 风格:
- 类名
PascalCase, 方法/变量camelCase, 常量UPPER_SNAKE_CASE - 使用 Lombok (
@Data,@Slf4j,@RequiredArgsConstructor) 简化代码 - Controller 返回统一泛型对象
Response<T>
- 类名
- 分包策略: 按业务领域分包 (
dataCollector,modelService等),而非按层分包。 - 错误处理: 使用全局异常处理 (
@ControllerAdvice),禁止吞掉异常。
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.
- 6d ago First seen · 392 lines · 4,686 tokens per session scan A 35e348979190
stock-trading AGENTS.md is an instructions file published in the GitHub repository mwangli/stock-trading (147 stars, last pushed 3mo ago), licensed MIT. It adds 4,686 tokens to every session, about $0.0234 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 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.