stock-trading: Instructions file for Codex

AGENTS.md

stock-trading AGENTS.md is an instructions file for Codex, OpenCode from mwangli/stock-trading. It costs 17,904 tokens per session, scanned A, original, MIT.

Instructions for a stock-trading system, requiring user-facing communication in Chinese and describing its Java backend, React frontend, machine-learning models, documentation, and temporary-file rules.

In plain words
What is it for?
Use them when developing or reviewing the trading system, especially its data collection, analysis, trade execution, Java services, React interface, models, and documentation.
Why use it?
They keep explanations in the required language and help an agent work in the correct part of a project that has separate backend and frontend applications.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is mwangli/stock-trading's own configuration. It tells Codex and OpenCode how to work on stock-trading itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stock-trading configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mwangli/stock-trading. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mwangli/stock-trading/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mwangli/stock-trading

Made for: Codex, OpenCode.

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.

agentmods badge for stock-trading AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mwangli/stock-trading/agents-md/github.svg)](https://agentmods.dev/instructions/mwangli/stock-trading/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mwangli/stock-trading/agents-md"><img src="https://agentmods.dev/badge/instructions/mwangli/stock-trading/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.

agentmods 80×15 button for stock-trading AGENTS.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 17,904 This file is loaded in full into every session.
When invoked 17,904 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.17904 $0.17904
Opus 5.5 $0.07162 $0.07162
Sonnet 5.5 $0.03581 $0.03581
Haiku 4.5 $0.01790 $0.01790

Measured today against content hash dd998c76685e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 today.

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.

AGENTS.md · 716 lines

How it starts

The opening of the file, as written. The whole thing — 716 lines — stays where its author put it; the contents beside it link to each section on GitHub.

交互语言要求

  1. 强制使用中文:所有回答、思考过程、输出内容必须使用中文
  2. 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
  3. 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)

  1. 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。
  2. 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。
  3. “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。

编译执行控制(项目级)

  • 后续本项目中的代码、配置、Markdown、SQL 及其他文档修改,默认只进行源码和文件层面的检查,不自动执行前端或后端编译、构建、打包、测试、启动或运行验证。
  • 前端 npm run build、npm run tsc、后端 mvn compile、mvn package 等编译或构建动作,必须由用户自行执行;除非用户在当前请求中明确授权,否则 Agent 不得执行。
  • 汇报验证结果时,必须明确说明未执行编译,并将“源码检查通过”与“编译通过”严格区分。
  • 本规则覆盖本文件中其他要求 Agent 自动执行编译、构建、测试或运行验证的旧条款;除非用户在当前请求中明确授权,否则这些旧条款不生效。

源码分析与修改边界(项目级)

  • 后续进行代码检索、依赖分析、架构检查、缺陷定位、重构和文件修改时,默认忽略所有 Maven 构建输出目录 **/target/** 以及其中的 *.class、生成资源和其他编译产物。
  • target/ 中的内容不得作为源码存在性、调用关系、模块依赖、Port/Adapter 残留或重构完成状态的判断依据;相关结论必须以 src/、pom.xml、配置和正式文档等受版本管理的源文件为准。
  • 默认不读取、不修改、不删除 target/ 内文件。只有用户在当前请求中明确要求清理或检查构建产物时,才允许对指定输出目录执行操作。
  • 搜索命令应显式排除 target,例如使用 rg --glob '!**/target/**';文件遍历和自定义检查脚本也必须应用同等排除规则。

AGENTS.md - AI 股票交易系统开发指南

系统目标与最高优先级设计原则

本项目的最终目标是建设一个面向 A 股的自学习、自适应、无人值守自动交易系统。正常生产链路不依赖人工审批、人工选择模型、人工调整权重或持续人工监督,系统必须能够基于真实数据和交易反馈自动完成:

数据更新 → 数据校验 → 周期训练 → 候选评估 → 自动晋级或淘汰
→ 自动预测与排名 → 分阶段交易 → 券商执行
→ 成交与绩效回写 → 滚动评估 → 自动调权、回退和再训练

后续设计和实现必须遵循以下要求:

  1. 无人值守闭环:模型训练、候选比较、生产切换、融合调权、策略参数调整、失效回退和再训练均由统一调度与确定性规则自动完成。人工界面用于观察、诊断和紧急停机,不作为正常晋级或交易流程的必经审批环节。
  2. 最简单、最快速实现:优先选择能够形成完整闭环的最少组件、最少状态和单一路径。不得为假设中的扩展增加多套框架、重复评分、兼容适配层、人工工作流或无调用方抽象。
  3. 允许直接收敛旧机制:本项目不要求前向兼容或保留冗余历史实现。新方案落地后应删除被替代的人工激活、重复 Gate、旧配置、旧状态和旁路入口,只保留一个权威流程。
  4. 自学习采用周期增量闭环:优先使用定时重训、不可变快照、Champion-Challenger 自动比较和生产反馈评估,不引入复杂在线学习平台。只有现有周期闭环无法满足目标时,才允许增加实时在线学习机制。
  5. 自适应必须有边界:允许系统自动调整模型版本和融合权重,但所有可调参数必须有明确上下限、观察窗口、最小样本和自动回退条件,禁止模型或 Agent 直接修改权限、资金、幂等规则或券商凭据。
  6. Gate 只保留必要硬门禁:Gate 仅用于阻止数据/制品无效、数值异常、样本明显不足、回撤越界和真实交易安全违规。普通质量指标统一进入一个可解释的综合评分,不为每个指标建立独立的一票否决规则。
  7. 自动晋级和自动回退:候选模型通过硬门禁且综合评分稳定优于当前生产模型时自动小权重上线;根据滚动实盘/影子结果自动升权。出现数据异常、输出塌缩、回撤越界、持续劣化或运行失败时自动降权至零并回退到最近健康版本。
  8. Java 保留最终交易权威:无人值守不等于取消安全边界。市场事实、账户、权限、资金、持仓、T+1、交易时间、价格保护、仓位上限、最大亏损、幂等和券商执行仍由 Backend 的确定性 Java 逻辑最终决定;模型和 Agent 不能绕过这些规则。
  9. 默认自动、失败保守:正常情况下系统自动推进;证据不足、状态不一致或关键依赖异常时停止新增风险并自动回退,不等待人工确认后继续冒险。

Read the full file on GitHub · 716 lines

Changes

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.

  1. today Changed · +10 lines · +1,150 tokens per session dd998c76685e
  2. 2d ago Changed · +13 lines · +542 tokens per session 9ddfeabdebd4
  3. 4d ago Changed · +21 lines · +454 tokens per session a829c7d51436
  4. 5d ago Changed · +47 lines · +1,563 tokens per session b2d13d1600b6
  5. 6d ago Changed · +14 lines · +795 tokens per session 1f764ebba3a7
  6. 7d ago Changed · -3 lines · +258 tokens per session cebfe487ede9
  7. 10d ago Changed · +86 lines · +4,230 tokens per session 7004e8f18ac6
  8. 12d ago Changed · +31 lines · +1,846 tokens per session 75acdcc4fc5c
  9. 13d ago Changed · +7 lines · +196 tokens per session 116389bb8314
  10. 16d ago First seen · 490 lines · 6,870 tokens per session scan A 5b7e5923937c

Subscribe to this mod's changes

stock-trading AGENTS.md is an instructions file published in the GitHub repository mwangli/stock-trading (148 stars, last pushed today), licensed MIT. It adds 17,904 tokens to every session, about $0.0716 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.

Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,750 tokens

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.

deepseek-ai/deepseek-harness · 4,261 tokens