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/iceygo/windbot/agents-mdgit clone --depth 1 https://github.com/IceYGO/windbotWhat 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 | $0.05254 | $0.05254 |
| Opus 5 | $0.02627 | $0.02627 |
| Sonnet 5 | $0.01051 | $0.01051 |
| Haiku 4.5 | $0.00525 | $0.00525 |
Grade A, and why
windbot 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 2d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
项目定位
- WindBot 是面向 YGOPro/YGOSharp/SRVPro 协议的 C# 决斗机器人，本质上是一个自动操作的 YGOPro 客户端。
- 主程序基于 .NET Framework 4.8，解决方案支持 Any CPU 和 x86，当前默认平台与 CI 主验证平台为 Any CPU；项目是旧式非 SDK
.csproj，不要默认使用仅适用于现代 .NET/SDK 项目的工具和 API。 - 机器人只能使用服务器发给当前客户端的信息。对方手牌、牌组、盖卡等未公开信息通常只有数量或
Id == 0的占位对象，不能读取、推断或硬编码其真实内容。 - 服务器在要求客户端响应时已经给出了合法操作候选。牌组 AI 的职责主要是判断“现在是否值得这样做”以及“选哪个目标”，而不是复述发动条件。
解决方案与运行链路
解决方案包含两个项目：
WindBot.csproj：控制台主程序，包含网络协议、客户端状态和全部决斗 AI；输出WindBot.exe。BotWrapper/BotWrapper.csproj：供 YGOPro 人机模式调用的轻量启动器，整理启动参数并启动WindBot.exe；输出Bot.exe。
主程序的调用链如下：
Program.cs读取命令行或配置文件，初始化牌组注册表和cards.cdb，然后以单实例模式或 HTTP server 模式启动机器人。Game/GameClient.cs建立连接、进入房间并把收到的数据包交给GameBehavior。Game/GameBehavior.cs按StocMessage/GameMessage解包，更新Duel、ClientField、ClientCard等客户端可见状态，并在需要响应时调用GameAI。Game/GameAI.cs整理服务端给出的合法候选，按优先级查询当前牌组的Executor并返回决策；GameBehavior负责验证、编码并把响应发回服务器。Game/AI/DecksManager.cs通过反射发现带[Deck]的执行器，并为每局实例化对应牌组 AI。Game/AI/Executor.cs定义公共回调和有序的CardExecutor列表；各牌组通常继承DefaultExecutor。
server 模式会为每个 HTTP 请求创建独立线程和独立的 GameClient/Duel/Executor。不要把单局可变状态放进静态字段，也不要让不同机器人实例共享未同步的牌组状态。
目录职责
Game/：决斗状态、消息处理、主阶段/战斗阶段动作模型。Game/AI/：AI 调度、选择队列、通用决策、卡片扩展方法和领域常量。Game/AI/Decks/：各牌组的专用执行器，是新增或调整牌组逻辑的首选位置。Game/AI/Enums/：跨牌组共享的已知卡分类，例如压制卡、危险怪兽、不可取对象等。YGOSharp.Network/：TCP 数据帧和 CTOS/STOC 协议层。YGOSharp.OCGWrapper/、YGOSharp.OCGWrapper.Enums/：卡片数据库模型和协议/规则枚举。Decks/：运行时.ydk牌组文件。Dialogs/：运行时 JSON 对话资源。BotWrapper/：外部 bot 启动包装器及其配置。
层次边界应保持清晰：
- 协议解析和客户端状态同步放在
GameBehavior/网络层。 - 通用、确实能被多个牌组复用的决策放在
DefaultExecutor、AIUtil、CardExtension或共享枚举中。 - 单一牌组的展开路线、卡片优先级和临时标志留在对应牌组执行器中。
- 不要为了一个牌组的特例污染协议层或全局默认逻辑。
AI 决策模型
AddExecutor 顺序就是优先级
GameAI 会按注册顺序遍历 Executor.Executors，再遍历服务器给出的候选卡；第一个匹配且返回 true 的执行器立即胜出。因此：
- 构造函数中的
AddExecutor顺序具有决定性影响，调整顺序属于行为修改，不是格式整理。 - 更具体、更紧急的响应放在前面，通用处理和兜底放在后面。
- 同一张卡的不同效果或不同局面可以注册多次；需要用
Card、ActivateDescription、CurrentTiming和当前连锁状态区分。 AddExecutor(type, cardId)表示匹配后无条件接受；只应在所有合法出现时都适合执行的场景使用。GoToBattlePhase、GoToEndPhase、Surrender等没有卡片上下文，其条件函数不能依赖Card。
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.
- 2d ago First seen · 169 lines · 5,254 tokens per session scan A 6261d7e4c834
windbot AGENTS.md is an instructions file published in the GitHub repository IceYGO/windbot (103 stars, last pushed 3d ago), licensed MIT. It adds 5,254 tokens to every session, about $0.0263 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
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 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
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, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.