Borrowing it
Nothing to install: this file belongs to wuwahe/Many-Foot. 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/wuwahe/Many-Foot/main/AGENTS.mdgit clone --depth 1 https://github.com/wuwahe/Many-FootWrote 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/wuwahe/many-foot/agents-md)<a href="https://agentmods.dev/instructions/wuwahe/many-foot/agents-md"><img src="https://agentmods.dev/badge/instructions/wuwahe/many-foot/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 | $0.09167 | $0.09167 |
| Opus 5 | $0.04584 | $0.04584 |
| Sonnet 5 | $0.01833 | $0.01833 |
| Haiku 4.5 | $0.00917 | $0.00917 |
Grade A, and why
Many-Foot 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 — 1,190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件为 OpenCode / AI 编程 Agent 在 ManyFoot 代码库中工作时提供高信号指导。
AI 在本项目中不应只完成"能跑的代码"，而应以架构师视角进行设计与实现：优先保证模块边界清晰、职责单一、低耦合、高内聚、易测试、易扩展、易替换。
一、核心编码原则
1. 架构师式编码要求
在新增、修改代码时，必须优先考虑：
- 是否符合现有模块边界
- 是否破坏已有继承链、策略链、工厂注册机制
- 是否引入了不必要的耦合
- 是否方便后续扩展新的 Agent、模型厂商、工具、沙箱能力
- 是否可以通过配置扩展，而不是硬编码
- 是否可以独立测试
- 是否符合 Spring Boot 的 Bean 生命周期和条件装配习惯
不要为了快速实现功能而写临时逻辑、硬编码分支、跨模块直接调用、重复代码或"大而全"的类。
二、快速参考
后端
# 构建
mvn clean package
# 运行（端口 8100）
mvn spring-boot:run
# 测试
mvn test
前端
# 进入前端目录
cd foot-ui
# 安装依赖
npm install
# 启动开发服务器（端口 3000）
npm run dev
# 类型检查
npm run typecheck
# 生产构建
npm run build
# 预览构建
npm run preview
三、项目概述
ManyFoot 是基于 Spring AI Alibaba Agent Framework 的 Supervisor 多智能体协作系统，采用 ReactAgent 模式实现智能体编排。
技术栈
后端：
- Spring Boot 3.4.4
- Java 17
- Maven
- Spring AI 1.1.0
- Spring AI Alibaba Agent Framework 1.1.0.0
- Redis (Redisson)
- Docker Sandbox
- Apache Tika（文档解析）
前端：
- React 19
- TypeScript
- Vite
- Tailwind CSS CDN
- react-markdown + remark-gfm
- lucide-react
本项目定位：可扩展的多智能体协作框架，通过 Supervisor 模式协调 8 个智能体完成复杂任务。
四、根包与模块边界
后端根包
com.lh.manyfoot
单模块 Maven 项目。
| 包路径 | 职责 |
|---|---|
agent.core.* |
智能体核心接口：Agent、AbstractAgent、AbstractToolAgent、StreamingAgent、ToolAwareAgent |
agent.context.* |
智能体执行上下文：AgentContext、AgentAttachment、SessionContextHolder |
agent.domain.* |
智能体领域对象：PlanGraph、TaskSpec、ActionCall、ActionResult、DomainDraft 等 |
agent.exception.* |
智能体异常：AgentExecutionException |
agent.factory.* |
智能体工厂：AgentFactory、AgentType |
agent.impl.* |
智能体实现：SupervisorAgent、PlannerRouterAgent、ResearchRetrievalAgent、DomainSpecialistAgent、DocumentSpecialistAgent、ToolActionExecutorAgent、CodeAgent、ChatAgent |
agent.prompt.* |
提示词提供者：AgentPromptProvider 及各智能体专属 PromptProvider |
agent.registry.* |
智能体注册表：AgentRegistry（动态发现所有 Agent Bean） |
agent.strategy.* |
执行策略：ExecutionStrategy、SyncCallStrategy、StreamingStrategy |
agent.supervisor.* |
Supervisor 编排：AgentTool（Agent→ToolCallback 适配器）、SupervisorToolProvider |
agent.support.* |
工具类：SpecialistJsonUtils、AgentMessageFactory |
agent.tool.* |
工具提供者：AgentToolProvider、FullToolProvider |
agent.tool.sandbox.* |
沙箱工具：SandboxTool、SandboxEngine、DocumentParser、ExecutionResultFormatter |
agent.tool.sandbox.domain.* |
沙箱领域对象：SandboxExecutionRequest、SandboxExecutionResult、SandboxCodeType |
models.registry.* |
模型注册：ModelResolver、AiModelRegistrar、ModelRole、AiModelInitializer |
models.failover.* |
故障转移：FailoverChatModel |
models.support.* |
模型支持：ChatOptionsBinder |
models.* |
厂商工厂：AiModelFactory 接口及各厂商实现（Dashscope、OpenAI、Anthropic、DeepSeek、Gemini、Ollama、Qianfan 等） |
config.* |
Spring 配置：RedissonConfig、DockerClientConfig、McpClientConfig、ManyFootToolConfig |
config.properties.* |
配置属性：AiProvidersProperties、SandboxConfig、VendorEnums |
controller.* |
REST API：ChatController、R（统一响应）、HttpStatus |
controller.dto.* |
请求 DTO：ChatRequest |
service.* |
基础设施服务：SandboxContainerManager、RedisUtils |
domain |
共享 DTO / 枚举：ExecutionResult、ExecutionStatus、SandboxContainer、ContainerStatus、AiModelConfig |
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 · 1,190 lines · 9,167 tokens per session scan A d3da5d065496
Many-Foot AGENTS.md is an instructions file published in the GitHub repository wuwahe/Many-Foot (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 9,167 tokens to every session, about $0.0458 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
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 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).
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.
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.