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/nuwax-ai/nuwax/agents-mdgit clone --depth 1 https://github.com/nuwax-ai/nuwaxWrote 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/nuwax-ai/nuwax/agents-md)<a href="https://agentmods.dev/instructions/nuwax-ai/nuwax/agents-md"><img src="https://agentmods.dev/badge/instructions/nuwax-ai/nuwax/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 | $0.05807 | $0.05807 |
| Opus 5 | $0.02903 | $0.02903 |
| Sonnet 5 | $0.01161 | $0.01161 |
| Haiku 4.5 | $0.00581 | $0.00581 |
Grade A, and why
nuwax 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 — 948 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent System Documentation
系统概述
本项目集成了先进的 AI Agent 系统,为用户提供智能化的代码开发辅助功能。系统通过 SSE (Server-Sent Events) 实现实时通信,支持流式对话和工具调用。
AI Agent 架构
核心组件
1. SSE 连接管理器 (utils/sseManager.ts)
负责管理与服务器的实时连接:
- 自动重连机制
- 连接状态监控
- 消息分发和处理
- 错误恢复策略
2. AppDev Web IDE 系统
文件管理 Hook (hooks/useAppDevFileManagement.ts)
- 项目文件树管理
- 文件内容缓存和同步
- 文件修改状态跟踪
- 自动保存机制
开发服务器 Hook (hooks/useAppDevServer.ts)
- 开发环境自动启动
- 服务器状态监控
- 保活机制
- 端口自动分配
聊天系统 Hook (hooks/useAppDevChat.ts)
- SSE 实时连接管理
- 消息流式处理
- AI 思考过程展示
- 工具调用状态管理
3. 消息处理器 (pages/AppDev/index.tsx)
处理不同类型的 AI 消息:
agent_thought_chunk: AI 思考过程agent_message_chunk: AI 回复内容tool_call: 工具调用通知prompt_end: 会话结束
4. 会话管理
- 会话 ID 生成和管理
- 多会话并发支持
- 会话状态持久化
AI 功能特性
1. 智能对话
interface ChatMessage {
id: string;
type: 'ai' | 'user' | 'button' | 'section' | 'thinking' | 'tool_call';
content?: string;
sessionId?: string;
isStreaming?: boolean;
}
2. 思考过程可视化
- 实时显示 AI 思考过程
- 上下文理解展示
- 推理路径可视化
3. 工具调用支持
- 自动执行开发任务
- 文件操作自动化
- 代码生成和修改
4. 流式响应
- 实时文本流显示
- 打字机效果
- 增量内容更新
AppDev Web IDE 功能
1. 文件管理系统
文件树组件 (pages/AppDev/components/FileTree/index.tsx)
- 支持文件夹展开/折叠
- 文件选择和编辑
- 文件创建、删除操作
- 拖拽操作支持
- 右键菜单功能
文件内容管理
- 文件内容缓存机制
- 修改状态实时跟踪
- 自动保存功能
- 文件类型识别
2. 代码编辑器
Monaco Editor 集成 (pages/AppDev/components/MonacoEditor/index.tsx)
- 支持多种编程语言语法高亮
- TypeScript/JavaScript 智能提示
- 自定义主题配置
- 实时内容同步
- 代码折叠和格式化
3. 实时预览系统
预览组件 (pages/AppDev/components/Preview/index.tsx)
- iframe 嵌入式预览
- 自动刷新功能
- 全屏预览支持
- 错误状态处理
- 加载状态显示
4. 开发服务器管理
服务器生命周期管理
- 自动启动开发环境
- 自动端口分配 (3000-4000 范围)
- 服务器状态实时监控
- 保活机制防止服务中断
- 错误恢复和重试机制
5. 错误恢复机制
开发环境错误处理
- 后端服务不可用时的前端开发支持
- URL 参数控制 (
?mock=true/false) - localStorage 持久化配置
- 模拟网络延迟 (300ms)
- 完整的 API 端点模拟
集成接口
核心服务接口
发送聊天消息
const response = await sendChatMessage({
user_id: 'app-dev-user',
prompt: userInput,
project_id: workspace.projectId,
session_id: sessionId,
request_id: generateRequestId(),
});
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 · 948 lines · 5,807 tokens per session scan A 921d4f85d6ba
nuwax AGENTS.md is an instructions file published in the GitHub repository nuwax-ai/nuwax (880 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,807 tokens to every session, about $0.0290 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
zeroclaw CLAUDE.md
Claude Code instructions for zeroclaw-labs/zeroclaw, covering claude.md — zeroclaw (claude code), claude code settings, hooks and slash commands.
ReMe AGENTS.md
AGENTS.md instructions for agentscope-ai/ReMe, covering agents.md, project principles, sources of truth, repository map and development setup.
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.
Agentlas-OS GEMINI.md
Gemini CLI instructions for agentlas-ai/Agentlas-OS, covering gemini cli adapter, public release boundary, startup, default behavior and global command.
AgentEval copilot-instructions.md
Copilot instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.
framework AGENTS.md
AGENTS.md instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.