`~/.claude/agents/`에 위치:

List all defined agents with their roles, tiers, and teams

Read the CLAUDE subagent documentation:

Thaler and Sunstein's choice architecture maps directly to hook enforcement design -- blocking hooks are mandates, context-injecting hooks are nudges, and the graduation between them prevents alert

> 来源：CLAUDE.md v2.0

GSD는 특수화된 에이전트들을 사용하여 복잡한 작업을 자율적으로 처리합니다.

Přiřazení agentů k úkolům, hotové instrukce pro spuštění

Sub-agents let you run background tasks without blocking the main conversation. When you spawn a sub-agent, it runs in its own isolated session, does its work, and announces the result back to the cha

CLAUDE.md

Parallel orchestration engine. Uses a Blackboard architecture for multi-agent collaboration without bottlenecks.

A PAI modular skill for genesis.

`AGENTS.md` is the repo-level contract for agents working in this repository.

对 ExoMind 项目的 GitHub Issues 进行周期性分诊治理——关闭已完成的、合并重叠的、标注优先级、同步过时描述，保持 Issue 池的信噪比。

Use canonical instructions.

Proactively analyzes the current state of the project and history to suggest the next logical steps or warn about potential issues. USE WHEN starting a session or finishing a major task.

Follow these steps to refresh the local environment of other agents, ensuring that their agent skills and plugins are fully up-to-date.

If `BOOTSTRAP.md` exists in this workspace, follow it first. After completing its instructions successfully, delete it. Once deleted, you will not see it again — your ongoing instructions come from HE

This document defines the agent orchestration for the Procurement role. Agents work together to handle the full procurement lifecycle: vendor evaluation, price comparison, bid analysis, purchase order

A PAI modular skill for vibe.

A PAI modular skill for voice.

Handles agent-to-agent negotiations, commerce, and micro-payments using the Agentic Commerce Protocol (ACP). USE WHEN you want to hire other agents or trade resources/data for value.

Use this file only in stages `3.2` and `3.3`.

Uses Zero-Knowledge Proofs (ZKP) to share insights with other agents without revealing raw sensitive data. USE WHEN you need to collaborate while protecting your "Soul" or private history.

Spatial design engine. Manages virtual Dojo reconfiguration via SpacetimeDB world-state transactions.

**角色**：Master Executor + 流程協調者

List all currently open issues

bg

Interact with WDK-managed wallets — check balances, send USDT, manage Aave positions, query TRON energy costs

每日系統健康報告。執行檢查腳本並輸出報告。

Purpose:

LLM-powered market sizing using top-down and bottom-up methodologies.

LLM-powered Porter's Five Forces framework analysis for any industry or company.

抓取微信公众号文章并转换为 Markdown 文档。使用脚本自动获取文章标题、作者、正文内容，保留格式并保存为 .md 文件，支持下载图片到本地。适用场景：用户要求抓取/获取/下载/保存微信公众号文章内容为 Markdown 格式，或给出 mp.weixin.qq.com 链接需要提取内容。支持 Obsidian 模式（使用 -obsidian 参数）。

Agents are trained to help visitors according to the business need.  An agent’s area of expertise is referred to as a skill. For example, you can create the skill "sales" for agents who are sales repr

> **Site**: https://hallofshame.cc — A humorous forum for stories of AI misbehavior, failures, and unintended comedy.

>

Validate and package a Claude Code Skill into a distributable zip file

**版本**: 1.1 (新增次日早晨定时触发机制)

Before responding to ANY user request, you MUST:

This document provides context for AI agents and assistants to effectively assist with the development of this project.

AGENTS.md

我是主Agent（reits-expert）的交通物流资产分析师，不是主Agent。我接受主Agent的任务调度，执行交通物流类资产（高速公路、地铁/轨道交通、港口、物流仓储）的专项分析与估值建模工作，完成后将结果回传给主Agent。

> **Scope:** Applies to all Windsurf conversations **within this repository** (and by convention across Synaptix repos).

22+ lifecycle hooks intercepting/modifying agent behavior. Context injection, error recovery, output control, notifications.

Follow the same repo contract as every other AI tool:

- EV3 robot controlled by a PS4 controller using Pybricks.

Located in `.claude/agents/`:

Three working hooks for session lifecycle management.