<!-- Repo-level context for AI coding agents (Gemini, Claude, open-swe, etc.)

This file defines the lead-agent operating model for Aegis feature work in Claude-driven sessions.

How to use different LLM models for different agents in Present-Agent2.

Analyze conversation context and suggest relevant agents to use

Python module/script

| Agent ID | Owns | Entry dirs | Model | Can parallel with |

Please use subagents to do the following tasks: $ARGUMENTS

Notes on when and how to use subagents for parallel work.

> This file defines the agent team structure, sub-agent roles, and orchestration patterns for the MTA Website project.

This directory is the canonical home for all agent definitions in this repo. Both Claude Code and OpenCode reference these files as the single source of truth.

`{{PROJECT_NAME}}` is {{PROJECT_SUMMARY}}.

이 문서는 AI 가계부 프로젝트의 모든 코딩 컨벤션을 정의합니다.

Full Claude Code `settings.json` hook compatibility layer. Intercepts OpenCode events to execute external scripts/commands defined in Claude Code configuration.

| Aufgabe | Agent | Wann |

This project uses Claude Code project settings (in `.claude/settings.json`) to enforce constraints deterministically.

`~/.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

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

Agent configurations for Claude CLI. Tools use Claude's tool names.

This is the highest-density area of unknown unknowns because AI agent systems are new enough that most developers have never encountered these failure modes.

|v1.0.0|Velt|April 2026

{{PROJECT_ONE_LINE}}

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.

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.

Each skill has two parts:

Advanced semantic retrieval and concept matching across PAI history. USE WHEN you need to find conceptually related solutions or patterns, even if keywords don't match.

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 directory contains supporting files for the patterns skill.

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

This project uses C# 14 and .NET 10. Always prefer features from these versions over older

This directory contains supporting files for the patterns skill.

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.

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.

List all currently open issues

Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (Claude picks recommended defaults).

You are the Product Visionary.

Create isolated git worktrees for feature work with smart directory selection and safety verification. Use when starting feature work that needs isolation from current workspace or before executing implementation plans.

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

Eigenständige Dokumentsynthese aus RAG-Kontext. Generiert versionierte Markdown-Dokumente (Systemzustand, Grow-Zusammenfassung, Skill-Inventar etc.) via LLM auf Basis lokaler RAG-Retrieval-Ergebnisse. Kein RAG-Rückschreiben – nur Quell-Retrieval.