- **Typed contracts are non-negotiable.** Never widen a contract field to `dict[str, Any]` or `Any`. Every module output is a typed Pydantic `BaseModel`.

> AI 原生 Tool Calling 架构 — 单 runtime，LLM 自主编排。

- 产品：约拍平台（支持 iOS/Android）

本仓库采用 **基于分支的开发方式**，并要求对每个有意义的分支进行记录。

| Constant | Value | Purpose |

Implemented the ability to resume finished agents **and agents that hit errors** by sending them a message. Previously, when an agent finished or hit an error (like rate limits), it would completely s

<!-- Created: 2026-03-23 12:30 -->

**Role**: You are a senior software engineer. Write high-quality, well-structured, maintainable code appropriate to the current file’s language. No emojis or fluff.

See details in CLAUDE.md

this is a source code for a rust cli called clops

Spawn subagents to develop features in parallel worktrees

Initialize agent team for an existing project

A **subagent** is like hiring a temporary assistant to do part of the job while you continue with other work.

- All agents extend `BaseAgent` from `conductor.agents.base`

Two working hooks. Most Claude Code hook types are broken (Jan 2025).

- YAML frontmatter MUST include: `name`, `subagent_type`, `description`, `tools`, `model`, `color`, `skills`

> **Scope:** AI coding agents (Claude, Cursor, Copilot, and any other AI assistant operating in this codebase).

자율 AI 코딩 에이전트 저장소 목록 (Stars 순)

- **Independent searches**: Looking for multiple unrelated things in a codebase

- [Creating Agents](#creating-agents)

Always set `model:` when spawning subagents. Haiku costs 12× less than Sonnet — use it for all search and explore work.

This file documents all 5 Agno-powered agents in the WAIGenie framework.

<!-- 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

maa-main # 主控制台 - 监控所有session

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.

../../prompt/instructions/ecc-common-agents.md

| 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

> 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