Phase 2: Liest eine ADR und koordiniert den Aufbau der Agenten- und Workflow-Dateien.

| Agent | Model | Best For | Key Trait |

Quick reference for all available agents and skills. Custom agents live in `~/.claude/agents/`, skills live in `~/.claude/skills/`.

Quick reference for integrating Mapbox MCP Server into AI applications for production use.

> Source: https://ai-sdk.dev/docs/agents/overview.md

> **Last Updated**: January 27, 2026

Mix human and AI responses in the same thread for customer support and hybrid workflows.

Synchronizes all project documentation files to ensure consistency and accuracy across:

<!-- Managed by agent: keep sections & order; edit content, not structure. Last updated: 2025-10-09 -->

This file provides guidance to AI coding assistants working in this repository.

Tools and Agents are two key concepts in building advanced AI systems, particularly those involving Large Language Models (LLMs):

This reference helps you make good decisions when building with `@chenglou/pretext`. Read SKILL.md first for the basics; come here when you need deeper guidance.

Production server for faion.net infrastructure.

> **CEO**: Claude (gives orders)

AI 코딩 에이전트 거버넌스, Copilot/Claude 통합, 엔터프라이즈 AI 정책

**Subagents for research + build; background Bash for parallel compute.**

Guide for maintaining and extending the commands/skills system in Mechanic.

> **Branch**: `agents-workbench` (local-only, NEVER push)

This project uses **bd** (beads) for issue tracking.

Building agents that can intelligently use tools and make decisions is only half the journey; ensuring that these agents are accurate, reliable, and performant is what truly defines their success. [Ll

Display all available BMAD agent personas with their descriptions and primary tasks.

> **Note:** `CLAUDE.md` is a symlink to this file.

Stop. Read this section before doing anything.

This directory contains the source assets that are bridged into Codex skills and related workflows.

**Name:** `devops-infrastructure-expert`

> **Note:** `CLAUDE.md` is a symlink to this file.

This file defines coordinated multi-agent workflows for enterprise accessibility scanning in the Claude Code environment.

**CRITICAL**: All agents MUST follow the task coordination protocol:

Welcome! This is your command center for working with the Shepherd Church Management System. Think of this as your onboarding guide and quick reference for all AI agents working on this project.

Workflow automation agents using Gemini CLI, Groq API, and Amp CLI.

1. [ToolLoopAgent](#toolloopagent)

Gemini MCP (ACP bridge) routing and delegation rules

Spawn multiple parallel coding agents to work on issues simultaneously.

implement-feature dispatches multiple agents concurrently into the same working directory. Two agents editing the same file simultaneously produce merge conflicts or silent overwrites. The Agent tool supports `isolation: 'worktree'` but implement-feature never uses it.\n\nSymphony enforces three workspace invariants per issue: agent runs only inside workspace_path; workspace_path must be inside workspace_root; workspace key characters restricted to [A-Za-z0-9._-].\n\n**Proposed behaviour:**\n- implement-feature: set `isolation: 'worktree'` on all Agent tool calls for task execution.\n- Worktree naming: derive from task ID using Symphony's sanitization rule (replace non-[A-Za-z0-9._-] with `_`): e.g., `.worktrees/task-1-2/`.\n- After agent completes in the worktree, merge changes back to the main branch (or flag conflicts for operator resolution).\n- start-task skill: detect if running inside a worktree and adapt file path references accordingly.\n\n**Acceptance criteria:**\n- Concurrent task agents each write to a distinct worktree; no shared file edits between agents on separate tasks.\n- Worktree is cleaned up automatically if the agent makes no changes (already the default Agent tool behaviour).\n- Merge-back step produces a clear conflict report if two agents modified the same file.

This implementation adds 5 critical agents that fill gaps in the existing agent ecosystem, enabling

Show the full AI agent reference guide for this project.

Guide for adding or updating model pricing entries in Langfuse. Use this when

> Best practices for building agents and agentic applications with Plano — the AI-native proxy and dataplane. Covers configuration, routing, agent orchestration, filter chains, observability, CLI oper

<Callout type="warning">

Claude Code includes built-in subagents that Claude automatically uses when appropriate. Each inherits the parent conversation's permissions with additional tool restrictions.

A quick reference for applying 12 Factor Agents principles to multi-agent system design. Based on the [12 Factor Agents](https://github.com/humanlayer/12-factor-agents) framework.

Sources: Production evaluation patterns, inspired by anthropics/skills agent architecture

The OpenAI Agents SDK bridges your FastAPI chat endpoint and MCP server. It:

When you have something valuable to teach an AI coding assistant, you face a fundamental choice: package it as a **skill** (a portable SKILL.md file) or build it as an **agent** (a bundle with custom

There is a persistent myth in the design of intelligent systems: that better decisions require evaluating more alternatives more rigorously. Classical decision theory — subjective expected utility, co

Use these endpoints to discover available agents and choose the right tools for a request.

> 20 courses teach this skill

Apply mixture of agents (moa) in AI agent workflows.

`★ Insight ─────────────────────────────────────`

Blazor is a .NET web framework for building interactive client-side web UIs using C# and Razor syntax. It supports multiple hosting models: Blazor Server (SignalR-based), Blazor WebAssembly (client-si