The `remote` crate is the hosted Vibe Kanban Cloud server: an Axum HTTP API, a React SPA frontend, and real-time sync via ElectricSQL.

- Component: task-bar

> **Purpose.** This document gives Codex CLI and human contributors a **single source of truth** for how to build and evolve **AI-MarketTracker** without code drift. It defines non-negotiables, coding

This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, etc.) when working with skills in this repository.

What are the Tradeoffs?

This project uses [nexus-agents](https://github.com/williamzujkowski/nexus-agents) v2.3.0 for multi-agent orchestration.

These instructions guide any automated agent (such as Codex) that modifies this

> **Read First:** [docs/PHILOSOPHY.md](../docs/PHILOSOPHY.md) - Framework philosophy and principles

Learn how to create powerful, interconnected Claude sub-agents using advanced patterns.

Subagents are isolated Claude instances spawned within your session via the Agent tool.

Apply this rule when:

Delegate read-only analysis tasks to Gemini CLI agents

> Nutze 6 AI Agents um neue Discord Bot Features zu entwickeln: Requirements → Architecture → Development → QA → Deployment

A guide to securing Claude Code and Agent SDK deployments with isolation, credential management, and network controls

**Feature Type:** Automatic

The agents documentation contains 6 core markdown files:

Three-criteria evaluation framework for autonomous agent deployment

| Use Case | Use | Why |

Parallel execution requires:

1. 1

As of early 2026, Cursor has shifted heavily toward **Cloud Agents** and **Dynamic Context Discovery**. If you are using Cursor for your MVP build (Step 5 of the vibe-coding workflow), use these patte

Instructions for sub-agents working in this repository.

Deliver the BUILD_PLAN in phase order while protecting tenant isolation and compliance requirements.

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

Use this skill to onboard a project onto PowerSync without trial-and-error. Treat this as a guided workflow first and a reference library second.

> This document is mainly for agents and LLMs. For the overview and quick reference, see `SKILL.md`.

- **Always bump the npm version** (`npm version patch`) and `npm publish` after any change that gets pushed to main -- code, docs, config, anything.

| Agent | Role | Model | MCP Servers |

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

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.

You are a system of 4 agents working in sequence.

> This document is mainly for agents and LLMs. For the overview and quick reference, see `SKILL.md`.

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

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

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):

Production server for faion.net infrastructure.

The `ToolLoopAgent` class encapsulates LLM configuration, tools, and behavior into reusable components.

**Version:** 2.1.0

Quick reference for building store locators and location finders with Mapbox.

> **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.

Guidelines and gotchas for AI agents working on the overcode codebase.

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

- 직접 코드 작성하지 않음