파일 수 > 3개 / 독립 작업 > 2개 / 리팩토링 범위 > 1 디렉토리 → 병렬 에이전트 사용

**Agents analyze existing code** - use for reviews, audits, and quality checks.

> **Full agent type definitions:** See `references/agents.md` for complete 37 agent role specifications across 7 swarms (Engineering, Operations, Business, Data, Product, Growth, Review).

The lead agent (Claude main) should invoke specialized agents when:

**Version 3.0.0**

> Claude Code 서브에이전트 시스템 기반 작성 가이드

<!-- Parent: ../AGENTS.md -->

This skill provides Apple Human Interface Guidelines for macOS. Apply these rules when building, reviewing, or designing Mac apps using SwiftUI or AppKit.

Prompts for parallel documentation review agents.

Problem definition → small, safe change → change review → refactor — repeat the loop.

Comprehensive code review knowledge base for React applications (framework-agnostic). Contains rules across security, performance, architecture, and quality categories. Each rule includes detailed exp

> Load on-demand when spawning agents

Proactively invoke agents when trigger conditions are met:

Code review rules for Supabase applications. Covers RLS security, auth patterns, query performance, migration workflows, and type safety. Each rule includes incorrect/correct examples, CWE/OWASP mappi

Shared code-review agent definitions used by /code-review and /post-plan.

The project uses the following models for AI agents:

This scope governs the Claude Code subagent wiring files that connect Claude Code's Agent tool to Armature persona definitions. Core agent wiring (reviewer, planner, red team) uses thin pointers to `.

When and how to use specialized agents

**Projekt-specifikke agenter** (review, frontend, …) ligger i `.claude/agents/` — se `.claude/README.md` § *Agenter*. Tabellen nedenfor dækker typisk **globale** agenter under `~/.claude/agents/` og t

1. [compiler.py](#compilerpy) — ingest agent (tool-calling loop)

Build a frontend-first internal micro-task platform.

| Agent | Purpose | When to Use |

Reviews code for DRY violations, complexity, naming issues, and best practices.

Cập nhật guardrails của các agent (đặc biệt là test commands, coverage commands, start/stop commands) sau khi `/detect-stack` và `PROJECT-PROFILE.md` đã được điền đầy đủ.

1. **Documentation bug** - Line 85 listed invalid types ('context', 'temporary'). **FIXED**

This guide reviews common workflow and agent patterns.

Quick reference for which agent to dispatch for each task type in the Seam monorepo.

This document defines specialized agents that can be used with Claude Code to enforce architectural principles and assist with specific tasks.

**A review guide for Go + vanilla JS + Wails v2 desktop applications**, organized by priority and impact. This app spawns external processes, has no database, and targets Windows.

Run after making React changes to catch issues early. Use when reviewing code, finishing a feature, or fixing bugs in a React project.

> Version: 1.3 | CLAUDE.md Synced: MVP 1.5 | Last Updated: April 15, 2026

**Every worker agent has a paired critic. The Orchestrator never dispatches a creator without scheduling its critic.**

This file provides guidance for AI coding agents working on this Flutter project.

> Agents are proposed when repeated specialist patterns are detected or when tech detection identifies technologies needing specialized expertise.

Create a new subagent definition file

Review UI code for compliance with these rules. Output concise findings in `file:line` format.

When your AI agent hires other AI agents for specialized subtasks.

**Version 1.0.0**

Use this reference for agents that extract structure, rank candidates, classify actions, route work, moderate content, or gate automation.

| Agent | Tier | Model | Purpose |

'Merge overlapping review specialist agents into a single general-review-specialist.

docs/plans/

Copy and customize these examples for your needs.

Known review agents that can be invoked on a PR, their GitHub usernames, and how they are triggered.

> **Note:**

This file defines the mandatory rules for AI coding agents

- Always use English for file contents and generations.

> This document is for AI agents and LLMs to follow when writing, reviewing, or debugging redux-saga code. It compiles all rules and references into a single executable guide.

Reduces token usage from paid providers by offloading work to local LM Studio models. Use when: (1) Cutting costs—use local models for summarization, extraction, classification, rewriting, first-pass review, brainstorming when quality suffices, (2) Avoiding paid API calls for high-volume or repetitive tasks, (3) No extra model configuration—JIT loading and REST API work with existing LM Studio setup, (4) Local-only or privacy-sensitive work. Requires LM Studio 0.4+ with server (default :1234). No CLI required.

End-of-week review. Summarize the week, surface patterns, prune stale notes.