By atmigtnca
Unified plugin merging Superpowers discipline + OMC orchestration: TDD, systematic debugging, verification gates, multi-agent coordination, MCP tools
Pre-planning consultant for requirements analysis (Opus)
Strategic Architecture & Debugging Advisor (Opus, READ-ONLY)
Expert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategy
Work plan and code review expert — thorough, structured, multi-perspective (Opus)
Root-cause analysis, regression isolation, stack trace analysis, build/compilation error resolution
Invoke parallel document-specialist agents for external web searches and documentation lookup
Use when completing tasks, implementing major features, or before merging to verify work meets requirements. Also use when receiving code review feedback.
Orchestrate parallel scientist agents for comprehensive analysis with AUTO mode
Manage local skills - list, add, remove, search, edit, setup wizard
Use when implementing any feature or bugfix, before writing implementation code
Matches all tools
Hooks run on every tool call, not just specific ones
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Executes bash commands
Hook triggers when Bash tool is used
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Superpowers의 개발 규율 + Oh-My-ClaudeCode의 오케스트레이션
3개 플러그인의 기능 겹침을 제거하고, 각각의 장점만 취합한 Claude Code 통합 플러그인
왜 만들었나 · 빠른 시작 · 스킬 · 에이전트 · 워크플로우 · 크레딧
그냥 내가 쓰려고 만들었습니다.
Claude Code 플러그인을 이것저것 깔다 보니 Superpowers, Oh-My-ClaudeCode, Ralph Loop 3개가 동시에 돌아가고 있었는데, /context를 찍어보니 비슷한 스킬이 이름만 다르게 수십 개 로드되어 있었습니다.
매 턴마다 컨텍스트를 잡아먹고, "이 작업은 brainstorming을 써야 하나 deep-interview를 써야 하나?" 같은 혼란이 반복되길래 — 그냥 하나로 합쳤습니다.
겹치는 영역:
| 도메인 | 이렇게 겹침 |
|---|---|
| 계획 | brainstorming ↔ deep-interview ↔ omc-plan ↔ ralplan |
| 실행 | subagent-driven-dev ↔ ultrawork ↔ autopilot ↔ ralph |
| 코드리뷰 | requesting-code-review ↔ code-reviewer agent ↔ critic agent |
| 검증 | verification-before-completion ↔ verifier agent ↔ ultraqa |
| 병렬작업 | dispatching-parallel-agents ↔ ultrawork ↔ team |
sidep-ops는 이 문제를 해결합니다:
| 항목 | 기존 (3개 플러그인) | sidep-ops | 절감 |
|---|---|---|---|
| 스킬 | ~50개 | 26개 | -48% |
| 에이전트 | 20개 | 15개 | -25% |
| 플러그인 수 | 3개 | 1개 | -67% |
| 컨텍스트 소비 | ~3k 토큰/턴 | ~1.6k 토큰/턴 | ~45% |
# 1. 마켓플레이스 등록
/plugin marketplace add https://github.com/atmigtnca/sidep-ops
# 2. 설치
/plugin install sidep-ops
# 3. 리로드
/reload-plugins
/plugin uninstall superpowers
/plugin uninstall oh-my-claudecode
/plugin uninstall ralph-loop
/context # Skills 섹션에 sidep-ops 스킬이 보이면 성공
OMC가 "어떻게(How)"를, Superpowers가 "왜(Why)"를 제공합니다.
| OMC의 기계 (인프라) | Superpowers의 규율 (원칙) |
|---|---|
| 11 훅 | TDD 필수법칙 |
| 15 MCP 도구 | 체계적 디버깅 |
| 상태 관리 | 검증 게이트 |
| 병렬 엔진 | 2단계 코드리뷰 |
sidep-ops/
│
├── .claude-plugin/
│ └── plugin.json # 플러그인 매니페스트
├── .mcp.json # MCP 서버 설정
│
├── agents/ # 🤖 15개 에이전트 정의
│ ├── executor.md # 구현 (Sonnet, TDD 강화)
│ ├── architect.md # 아키텍처 (Opus, 읽기전용)
│ ├── critic.md # 비평 (Opus, 읽기전용)
│ ├── code-reviewer.md # 코드리뷰 (Opus, 2단계)
│ ├── planner.md # 계획 (Opus)
│ ├── debugger.md # 디버깅 (Sonnet, 4단계)
│ ├── test-engineer.md # 테스트 (Sonnet, TDD)
│ ├── verifier.md # 검증 (Sonnet, 증거 게이트)
│ ├── explore.md # 탐색 (Haiku, 읽기전용)
│ ├── analyst.md # 요구사항 (Opus, 읽기전용)
│ ├── qa-tester.md # QA (Sonnet)
│ ├── security-reviewer.md # 보안 (Opus, 읽기전용)
│ ├── scientist.md # 연구 (Sonnet, 읽기전용)
│ ├── document-specialist.md # 외부 문서 (Sonnet, 읽기전용)
│ └── tracer.md # 인과 추적 (Sonnet)
│
├── skills/ # 🛠️ 26개 스킬
│ ├── design/ # 설계 (SP+OMC 병합)
│ ├── plan/ # 계획 (SP+OMC 병합)
│ ├── execute/ # 실행 (SP+OMC 병합)
│ ├── review/ # 코드리뷰 (SP 병합)
│ ├── meta/ # 스킬 메타 (SP 재작성)
│ ├── tdd/ # TDD (SP)
│ ├── debug/ # 디버깅 (SP)
│ ├── verify/ # 검증 (SP)
│ ├── worktree/ # Git worktree (SP)
│ ├── finish/ # 브랜치 완료 (SP)
│ ├── autopilot/ # 자율 실행 (OMC)
│ ├── team/ # 팀 협업 (OMC)
│ ├── qa/ # QA 사이클 (OMC)
│ ├── trace/ # 가설 추적 (OMC)
│ ├── deep-dive/ # 심층 분석 (OMC)
│ ├── deslop/ # 코드 정리 (OMC)
│ ├── research/ # 외부 검색 (OMC)
│ ├── science/ # 과학 분석 (OMC)
│ ├── ask/ # 멀티모델 (OMC)
│ ├── learn/ # 스킬 추출 (OMC)
│ ├── cancel/ # 모드 취소 (OMC)
│ ├── skill/ # 스킬 관리 (OMC)
npx claudepluginhub atmigtnca/sidep-ops --plugin sidep-opsCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Unified Claude Code plugin merging superpowers workflows (TDD, debugging, planning) with everything-claude-code productivity (agents, learning, hooks, rules)
Agentic development framework for Claude Code — disciplined workflow routing, TDD enforcement, safety hooks, systematic debugging, and code review
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.