~ / rigs / secretj / secretj-claude-config

secretj/secretj-claude-config

개인 Claude Code dotfiles — agents, commands, skills, hooks, memory, MCP 템플릿. clone + install.sh 로 환경 복원.

↗ GitHub ★ 0 no license updated 1d ago personal setup Claude Code Claude plugin
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.8k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit secretj/secretj-claude-config/agents ./rig-secretj-claude-config/agents
$ npx degit secretj/secretj-claude-config/skills ./rig-secretj-claude-config/skills
$ npx degit secretj/secretj-claude-config/hooks ./rig-secretj-claude-config/hooks

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit secretj/secretj-claude-config/skills/blog-post .claude/skills/blog-post
$ npx degit secretj/secretj-claude-config/skills/build-service .claude/skills/build-service
$ npx degit secretj/secretj-claude-config/skills/distill .claude/skills/distill
$ npx degit secretj/secretj-claude-config/skills/html-doc .claude/skills/html-doc
$ npx degit secretj/secretj-claude-config/skills/sync-knowledge .claude/skills/sync-knowledge
$ npx degit secretj/secretj-claude-config/skills/verify .claude/skills/verify
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/architect.md
$ curl -fsSL --create-dirs -o .claude/agents/codebase-analyzer.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/codebase-analyzer.md
$ curl -fsSL --create-dirs -o .claude/agents/codebase-locator.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/codebase-locator.md
$ curl -fsSL --create-dirs -o .claude/agents/codebase-pattern-finder.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/codebase-pattern-finder.md
$ curl -fsSL --create-dirs -o .claude/agents/designer.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/designer.md
$ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/developer.md
$ curl -fsSL --create-dirs -o .claude/agents/docs-analyzer.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/docs-analyzer.md
$ curl -fsSL --create-dirs -o .claude/agents/docs-locator.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/docs-locator.md
$ curl -fsSL --create-dirs -o .claude/agents/infra.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/infra.md
$ curl -fsSL --create-dirs -o .claude/agents/lead.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/lead.md
$ curl -fsSL --create-dirs -o .claude/agents/marketer.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/marketer.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/pm.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/pm.md
$ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/qa.md
$ curl -fsSL --create-dirs -o .claude/agents/security.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/security.md
$ curl -fsSL --create-dirs -o .claude/agents/web-search-researcher.md https://raw.githubusercontent.com/secretj/secretj-claude-config/main/agents/web-search-researcher.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "$HOME/.claude/hooks/gate-git-write.sh"
          }
        ]
      }
    ]
  }
}

Skills (6)

Subagents (16)

architect
model: opus
소프트웨어 아키텍트. 구조 설계, 바운디드 컨텍스트 분리, 레이어 매핑, ADR, API 스펙, DB 마이그레이션 계획, 트레이드오프 분석. 설계 결정이 필요한 시점에만 호출한다. 코드는 직접 쓰지 않는다. 키워드: 아키텍트, 설계, 구조 설계, DDD, 바운디드 컨텍스트, ADR, API 설계, 마이그레이션 계획, 도메인 모델. 코드 구현은 develop
codebase-analyzer
model: sonnet
Analyzes codebase implementation details. Call this agent when you need to understand HOW specific code works — trace data flow, explain logic, identify patterns. Give a detailed prompt describing wha
codebase-locator
model: sonnet
Locates files, directories, and components relevant to a feature or task. A "Super Grep/Glob" — use it when you need to find where code lives across the codebase. Give a human language prompt describi
codebase-pattern-finder
model: sonnet
Finds similar implementations, usage examples, or existing patterns that can be modeled after. Like codebase-locator but also gives you concrete code details. Use when you need to find "how is X done
designer디자이너. 화면 레이아웃·컬러·타이포·스페이싱·인터랙션, UX 마이크로카피(버튼·에러·빈 상태), 접근성 검토. CSS/HTML 을 직접 고친다. 키워드: 디자이너, UX, 레이아웃, 컴포넌트, 인터랙션, 접근성, 템플릿같지 않게, 시각 언어, 와이어, 버튼 카피, 빈 상태. 요구사항 정의는 planner, 비즈니스 로직·API 는 developer, 외부
developer
model: sonnet
개발자. 코드 구현·리팩토링·버그 수정·성능 개선, 단위·통합 테스트 작성(정상/실패/경계값), README·코드 문서화. 키워드: 개발자, 구현, 리팩토링, 버그 수정, 성능 개선, 엔티티, 리포지토리. 구조 설계·DDD·ADR·API 스펙·마이그레이션 계획은 architect, E2E·회귀·릴리스 게이트는 qa, 취약점 정밀 분석은 security, 배
docs-analyzer
model: sonnet
Extracts high-value insights from project documents (.handoffs/, .plans/, .research/). Use when you need to deeply analyze a past handoff, plan, or research doc — filters noise and returns only action
docs-locator
model: sonnet
Discovers relevant documents in .handoffs/, .plans/, .research/ directories. Use when you need to find past handoffs, plans, or research docs related to a current task. Like a "Super Grep" for project
infra인프라. 배포 파이프라인, 도메인·SSL, 모니터링·로그, 백업, 비용 추적. PaaS 와 VPS 양쪽 옵션을 트레이드오프와 함께 제시하고 결정은 사용자에게 맡긴다. 키워드: 인프라, 배포, CI/CD, nginx, systemd, 도메인, SSL, 모니터링, 로그, 비용, free tier, 백업, 장애, postmortem, runbook, health
lead팀장 역할. 직군 간 충돌 조정, 방향 결정/승인, 리뷰 종합, 우선순위 충돌 해소. '팀장이', '결정', '방향', '리뷰 종합', '승인', '직군 충돌' 같은 요청에 사용.
marketer마케터 역할. 타겟 페르소나, 메시지/카피, 채널 전략, 캠페인 기획, 가치 제안 정리. '마케터한테', '마케팅', '카피', '타겟', '캠페인', '메시지' 같은 요청에 사용.
planner기획자. 요구사항 명확화, 차별화 가설, MVP 분해·우선순위, 요구사항 반영도 검증, PRD-mini 작성. 키워드: 기획자, 스펙, 요구사항 정리, 유저 플로우, PRD, MVP, 우선순위, 차별화, 서비스 컨셉. 코드 구현은 developer, 일정·리스크 관리는 pm, UI 디자인은 designer, 최종 승인은 lead, 마케팅 카피는 market
pmPM. 작업 분해(스토리→태스크), 우선순위 조정, 진척 측정(git/gh 정량), 리스크·블로커 식별, 회고. 다른 agent 산출물의 의존성·정합성을 교차 검증한다. Agent 도구로 다른 subagent 를 직접 spawn 하는 오케스트레이터 모드를 갖는다. 키워드: PM, 일정, 진척, 작업 내역, 태스크 분해, 리스크, 블로커, 의존성, 회고, 스
qa
model: sonnet
QA/품질 엔지니어. 위험 기반 테스트 케이스 설계, 스모크·E2E·회귀 실행, 결함 리포트(재현 절차 필수), 릴리스 게이트 Go/No-Go 평가. 추측하지 않고 재현으로 말한다. 자가 보고를 신뢰하지 않는다. 키워드: QA, 테스터, 테스트 케이스, 회귀, regression, 스모크, E2E, 품질 게이트, 릴리스 점검, 결함, 버그 리포트, flak
security보안 엔지니어. OWASP Top 10 검토, 위협 모델(STRIDE), 인증·인가·세션·비밀 관리·CORS·CSP 검토, 의존성 CVE 스캔. 증거(파일:라인)와 재현 가능한 PoC 로만 보고한다. 키워드: 보안, OWASP, 취약점, CVE, XSS, SQL injection, CSRF, SSRF, IDOR, 인증, 인가, 세션, JWT, secret,
web-search-researcher
model: sonnet
Searches the web for modern, up-to-date information you're not confident about. Use when you need documentation, best practices, comparisons, or solutions that may only be discoverable online. Re-run

Hooks (1)

eventmatcherruns
PreToolUseBash$HOME/.claude/hooks/gate-git-write.sh

Plugins (1)

frontend-design@claude-plugins-official

Permissions

deny (0)
—
ask (0)
—
allow (7)
mcp__codegraph__codegraph_search
mcp__codegraph__codegraph_context
mcp__codegraph__codegraph_callers
mcp__codegraph__codegraph_callees
mcp__codegraph__codegraph_impact
mcp__codegraph__codegraph_node
mcp__codegraph__codegraph_status

Similar rigs

copied ✓