ain0633/ainsof-office
Claude Code 멀티에이전트: 역할별 AI 봇 여섯 + 코드로 된 승인 게이트 + 픽셀 사무실 페이지
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~15.2k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Context hog · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add pw-read -- cmd /c npx -y @playwright/mcp@0.0.83 --isolated --headless --block-service-workers --no-webmcp $ claude mcp add pw-local -- cmd /c npx -y @playwright/mcp@0.0.83 --isolated --headless --allowed-origins 'http://localhost:5173;http://127.0.0.1:5173;http://localhost:4173;http://127.0.0.1:4173;http://localhost:8080;http://127.0.0.1:8080'
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.
$ claude mcp add pw-read -- cmd /c npx -y @playwright/mcp@0.0.83 --isolated --headless --block-service-workers --no-webmcp $ claude mcp add pw-local -- cmd /c npx -y @playwright/mcp@0.0.83 --isolated --headless --allowed-origins 'http://localhost:5173;http://127.0.0.1:5173;http://localhost:4173;http://127.0.0.1:4173;http://localhost:8080;http://127.0.0.1:8080'
$ npx degit ain0633/ainsof-office/plugin/skills/design-brief .claude/skills/design-brief $ npx degit ain0633/ainsof-office/plugin/skills/design-output .claude/skills/design-output $ npx degit ain0633/ainsof-office/plugin/skills/research-claims .claude/skills/research-claims $ npx degit ain0633/ainsof-office/plugin/skills/retro .claude/skills/retro $ npx degit ain0633/ainsof-office/plugin/skills/review-findings .claude/skills/review-findings $ npx degit ain0633/ainsof-office/plugin/skills/task-card .claude/skills/task-card
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (2)
| server | source | est. tokens |
|---|---|---|
| Playwright MCP · "pw-read" | npm | 7.5k |
| Playwright MCP · "pw-local" | npm | 7.5k |
Skills (6)
Similar rigs
777genius/agent-teams-ai
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/GitHub/Kiro/Z.AI/Xiaomi
Pragmatist 12.5k tok · · Q3
kaorii-ako/Shiori-v1
Open-source AI study companion — Google Classroom sync, Gemini AI plans, SRS flashcards, GPA predictor, AI quiz, MCP server for Claude Code. Try demo at shiori-v1.vercel.app
Pragmatist 8.8k tok · · Q15
atxtechbro/dotfiles
AI-orchestration dotfiles for developers who want leverage. Parallelize agents, enforce principles, and self-heal your stack for 100x throughput. Built to version the AI era.
YOLO Cowboy 7.5k tok · · Q0
netresearch/retro-skill
LLM-driven session retrospection skill: detects friction in agent sessions and materializes learnings into correct destinations (user-memory, project-rules, skill PRs, checkpoints, harness artefacts)
Minimalist 1.5k tok · · Q0