ultivis-iot/claude-code-setup
No description.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit ultivis-iot/claude-code-setup/agents ./rig-claude-code-setup/agents $ npx degit ultivis-iot/claude-code-setup/commands ./rig-claude-code-setup/commands $ npx degit ultivis-iot/claude-code-setup/hooks ./rig-claude-code-setup/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 ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/codebase-design .claude/skills/codebase-design $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/diagnosing-bugs .claude/skills/diagnosing-bugs $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/domain-modeling .claude/skills/domain-modeling $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/grill-me .claude/skills/grill-me $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/grilling .claude/skills/grilling $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/handoff .claude/skills/handoff $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/improve-codebase-architecture .claude/skills/improve-codebase-architecture $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/research .claude/skills/research $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/resolving-merge-conflicts .claude/skills/resolving-merge-conflicts $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/tdd .claude/skills/tdd $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/teach .claude/skills/teach $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/ultivis-flow .claude/skills/ultivis-flow $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/ux-review .claude/skills/ux-review $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/wayfinder .claude/skills/wayfinder $ npx degit ultivis-iot/claude-code-setup/codex/plugins/dev-workflow/skills/writing-great-skills .claude/skills/writing-great-skills
$ curl -fsSL --create-dirs -o .claude/agents/cli-validator.md https://raw.githubusercontent.com/ultivis-iot/claude-code-setup/master/agents/cli-validator.md $ curl -fsSL --create-dirs -o .claude/agents/code-simplifier.md https://raw.githubusercontent.com/ultivis-iot/claude-code-setup/master/agents/code-simplifier.md $ curl -fsSL --create-dirs -o .claude/agents/doc-validator.md https://raw.githubusercontent.com/ultivis-iot/claude-code-setup/master/agents/doc-validator.md $ curl -fsSL --create-dirs -o .claude/agents/intent-validator.md https://raw.githubusercontent.com/ultivis-iot/claude-code-setup/master/agents/intent-validator.md $ curl -fsSL --create-dirs -o .claude/agents/security-validator.md https://raw.githubusercontent.com/ultivis-iot/claude-code-setup/master/agents/security-validator.md $ curl -fsSL --create-dirs -o .claude/agents/test-validator.md https://raw.githubusercontent.com/ultivis-iot/claude-code-setup/master/agents/test-validator.md $ curl -fsSL --create-dirs -o .claude/agents/visual-qa-analyzer.md https://raw.githubusercontent.com/ultivis-iot/claude-code-setup/master/agents/visual-qa-analyzer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (15)
codebase-designdiagnosing-bugsdomain-modelinggrill-megrillinghandoffimprove-codebase-architectureresearchresolving-merge-conflictstddteachultivis-flowux-reviewwayfinderwriting-great-skills
Subagents (7)
| cli-validator model: sonnet | CLI 커맨드 동기화 및 help 품질 검증. 검증 2단계에서 병렬 실행. |
| code-simplifier model: sonnet | Standards Review. 저장소 규칙과 코드 스멜 기준으로 변경사항을 검증. 검증 2단계에서 병렬 실행. |
| doc-validator model: haiku | 문서-코드 일치 검증. 검증 2단계에서 병렬 실행. |
| intent-validator model: sonnet | Spec Review. 승인된 Plan/Task/Issue의 의도대로 구현되었는지 검증. 코드 변경 후 자동 사용. |
| security-validator model: haiku | 검증 대상 diff와 기존 보안 검사 결과를 근거로 보안 문제를 검토 |
| test-validator model: haiku | 변경된 동작을 공개 인터페이스의 테스트와 실제 실행 결과로 검증 |
| visual-qa-analyzer model: sonnet | 수집된 라우트 데이터(DOM 요약/콘솔/네트워크/스크린샷)로 라우트별 회귀를 판정. 디자인 품질 평가는 하지 않는다 |
Slash commands (16)
/commit-and-verify/create-pr/issue/review-cycle/ult-finish-task/ult-my-tasks/ult-start-task/ult-story-create/ult-story-run/ult-sync-task/ult-task-create/ult-task-link-issue/ult-task-note/ult-task-status/ult-weekly-report/visual-qa
Similar rigs
michaelmjhhhh/pi-atelier
An elegant, information-rich status, menu, and side bar for Pi Agent.
Skill Collector 1.6k tok ·
crafts69guy/.dotfiles
This repo leverages GNU Stow to simplify symlink management, making it easy to install and update configurations across different machines.
Skill Collector 5.3k tok ·
rio/dotfiles
—
Skill Collector 1.3k tok ·
stevesolun/ctx
CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.
Skill Collector 3.4k tok ·