juanagu/claude-code-config
Personal Claude Code global config: CLAUDE.md, subagents, and custom skills
field: unknown workflow: Planning & specsFrontend & designPR / code reviewCI/CD & deployTesting & TDD
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 juanagu/claude-code-config/agents ./rig-claude-code-config/agents $ npx degit juanagu/claude-code-config/skills ./rig-claude-code-config/skills $ npx degit juanagu/claude-code-config/hooks ./rig-claude-code-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 juanagu/claude-code-config/skills/android-architecture .claude/skills/android-architecture $ npx degit juanagu/claude-code-config/skills/fastify-architecture .claude/skills/fastify-architecture $ npx degit juanagu/claude-code-config/skills/flutter-architecture .claude/skills/flutter-architecture $ npx degit juanagu/claude-code-config/skills/ios-architecture .claude/skills/ios-architecture $ npx degit juanagu/claude-code-config/skills/nextjs-architecture .claude/skills/nextjs-architecture $ npx degit juanagu/claude-code-config/skills/open-pr .claude/skills/open-pr $ npx degit juanagu/claude-code-config/skills/react-native-architecture .claude/skills/react-native-architecture $ npx degit juanagu/claude-code-config/skills/resolve-pr-comments .claude/skills/resolve-pr-comments $ npx degit juanagu/claude-code-config/skills/retro .claude/skills/retro
$ curl -fsSL --create-dirs -o .claude/agents/android-engineer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/android-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/architect-engineer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/architect-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/backend-engineer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/backend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/designer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/designer.md $ curl -fsSL --create-dirs -o .claude/agents/devops-engineer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/devops-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/frontend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/ios-engineer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/ios-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/product-strategist.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/product-strategist.md $ curl -fsSL --create-dirs -o .claude/agents/qa-engineer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/qa-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/react-native-engineer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/react-native-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/security-engineer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/security-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/technical-writer.md https://raw.githubusercontent.com/juanagu/claude-code-config/main/agents/technical-writer.md
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 *)"
]
}
} Skills (9)
android-architecturefastify-architectureflutter-architectureios-architecturenextjs-architectureopen-prreact-native-architectureresolve-pr-commentsretro
Subagents (12)
| android-engineer model: sonnet | Use for building or modifying native Android apps in Kotlin and Jetpack Compose: screens, ViewModels and UiState, navigation, repositories and data sources, Hilt wiring, Gradle modules and convention |
| architect-engineer model: opus | Use for system/module design decisions, defining boundaries between layers, evaluating architectural tradeoffs, and writing short ADRs before implementation starts. Invoke when a change spans 2+ layer |
| backend-engineer model: sonnet | Use for Node.js/Fastify implementation across BFFs, APIs/microservices, MongoDB repositories, schema validation, auth, and BullMQ/Redis background jobs. Proactively invoke for any backend implementati |
| designer model: opus | Use for real UI/UX design decisions — information architecture (which screen a feature belongs on), new components, layout/UX patterns not already established, design systems, design tokens, and acces |
| devops-engineer model: sonnet | Use for Docker/Compose authoring, Cloudflare configuration (DNS, WAF rules, cache rules, edge routing), CI/CD pipeline setup, and deployment configuration. Invoke for infrastructure-as-config changes |
| frontend-engineer model: sonnet | Use for building or modifying user-facing UI — Next.js/React web apps, Astro static/marketing sites, or Flutter mobile apps: components, pages, screens, client-side state, styling, forms, and wiring t |
| ios-engineer model: sonnet | Use for building or modifying native iOS apps in Swift and SwiftUI: views, @Observable view models and state, navigation, repositories and integrations, Swift packages and the dependency graph, Xcode |
| product-strategist model: opus | Use to turn a rough new-platform/product idea into a scoped plan — problem framing, target users, prioritized feature set, business model/positioning, and a phased roadmap. Invoke at the very start of |
| qa-engineer model: sonnet | Use for test strategy, writing/expanding unit, integration, and e2e tests, hunting edge cases and regressions, and verifying a change actually works before it's called done. Proactively invoke after f |
| react-native-engineer model: sonnet | Use for building or modifying React Native apps on Expo: screens and components, Expo Router routes and layouts, TanStack Query and Zustand state, forms, the feature lib/ ports, Expo Modules and confi |
| security-engineer model: opus | Use for security review of code changes, threat modeling, and secure-coding guidance across the stack (Next.js, Astro, Fastify BFFs/microservices, BullMQ/Redis, MongoDB, Flutter, native Android and iO |
| technical-writer model: sonnet | Use for README files, API documentation, architecture docs, ADRs, changelogs, migration guides, and other developer-facing documentation. Invoke when a change needs documenting or existing docs need t |
Similar rigs
erayendes/kortext
The project brain for AI-driven development: a brief becomes approved analysis documents, then your own agent CLI (Claude, Codex etc.) writes the code. Local-first, no API key of its own.
Orchestrator 1.2k tok · · Q5
bsrikumar855-dot/ClaudeCODE-Autonomous-skills
An autonomous AI development skill for Claude Code. Turn project goals into planned, implemented, tested, and reviewed software using specialist AI subagents.
Orchestrator 789 tok · · Q0
ishaankarnik11/phishforge-agentic
AI studio that turns a scenario brief into email-safe phishing-simulation templates, with GPT Image 2 image generation, mask editing and an asset library. For authorized security-awareness audits. Built with an agentic workflow: scoped Clau
Orchestrator 2.1k tok · · Q0
SaketMunda/claude-org-template
Drop this into any project and start engineering at AI speed. No setup ceremony. No re-explaining context every session.
Orchestrator 1.4k tok · · Q33