jiaheyi-maggie/claude-code-config
Personal Claude Code configuration — commands, hooks, settings, and global instructions
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 jiaheyi-maggie/claude-code-config/agents ./rig-claude-code-config/agents $ npx degit jiaheyi-maggie/claude-code-config/commands ./rig-claude-code-config/commands $ npx degit jiaheyi-maggie/claude-code-config/skills ./rig-claude-code-config/skills $ npx degit jiaheyi-maggie/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 jiaheyi-maggie/claude-code-config/skills/route .claude/skills/route $ curl -fsSL --create-dirs -o .claude/agents/ai-engineer.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/ai-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/brand-strategist.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/brand-strategist.md $ curl -fsSL --create-dirs -o .claude/agents/chief-architect.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/chief-architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/frontend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/ai-engineering-kb-2026.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/knowledge/ai-engineering-kb-2026.md $ curl -fsSL --create-dirs -o .claude/agents/engineering-kb.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/knowledge/engineering-kb.md $ curl -fsSL --create-dirs -o .claude/agents/pitch-deck.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/pitch-deck.md $ curl -fsSL --create-dirs -o .claude/agents/product-manager.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/product-manager.md $ curl -fsSL --create-dirs -o .claude/agents/qa-engineer.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/qa-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/senior-engineer.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/senior-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/systems-debugger.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/systems-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/tech-writer.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/tech-writer.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/test-writer.md $ curl -fsSL --create-dirs -o .claude/agents/ui-mockup.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/ui-mockup.md $ curl -fsSL --create-dirs -o .claude/agents/ux-engineer.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/ux-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/visionary.md https://raw.githubusercontent.com/jiaheyi-maggie/claude-code-config/main/agents/visionary.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 (1)
Subagents (18)
| ai-engineer model: opus | Staff AI engineer and AI industry analyst. Deep expertise in AI development patterns, model capabilities, agent architectures, MCP, RAG, evals, AI UX, and the competitive landscape. Spawn to ask quest |
| brand-strategist model: opus | Brand and marketing strategist who deeply understands the product from the codebase, then writes compelling investor-facing and market-facing materials — pitch decks, one-pagers, product descriptions, |
| chief-architect | Master orchestrator for complex, multi-faceted software projects. Coordinates specialist agents (researchers, planners, implementers) to deliver cohesive solutions. Use for projects requiring 3+ capab |
| code-reviewer model: opus | Senior software engineer code reviewer. Automatically spawned after completing a big feature to run a 4-pass review (bugs, logic, engineering quality, product alignment). Use this agent proactively wh |
| debugger model: opus | Systematic deep debugger that reads the full project context, builds a mental model of the architecture, then traces the exact logic chain for a described issue. Never guesses — reads the actual code |
| frontend-engineer model: opus | Staff frontend engineer specializing in React/Next.js, component architecture, responsive design, performance, and modern CSS. Spawn for UI implementation, component design, state management decisions |
| ai-engineering-kb-2026 | — |
| engineering-kb | — |
| pitch-deck model: opus | Pitch deck builder that deeply understands the product from the codebase, identifies its strengths and moat, and generates polished interactive HTML pitch decks with information hierarchy that present |
| product-manager model: opus | Senior product manager who owns the "what" and "why." Spawn during ideation, requirements definition, feature prioritization, or when you need to challenge whether something should be built at all. Us |
| qa-engineer model: opus | Post-implementation QA agent. Verifies features against requirements, finds and fixes bugs, incorporates user tweaks, and iterates until the implementation is solid. Spawn after any implementation tha |
| senior-engineer model: opus | Principal software engineer with deep systems knowledge. Spawn for architecture decisions, complex implementations, technology selection, performance optimization, and system design. Always implements |
| systems-debugger | Low-level systems debugging specialist for C, memory issues, crashes, and performance problems. |
| tech-writer model: sonnet | Technical writer who produces API documentation, Architecture Decision Records (ADRs), changelogs, onboarding guides, and READMEs. Spawn when documentation needs to be created or updated alongside cod |
| test-writer | Test generation specialist. Writes comprehensive tests for existing code. |
| ui-mockup model: opus | UI mockup designer that reviews the codebase, identifies unbuilt pages and features, and generates detailed interactive HTML mockups. Iterates with the user until the design is right, then produces im |
| ux-engineer model: opus | UX/UI design engineer who thinks in user flows, interaction patterns, and visual systems. Spawn for UI/UX design decisions, wireframing, design system creation, user flow mapping, and interface critiq |
| visionary model: opus | Visionary product-engineering thinker with deep frontier tech knowledge. Works in two modes — (1) brainstorm within an existing product/repo, or (2) brainstorm from scratch with any raw idea, no repo |
Slash commands (23)
/architect/bugfix/build-features/catch-up/checkpoint/create-prd/eval/evolve/explore-feature/generate-prompt/handover/ideate/launch-multiagent-team/pre-ship/prime/recon/review-feature/search-first/security-audit/ship/summarize/tbc/tdd
Similar rigs
Yassinekrn/claude-setup
Personal Claude Code setup — orchestrator/subagent delegation policy, custom agents, and a colored PowerShell statusline (git branch, model+effort, tokens, cost, rate limits).
Orchestrator 1.2k tok ·
UtsavBalar1231/claude-code-configs
—
Pragmatist 5.0k tok ·
IvanKuzyshyn/dotfiles
Dotfiles optimized for speed, coffee, and questionable life choices. 😜
Pragmatist 3.0k tok ·
Mathiew82/minimal-claudeness
A minimal, dependency-free meta-harness for Claude Code.
Pragmatist 2.7k tok ·