pagoda111king/claude-code-pack
Claude Code config pack · 11 agents · 10 skills · 10 commands · 4 hooks · CLAUDE.md template · Solo Founder OS
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 pagoda111king/claude-code-pack/template/.claude ./rig-claude-code-pack # inspect, then merge into .claude/ 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 pagoda111king/claude-code-pack/template/.claude/skills/case-study-gen .claude/skills/case-study-gen $ npx degit pagoda111king/claude-code-pack/template/.claude/skills/content-blitz .claude/skills/content-blitz $ npx degit pagoda111king/claude-code-pack/template/.claude/skills/eval-refine .claude/skills/eval-refine $ npx degit pagoda111king/claude-code-pack/template/.claude/skills/idea-eval .claude/skills/idea-eval $ npx degit pagoda111king/claude-code-pack/template/.claude/skills/lead-intake .claude/skills/lead-intake $ npx degit pagoda111king/claude-code-pack/template/.claude/skills/prior-art-search .claude/skills/prior-art-search $ npx degit pagoda111king/claude-code-pack/template/.claude/skills/proposal-gen .claude/skills/proposal-gen $ npx degit pagoda111king/claude-code-pack/template/.claude/skills/release-window .claude/skills/release-window $ npx degit pagoda111king/claude-code-pack/template/.claude/skills/ship-checklist .claude/skills/ship-checklist $ npx degit pagoda111king/claude-code-pack/template/.claude/skills/soft-launch .claude/skills/soft-launch
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/backend-expert.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/backend-expert.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/customer-support.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/customer-support.md $ curl -fsSL --create-dirs -o .claude/agents/doc-writer.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/doc-writer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-expert.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/frontend-expert.md $ curl -fsSL --create-dirs -o .claude/agents/marketing.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/marketing.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-engineer.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/test-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/validator.md https://raw.githubusercontent.com/pagoda111king/claude-code-pack/main/template/.claude/agents/validator.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 (10)
case-study-gencontent-blitzeval-refineidea-evallead-intakeprior-art-searchproposal-genrelease-windowship-checklistsoft-launch
Subagents (11)
| architect model: sonnet | System architecture design. Used when the founder asks "how should this system be designed", "what tech stack should I use", or "how should the API be split". Does not write code—only produces archite |
| backend-expert model: sonnet | Backend Full-Cycle Expert (v1.1 · 2026-04-25 upgrade). **Full-cycle participation**: before (API / data design consultation) + during (transaction / error / log pair review) + after (QA review). Focus |
| code-reviewer model: sonnet | Code review. Run before commit, before merge, before deploy. Checks security, quality, performance, maintainability. Outputs a severity-ranked checklist. Report in Chinese. |
| customer-support model: sonnet | Handle customer inquiries, after-sales issues, and feedback collection. Use when receiving customer emails, WeChat messages, or ticket content. Classify messages, generate draft replies, update conver |
| doc-writer model: haiku | Documentation writing specialist. Used when delivering to clients / open source / shipping products — writing README / API docs / user guides / delivery docs. Haiku-driven, repetitive scripted tasks, |
| frontend-expert model: sonnet | Full-cycle frontend expert (v2.1 · iterated from Test 1). Before-build architecture consulting + mid-build pair review + after-build QA. Covers UX / a11y / responsive / performance / e-commerce page r |
| marketing model: sonnet | Content production, SEO, client proposals, brand content, case study reuse. Use for writing newsletter/social/X copy, SEO keyword research, drafting proposals to prospects, turning delivered projects |
| planner model: opus | From idea to implementation plan. Use when a founder says "I want to build X", "help me plan this feature", or "how should I approach this refactor". Outputs an executable, phased, verifiable implemen |
| security-reviewer model: sonnet | Security review. Use before release / after integrating external systems / when user data is involved / when payments are involved. Scans OWASP Top 10 + secret leaks + data compliance. Outputs a prior |
| test-engineer model: sonnet | Test engineering specialist. Use before writing new features / fixing bugs / refactoring. Decides "what to test and what not to test" · writes tests · runs coverage. Solo Founder edition doesn't chase |
| validator model: opus | A strict tech-lead / product-lead reviewer. Used after the founder completes pipeline phase 4 (eval/requirements/arch/plan) and before writing the first line of code. Purpose is to pour cold water: is |
Slash commands (10)
/cost/eval/learn-review/learn/loop/orchestrate/plan/resume-session/save-session/skill-create
Similar rigs
Yuutokata/claude-code-setup
🔄 One Claude Code setup for my desktop and MacBook, synced through git, with guardrails that keep secrets out.
Fort Knox 1.1k tok ·
cfrs2005/claude-init
Claude Code 中文开发套件 - 为中国开发者定制的零门槛 AI 编程环境。一键安装完整中文化体验，集成 MCP 服务器、智能上下文管理、安全扫描，支持免翻墙访问。让 AI 编程更简单。
Orchestrator 1.5k tok ·
mh2-lee/everything-claude-code
Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
Orchestrator 1.2k tok ·
hirokami3/everything-claude-code
Claude Code configs collection - agents, skills, hooks, commands, rules, and MCP configurations
Orchestrator 1.2k tok ·