zhsama/claude-sub-agent
AI-driven development workflow system built on Claude Code Sub-Agents.
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 zhsama/claude-sub-agent/agents ./rig-claude-sub-agent/agents $ npx degit zhsama/claude-sub-agent/commands ./rig-claude-sub-agent/commands
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.
$ curl -fsSL --create-dirs -o .claude/agents/senior-backend-architect.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/backend/senior-backend-architect.md $ curl -fsSL --create-dirs -o .claude/agents/senior-frontend-architect.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/frontend/senior-frontend-architect.md $ curl -fsSL --create-dirs -o .claude/agents/spec-analyst.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/spec-agents/spec-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/spec-architect.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/spec-agents/spec-architect.md $ curl -fsSL --create-dirs -o .claude/agents/spec-developer.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/spec-agents/spec-developer.md $ curl -fsSL --create-dirs -o .claude/agents/spec-orchestrator.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/spec-agents/spec-orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/spec-planner.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/spec-agents/spec-planner.md $ curl -fsSL --create-dirs -o .claude/agents/spec-reviewer.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/spec-agents/spec-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/spec-tester.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/spec-agents/spec-tester.md $ curl -fsSL --create-dirs -o .claude/agents/spec-validator.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/spec-agents/spec-validator.md $ curl -fsSL --create-dirs -o .claude/agents/ui-ux-master.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/ui-ux/ui-ux-master.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-agent.md https://raw.githubusercontent.com/zhsama/claude-sub-agent/main/agents/utility/refactor-agent.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 *)"
]
}
} Subagents (12)
| senior-backend-architect | Senior backend engineer and system architect with 10+ years at Google, leading multiple products with 10M+ users. Expert in Go and TypeScript, specializing in distributed systems, high-performance API |
| senior-frontend-architect | Senior frontend engineer and architect with 10+ years at Meta, leading multiple products with 10M+ users. Expert in TypeScript, React, Next.js, Vue, and Astro ecosystems. Specializes in performance op |
| spec-analyst | Requirements analyst and project scoping expert. Specializes in eliciting comprehensive requirements, creating user stories with acceptance criteria, and generating project briefs. Works with stakehol |
| spec-architect | System architect specializing in technical design and architecture. Creates comprehensive system designs, technology stack recommendations, API specifications, and data models. Ensures scalability, se |
| spec-developer | Expert developer that implements features based on specifications. Writes clean, maintainable code following architectural patterns and best practices. Creates unit tests, handles error cases, and ens |
| spec-orchestrator | Workflow coordination specialist focused on project organization, quality gate management, and progress tracking. Provides strategic planning and coordination capabilities without direct agent managem |
| spec-planner | Implementation planning specialist that breaks down architectural designs into actionable tasks. Creates detailed task lists, estimates complexity, defines implementation order, and plans comprehensiv |
| spec-reviewer | Senior code reviewer specializing in code quality, best practices, and security. Reviews code for maintainability, performance optimizations, and potential vulnerabilities. Provides actionable feedbac |
| spec-tester | Comprehensive testing specialist that creates and executes test suites. Writes unit tests, integration tests, and E2E tests. Performs security testing, performance testing, and ensures code coverage m |
| spec-validator | Final quality validation specialist that ensures requirements compliance and production readiness. Verifies all requirements are met, architecture is properly implemented, tests pass, and quality stan |
| ui-ux-master | Expert UI/UX design agent with 10+ years of experience creating award-winning user experiences. Specializes in AI-collaborative design workflows that produce implementation-ready specifications, enabl |
| code-refactorer-agent | Use this agent when you need to improve existing code structure, readability, or maintainability without changing functionality. This includes cleaning up messy code, reducing duplication, improving n |
Slash commands (1)
/agent-workflow
Similar rigs
mim1963/mim-CC-dev-bootstrap
Claude Code multi-agent dev environment pieces
Orchestrator 5.8k tok ·
Prorise-cool/Claude-Code-Multi-Agent
Claude-Code-Multi-Agent驱动的新一代AI编程助手生态系统,基于Claude Code构建的智能代理协调工作空间,实现从需求到交付的全流程自动化开发
MCP Hoarder 66.5k tok ·
RemiAsselin42/claude-config
Memory, features, skills, and agents for Claude, centralized and versioned, one-command installation
Automator 2.1k tok ·
DiegoOya/expense_tracker
Expense tracker MCP server built spec-first with Claude Code: hooks, skills, subagents and an honest log of what went wrong.
Fort Knox 21.5k tok ·