huangjia2019/claude-code-engineering
This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库，目标很明确： 👉 把 Claude Code 从“对话式编码工具”，变成 可设计、可复用、可治理的工程系统。
ARCHETYPE
MCP Hoarder
Six or more MCP servers wired in. Every tool, always in context.
Copy this rig
# review before running: this installs third-party code $ claude mcp add context7 -- npx -y @upstash/context7-mcp@latest $ claude mcp add filesystem -- npx @modelcontextprotocol/server-filesystem . $ claude mcp add fetch -- uvx mcp-server-fetch $ claude mcp add memory -- npx @modelcontextprotocol/server-memory $ claude mcp add postgres -e DATABASE_URL=YOUR_DATABASE_URL -- npx -y @anthropic/mcp-server-postgres $ claude mcp add github -e GITHUB_<redacted> -- npx -y @anthropic/mcp-server-github $ npx degit huangjia2019/claude-code-engineering/.claude ./rig-claude-code-engineering # 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.
$ claude mcp add context7 -- npx -y @upstash/context7-mcp@latest $ claude mcp add filesystem -- npx @modelcontextprotocol/server-filesystem . $ claude mcp add fetch -- uvx mcp-server-fetch $ claude mcp add memory -- npx @modelcontextprotocol/server-memory $ claude mcp add postgres -e DATABASE_URL=YOUR_DATABASE_URL -- npx -y @anthropic/mcp-server-postgres $ claude mcp add github -e GITHUB_<redacted> -- npx -y @anthropic/mcp-server-github
$ npx degit huangjia2019/claude-code-engineering/04-Skills/projects/00-basic-skill/.claude/skills/code-reviewing .claude/skills/code-reviewing $ npx degit huangjia2019/claude-code-engineering/04-Skills/projects/01-reference-skill/.claude/skills/api-conventions .claude/skills/api-conventions $ npx degit huangjia2019/claude-code-engineering/04-Skills/projects/02-progressive-skill/.claude/skills/api-documenting .claude/skills/api-documenting $ npx degit huangjia2019/claude-code-engineering/04-Skills/projects/03-financial-skill/.claude/skills/financial-analyzing .claude/skills/financial-analyzing $ npx degit huangjia2019/claude-code-engineering/04-Skills/projects/04-codebase-visualizer/.claude/skills/codebase-visualizer .claude/skills/codebase-visualizer $ npx degit huangjia2019/claude-code-engineering/04-Skills/projects/05-api-generator/.claude/skills/api-generating .claude/skills/api-generating $ npx degit huangjia2019/claude-code-engineering/04-Skills/projects/07-skill-fork-demo/.claude/skills/code-health-check .claude/skills/code-health-check $ npx degit huangjia2019/claude-code-engineering/04-Skills/projects/08-skill-pipeline/.claude/skills/doc-writing .claude/skills/doc-writing $ npx degit huangjia2019/claude-code-engineering/04-Skills/projects/08-skill-pipeline/.claude/skills/quality-checking .claude/skills/quality-checking $ npx degit huangjia2019/claude-code-engineering/04-Skills/projects/08-skill-pipeline/.claude/skills/route-scanning .claude/skills/route-scanning $ npx degit huangjia2019/claude-code-engineering/10-Plugins/projects/03-team-toolkit/skills/react-patterns .claude/skills/react-patterns
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/03-SubAgents/projects/01-code-reviewer/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-runner.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/03-SubAgents/projects/02-test-runner/.claude/agents/test-runner.md $ curl -fsSL --create-dirs -o .claude/agents/log-analyzer.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/03-SubAgents/projects/03-log-analyzer/.claude/agents/log-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/api-explorer.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/03-SubAgents/projects/04-parallel-explore/.claude/agents/api-explorer.md $ curl -fsSL --create-dirs -o .claude/agents/auth-explorer.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/03-SubAgents/projects/04-parallel-explore/.claude/agents/auth-explorer.md $ curl -fsSL --create-dirs -o .claude/agents/db-explorer.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/03-SubAgents/projects/04-parallel-explore/.claude/agents/db-explorer.md $ curl -fsSL --create-dirs -o .claude/agents/bug-analyzer.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/03-SubAgents/projects/05-bugfix-pipeline/.claude/agents/bug-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/bug-fixer.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/03-SubAgents/projects/05-bugfix-pipeline/.claude/agents/bug-fixer.md $ curl -fsSL --create-dirs -o .claude/agents/bug-locator.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/03-SubAgents/projects/05-bugfix-pipeline/.claude/agents/bug-locator.md $ curl -fsSL --create-dirs -o .claude/agents/bug-verifier.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/03-SubAgents/projects/05-bugfix-pipeline/.claude/agents/bug-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/api-doc-generator.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/04-Skills/projects/06-agent-skill-combo/.claude/agents/api-doc-generator.md $ curl -fsSL --create-dirs -o .claude/agents/doc-writer.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/04-Skills/projects/08-skill-pipeline/.claude/agents/doc-writer.md $ curl -fsSL --create-dirs -o .claude/agents/quality-checker.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/04-Skills/projects/08-skill-pipeline/.claude/agents/quality-checker.md $ curl -fsSL --create-dirs -o .claude/agents/route-scanner.md https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/main/04-Skills/projects/08-skill-pipeline/.claude/agents/route-scanner.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 *)"
]
}
} MCP servers (6)
| server | source | est. tokens |
|---|---|---|
| Context7 | npm | 1.2k |
| Filesystem | npm | 4.2k |
| Fetch | pypi | 450 |
| Memory (knowledge graph) · "memory" | npm | 2.6k |
| Postgres env: DATABASE_URL | npm | 600 |
| @anthropic/mcp-server-github · "github" env: GITHUB_TOKEN | npm | 2.5k |
Skills (11)
code-reviewingapi-conventionsapi-documentingfinancial-analyzingcodebase-visualizerapi-generatingcode-health-checkdoc-writingquality-checkingroute-scanningReact 最佳实践
Subagents (14)
| code-reviewer model: sonnet | Review code changes for quality, security, and best practices. Proactively use this after code modifications. |
| test-runner model: haiku | Run tests and report results concisely. Use this after code changes to verify everything works. |
| log-analyzer model: sonnet | Analyze log files and extract actionable insights. Use when troubleshooting issues or investigating incidents. |
| api-explorer model: haiku | Explore and analyze API-related code. Use when investigating endpoints, routing, or HTTP handling. |
| auth-explorer model: haiku | Explore and analyze authentication-related code. Use when investigating auth flows, session management, or security. |
| db-explorer model: haiku | Explore and analyze database-related code. Use when investigating data models, queries, or persistence. |
| bug-analyzer model: sonnet | Analyze root cause of bugs after location is identified. Second step in bug investigation. |
| bug-fixer model: sonnet | Implement bug fixes after analysis is complete. Third step in bug fix pipeline. |
| bug-locator model: sonnet | Locate the source of bugs in the codebase. First step in bug investigation. |
| bug-verifier model: haiku | Verify bug fixes by running tests. Final step in bug fix pipeline. |
| api-doc-generator model: sonnet | Generate comprehensive API documentation by scanning Express route files. |
| doc-writer model: sonnet | Pipeline Stage 2 - Generate API documentation from a route manifest. |
| quality-checker model: haiku | Pipeline Stage 3 - Validate generated API documentation against quality standards. |
| route-scanner model: haiku | Pipeline Stage 1 - Scan Express routes and produce a route manifest. |
Slash commands (9)
/commit/explain/git/log/git/status/review/todo/analyze/pr-create/safe-deploy
Permissions
deny (0)
—
ask (0)
—
allow (1)
Bash(xxd:*)
Similar rigs
affaan-m/agentshield
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
MCP Hoarder 60.2k tok ·
Cordycepsers/vscode-claude-setup-2025
Complete configuration for Python, Node.js, React, and TypeScript development with VS Code, Claude Desktop, and Claude Code
MCP Hoarder 53.0k tok ·
codeverbojan/claude-code-kickstart
Production-grade agentic workflow template for Claude Code. 4-layer architecture, task playbooks, session memory, sub-agents, one-click install.
Orchestrator 10.2k tok ·
nandhasuhendra/dotfiles
My configuration files that I use on several applications and Linux desktops.
MCP Hoarder 19.1k tok ·