LangHY/claude-code-config-LANG
Claude Code 配置模板：10 个子代理、5 个命令、6 个插件、41 个技能、MCP 服务器、输出风格、Rules（已脱敏）
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add stitch -- npx @_davideast/stitch-mcp proxy $ npx degit LangHY/claude-code-config-LANG/agents ./rig-claude-code-config-lang/agents $ npx degit LangHY/claude-code-config-LANG/commands ./rig-claude-code-config-lang/commands $ npx degit LangHY/claude-code-config-LANG/skills ./rig-claude-code-config-lang/skills
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 stitch -- npx @_davideast/stitch-mcp proxy $ npx degit LangHY/claude-code-config-LANG/skills/clean-code-mentor .claude/skills/clean-code-mentor $ npx degit LangHY/claude-code-config-LANG/skills/docx .claude/skills/docx $ npx degit LangHY/claude-code-config-LANG/skills/excalidraw-diagram-generator .claude/skills/excalidraw-diagram-generator $ npx degit LangHY/claude-code-config-LANG/skills/frontend-design .claude/skills/frontend-design $ npx degit LangHY/claude-code-config-LANG/skills/git-commit .claude/skills/git-commit $ npx degit LangHY/claude-code-config-LANG/skills/humanizer .claude/skills/humanizer $ npx degit LangHY/claude-code-config-LANG/skills/ima-skill .claude/skills/ima-skill $ npx degit LangHY/claude-code-config-LANG/skills/lark-approval .claude/skills/lark-approval $ npx degit LangHY/claude-code-config-LANG/skills/lark-attendance .claude/skills/lark-attendance $ npx degit LangHY/claude-code-config-LANG/skills/lark-base .claude/skills/lark-base $ npx degit LangHY/claude-code-config-LANG/skills/lark-calendar .claude/skills/lark-calendar $ npx degit LangHY/claude-code-config-LANG/skills/lark-contact .claude/skills/lark-contact $ npx degit LangHY/claude-code-config-LANG/skills/lark-doc .claude/skills/lark-doc $ npx degit LangHY/claude-code-config-LANG/skills/lark-drive .claude/skills/lark-drive $ npx degit LangHY/claude-code-config-LANG/skills/lark-event .claude/skills/lark-event $ npx degit LangHY/claude-code-config-LANG/skills/lark-im .claude/skills/lark-im $ npx degit LangHY/claude-code-config-LANG/skills/lark-mail .claude/skills/lark-mail $ npx degit LangHY/claude-code-config-LANG/skills/lark-markdown .claude/skills/lark-markdown $ npx degit LangHY/claude-code-config-LANG/skills/lark-minutes .claude/skills/lark-minutes $ npx degit LangHY/claude-code-config-LANG/skills/lark-okr .claude/skills/lark-okr $ npx degit LangHY/claude-code-config-LANG/skills/lark-openapi-explorer .claude/skills/lark-openapi-explorer $ npx degit LangHY/claude-code-config-LANG/skills/lark-shared .claude/skills/lark-shared $ npx degit LangHY/claude-code-config-LANG/skills/lark-sheets .claude/skills/lark-sheets $ npx degit LangHY/claude-code-config-LANG/skills/lark-skill-maker .claude/skills/lark-skill-maker $ npx degit LangHY/claude-code-config-LANG/skills/lark-slides .claude/skills/lark-slides $ npx degit LangHY/claude-code-config-LANG/skills/lark-task .claude/skills/lark-task $ npx degit LangHY/claude-code-config-LANG/skills/lark-vc .claude/skills/lark-vc $ npx degit LangHY/claude-code-config-LANG/skills/lark-whiteboard .claude/skills/lark-whiteboard $ npx degit LangHY/claude-code-config-LANG/skills/lark-wiki .claude/skills/lark-wiki $ npx degit LangHY/claude-code-config-LANG/skills/lark-workflow-meeting-summary .claude/skills/lark-workflow-meeting-summary $ npx degit LangHY/claude-code-config-LANG/skills/lark-workflow-standup-report .claude/skills/lark-workflow-standup-report $ npx degit LangHY/claude-code-config-LANG/skills/modern-ui-builder .claude/skills/modern-ui-builder $ npx degit LangHY/claude-code-config-LANG/skills/pdf .claude/skills/pdf $ npx degit LangHY/claude-code-config-LANG/skills/pptx .claude/skills/pptx $ npx degit LangHY/claude-code-config-LANG/skills/prd .claude/skills/prd $ npx degit LangHY/claude-code-config-LANG/skills/refactor .claude/skills/refactor $ npx degit LangHY/claude-code-config-LANG/skills/skill-creator .claude/skills/skill-creator $ npx degit LangHY/claude-code-config-LANG/skills/web-access .claude/skills/web-access $ npx degit LangHY/claude-code-config-LANG/skills/xlsx .claude/skills/xlsx
$ curl -fsSL --create-dirs -o .claude/agents/bug-analyzer.md https://raw.githubusercontent.com/LangHY/claude-code-config-LANG/main/agents/bug-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/code-explore.md https://raw.githubusercontent.com/LangHY/claude-code-config-LANG/main/agents/code-explore.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/LangHY/claude-code-config-LANG/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/dev-planner.md https://raw.githubusercontent.com/LangHY/claude-code-config-LANG/main/agents/dev-planner.md $ curl -fsSL --create-dirs -o .claude/agents/general-purpose.md https://raw.githubusercontent.com/LangHY/claude-code-config-LANG/main/agents/general-purpose.md $ curl -fsSL --create-dirs -o .claude/agents/impl-plan.md https://raw.githubusercontent.com/LangHY/claude-code-config-LANG/main/agents/impl-plan.md $ curl -fsSL --create-dirs -o .claude/agents/story-generator.md https://raw.githubusercontent.com/LangHY/claude-code-config-LANG/main/agents/story-generator.md $ curl -fsSL --create-dirs -o .claude/agents/tech-lead.md https://raw.githubusercontent.com/LangHY/claude-code-config-LANG/main/agents/tech-lead.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/LangHY/claude-code-config-LANG/main/agents/test-writer.md $ curl -fsSL --create-dirs -o .claude/agents/ui-sketcher.md https://raw.githubusercontent.com/LangHY/claude-code-config-LANG/main/agents/ui-sketcher.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 (2)
| server | source | est. tokens |
|---|---|---|
| qwen-vl | local / custom | 2.5k |
| @_davideast/stitch-mcp · "stitch" | npm | 2.5k |
Skills (39)
clean-code-mentordocxexcalidraw-diagram-generatorfrontend-designgit-commithumanizerima-skilllark-approvallark-attendancelark-baselark-calendarlark-contactlark-doclark-drivelark-eventlark-imlark-maillark-markdownlark-minuteslark-okrlark-openapi-explorerlark-sharedlark-sheetslark-skill-makerlark-slideslark-tasklark-vclark-whiteboardlark-wikilark-workflow-meeting-summarylark-workflow-standup-reportmodern-ui-builderpdfpptxprdrefactorskill-creatorweb-accessxlsx
Subagents (10)
| bug-analyzer model: inherit | Bug 深度分析代理。用于分析代码执行流程、追踪变量状态变化、定位根本原因。触发词：调试、bug、错误、异常、为什么不工作、根本原因。 |
| code-explore model: inherit | 快速代码库探索代理。用于搜索文件、查找代码、回答代码库问题。thoroughness: "quick"(基础搜索) / "medium"(中等深度) / "very thorough"(全面分析)。触发词：搜索、查找、探索代码库、项目结构。 |
| code-reviewer model: inherit | 专业代码审查代理。用于审查代码质量、安全漏洞、性能问题、最佳实践。主动在完成代码后调用。触发词：代码审查、review、检查代码。 |
| dev-planner model: inherit | Expert development planner that breaks down user stories and requirements into detailed, actionable development plans. Specializes in task decomposition, dependency analysis, timeline estimation, and |
| general-purpose model: inherit | 通用任务代理。用于研究复杂问题、搜索代码、执行多步骤任务。当需要多次搜索或不确定能否一次找到时使用。 |
| impl-plan model: inherit | 软件架构规划代理。用于设计实现方案、识别关键文件、考虑架构权衡。返回分步计划、关键文件列表、架构决策。触发词：规划、设计、架构、实现方案、如何实现。 |
| story-generator model: inherit | Use this agent when you need to generate user stories with acceptance criteria from various inputs like git diffs, conversation history, PRD documents, or any requirements that need to be structured i |
| tech-lead model: inherit | 技术负责人代理。用于拆解复杂需求、定义任务、协调多代理工作。不要自己写代码，而是定义 Task Prompt。触发词：技术负责人、拆解需求、项目管理、任务拆分。 |
| test-writer model: inherit | 测试编写代理。用于编写单元测试、集成测试、端到端测试。遵循测试金字塔原则。触发词：写测试、单元测试、测试覆盖。 |
| ui-sketcher model: inherit | Universal UI Blueprint Engineer that transforms any functional requirement into visual ASCII interface designs, user stories, and interaction specifications. Excels at converting brief descriptions in |
Slash commands (5)
/clean-code-mentor/commit/modern-dev/modern-ui-builder/syncthing
Plugins (6)
clangd-lsp@claude-plugins-officialclaude-mem@thedotmackpua@pua-skillsskill-creator@claude-plugins-officialsuperpowers@claude-plugins-officialvercel-plugin@vercel-vercel-plugin
Similar rigs
DropFan/claude-code-plugins
Claude Code plugins collection - custom plugins and curated favorites. chat-saver/skill-extractor/codex-bridge/etc...
Skill Collector 2.5k tok ·
rongxinzy/RongxinAI
An all-in-one local AI Agent workspace with a fully self-developed stack
MCP Hoarder 41.4k tok ·
ThinkInAIXYZ/deepchat
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
Skill Collector 2.3k tok ·
OpenCoworkAI/open-cowork
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.
Pragmatist 382 tok ·