~ / rigs / PacktPublishing / Agentic-Coding-with-Claude-Code

PacktPublishing/Agentic-Coding-with-Claude-Code

Agentic Coding with Claude Code, published by Packt

↗ GitHub ★ 200 MIT updated 4mo ago project Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~13.8k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add --transport http context7 https://mcp.context7.com/mcp -H 'CONTEXT7_API_KEY: YOUR_VALUE'
$ claude mcp add --transport http tavily 'https://mcp.tavily.com/mcp/?tavilyApiKey=XXXXX'
$ claude mcp add playwright -- npx @playwright/mcp@latest
$ npx degit PacktPublishing/Agentic-Coding-with-Claude-Code/Chapter03/hooks-notification/.claude ./rig-agentic-coding-with-claude-code  # 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 --transport http context7 https://mcp.context7.com/mcp -H 'CONTEXT7_API_KEY: YOUR_VALUE'
$ claude mcp add --transport http tavily 'https://mcp.tavily.com/mcp/?tavilyApiKey=XXXXX'
$ claude mcp add playwright -- npx @playwright/mcp@latest
$ curl -fsSL --create-dirs -o .claude/agents/prd-writer.md https://raw.githubusercontent.com/PacktPublishing/Agentic-Coding-with-Claude-Code/main/Chapter02/hookhub2/.claude/agents/prd-writer.md
$ curl -fsSL --create-dirs -o .claude/agents/python-backend-dev.md https://raw.githubusercontent.com/PacktPublishing/Agentic-Coding-with-Claude-Code/main/Chapter02/hookhub2/.claude/agents/python-backend-dev.md
$ curl -fsSL --create-dirs -o .claude/agents/react-typescript-specialist.md https://raw.githubusercontent.com/PacktPublishing/Agentic-Coding-with-Claude-Code/main/Chapter02/hookhub2/.claude/agents/react-typescript-specialist.md
$ curl -fsSL --create-dirs -o .claude/agents/system-architect.md https://raw.githubusercontent.com/PacktPublishing/Agentic-Coding-with-Claude-Code/main/Chapter02/hookhub2/.claude/agents/system-architect.md
$ curl -fsSL --create-dirs -o .claude/agents/ui-designer.md https://raw.githubusercontent.com/PacktPublishing/Agentic-Coding-with-Claude-Code/main/Chapter02/hookhub2/.claude/agents/ui-designer.md
$ curl -fsSL --create-dirs -o .claude/agents/code-comedy-carl.md https://raw.githubusercontent.com/PacktPublishing/Agentic-Coding-with-Claude-Code/main/Chapter07/.claude/agents/code-comedy-carl.md
$ curl -fsSL --create-dirs -o .claude/agents/mermaid-diagram-generator.md https://raw.githubusercontent.com/PacktPublishing/Agentic-Coding-with-Claude-Code/main/Chapter07/.claude/agents/mermaid-diagram-generator.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 (4)

serversourceest. tokens
verbose-server local / custom · remote 2.5k
Context7 remote · remote 1.2k
Tavily remote · remote 2.0k
Playwright MCP · "playwright" npm 7.5k

Subagents (7)

prd-writer
model: inherit
Use this agent for writing comprehensive Product Requirements Documents (PRDs) for software projects or features. This includes documenting business goals, user personas, functional requirements, user
python-backend-dev
model: inherit
Use this agent when developing Python backend services, APIs, data processing pipelines, or implementing comprehensive testing strategies. This agent excels at creating production-ready Python code wi
react-typescript-specialist
model: inherit
Use this agent when you need to develop React components with TypeScript, implement modern React patterns with strict type safety, or refactor existing React code to follow TypeScript best practices.
system-architect
model: inherit
Use this agent when you need comprehensive system design, architectural planning, or technology integration decisions. This agent should be used proactively at the start of new projects, when scaling
ui-designerUse this agent for creating and improving user interfaces. Specializes in ASCII wireframing for rapid prototyping, UI components, design systems, and visual aesthetics for web and mobile apps, with a
code-comedy-carl
model: sonnet
>
mermaid-diagram-generator
model: sonnet
Use this agent when you need to convert textual descriptions, requirements, processes, or concepts into visual Mermaid diagrams. Examples include: <example>Context: User wants to visualize a software

Hooks (1)

eventmatcherruns
Stop*uv run ~/GithubProjects/claude-code-crash-course/play_sound.py

Slash commands (3)

/infinite/commit-code/dad-joke

Similar rigs

copied ✓