spideynolove/claude-code-in-action
The process I experienced firsthand through the https://anthropic.skilljar.com/claude-code-in-action course using real-world daily projects
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 $ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -- npx -y @modelcontextprotocol/server-github $ claude mcp add notionMCP -- npx -y mcp-remote https://mcp.notion.com/sse $ claude mcp add deepwiki -- npx mcp-remote https://mcp.deepwiki.com/sse $ claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/git $ claude mcp add fetch -- uvx mcp-server-fetch $ claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking $ claude mcp add serena -- uvx --from git+https://github.com/oraios/serena serena-mcp-server $ claude mcp add playwright -- npx @playwright/mcp@latest $ npx degit spideynolove/claude-code-in-action/03-auto-simplify/.claude ./rig-claude-code-in-action # 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 $ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -- npx -y @modelcontextprotocol/server-github $ claude mcp add notionMCP -- npx -y mcp-remote https://mcp.notion.com/sse $ claude mcp add deepwiki -- npx mcp-remote https://mcp.deepwiki.com/sse $ claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/git $ claude mcp add fetch -- uvx mcp-server-fetch $ claude mcp add sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking $ claude mcp add serena -- uvx --from git+https://github.com/oraios/serena serena-mcp-server $ claude mcp add playwright -- npx @playwright/mcp@latest
$ npx degit spideynolove/claude-code-in-action/.claude/skills/codegraphcontext .claude/skills/codegraphcontext $ npx degit spideynolove/claude-code-in-action/00-materials/claude-howto/.claude/skills/lesson-quiz .claude/skills/lesson-quiz $ npx degit spideynolove/claude-code-in-action/00-materials/claude-howto/.claude/skills/self-assessment .claude/skills/self-assessment $ npx degit spideynolove/claude-code-in-action/02-mcp/lightpanda/.claude/skills/lightpanda .claude/skills/lightpanda $ npx degit spideynolove/claude-code-in-action/05-subagents/.claude/skills/mcp-knowledge-graph .claude/skills/mcp-knowledge-graph $ npx degit spideynolove/claude-code-in-action/05-subagents/.claude/skills/repomix .claude/skills/repomix $ npx degit spideynolove/claude-code-in-action/05-subagents/.claude/skills/sequential-thinking .claude/skills/sequential-thinking $ npx degit spideynolove/claude-code-in-action/05-subagents/dotfiles/.claude/skills/nuxt .claude/skills/nuxt $ npx degit spideynolove/claude-code-in-action/20-skill-sync/skills/sync-to-codex .claude/skills/sync-to-codex $ npx degit spideynolove/claude-code-in-action/25-autoresearch/.claude/skills/autoresearch .claude/skills/autoresearch $ npx degit spideynolove/claude-code-in-action/27-tdd-conductor-llmdev/.claude/skills/embedding-strategies .claude/skills/embedding-strategies $ npx degit spideynolove/claude-code-in-action/27-tdd-conductor-llmdev/.claude/skills/hybrid-search-implementation .claude/skills/hybrid-search-implementation $ npx degit spideynolove/claude-code-in-action/27-tdd-conductor-llmdev/.claude/skills/langchain-architecture .claude/skills/langchain-architecture $ npx degit spideynolove/claude-code-in-action/27-tdd-conductor-llmdev/.claude/skills/llm-evaluation .claude/skills/llm-evaluation $ npx degit spideynolove/claude-code-in-action/27-tdd-conductor-llmdev/.claude/skills/prompt-engineering-patterns .claude/skills/prompt-engineering-patterns $ npx degit spideynolove/claude-code-in-action/27-tdd-conductor-llmdev/.claude/skills/rag-implementation .claude/skills/rag-implementation $ npx degit spideynolove/claude-code-in-action/27-tdd-conductor-llmdev/.claude/skills/similarity-search-patterns .claude/skills/similarity-search-patterns $ npx degit spideynolove/claude-code-in-action/27-tdd-conductor-llmdev/.claude/skills/vector-index-tuning .claude/skills/vector-index-tuning $ npx degit spideynolove/claude-code-in-action/28-continuous-patterns/.claude/skills/compound-learnings .claude/skills/compound-learnings $ npx degit spideynolove/claude-code-in-action/28-continuous-patterns/.claude/skills/create-handoff .claude/skills/create-handoff $ npx degit spideynolove/claude-code-in-action/29-skill-authoring/.claude/skills/agentic-engineering .claude/skills/agentic-engineering $ npx degit spideynolove/claude-code-in-action/29-skill-authoring/.claude/skills/skill-security-auditor .claude/skills/skill-security-auditor
$ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/.claude/agents/e2e-runner.md $ curl -fsSL --create-dirs -o .claude/agents/go-reviewer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/.claude/agents/go-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/loop-operator.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/.claude/agents/loop-operator.md $ curl -fsSL --create-dirs -o .claude/agents/python-reviewer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/.claude/agents/python-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/.claude/agents/refactor-cleaner.md $ curl -fsSL --create-dirs -o .claude/agents/rust-reviewer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/.claude/agents/rust-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/typescript-reviewer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/.claude/agents/typescript-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/codebase-analyst.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/.claude/agents/codebase-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/mcp-manager.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/.claude/agents/mcp-manager.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/role-analyzer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/.claude/agents/role-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/role-architect.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/.claude/agents/role-architect.md $ curl -fsSL --create-dirs -o .claude/agents/role-reviewer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/.claude/agents/role-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/role-security.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/.claude/agents/role-security.md $ curl -fsSL --create-dirs -o .claude/agents/task-runner.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/.claude/agents/task-runner.md $ curl -fsSL --create-dirs -o .claude/agents/codebase-analyst.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/dotfiles/.claude/agents/codebase-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/mcp-manager.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/dotfiles/.claude/agents/mcp-manager.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/05-subagents/dotfiles/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/09-gstack-specific/.claude/agents/e2e-runner.md $ curl -fsSL --create-dirs -o .claude/agents/go-reviewer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/09-gstack-specific/.claude/agents/go-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/loop-operator.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/09-gstack-specific/.claude/agents/loop-operator.md $ curl -fsSL --create-dirs -o .claude/agents/python-reviewer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/09-gstack-specific/.claude/agents/python-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/09-gstack-specific/.claude/agents/refactor-cleaner.md $ curl -fsSL --create-dirs -o .claude/agents/rust-reviewer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/09-gstack-specific/.claude/agents/rust-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/typescript-reviewer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/09-gstack-specific/.claude/agents/typescript-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/27-tdd-conductor-llmdev/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/conductor-validator.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/27-tdd-conductor-llmdev/.claude/agents/conductor-validator.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-orchestrator.md https://raw.githubusercontent.com/spideynolove/claude-code-in-action/main/27-tdd-conductor-llmdev/.claude/agents/tdd-orchestrator.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 (9)
| server | source | est. tokens |
|---|---|---|
| Context7 | npm | 1.2k |
| GitHub MCP · "github" env: GITHUB_PERSONAL_ACCESS_TOKEN | npm | 18.0k |
| Notion · "notionMCP" | remote | 6.0k |
| DeepWiki | remote | 900 |
| Filesystem | npm | 4.2k |
| Fetch | pypi | 450 |
| Sequential Thinking · "sequential-thinking" | npm | 900 |
| Serena | git | 8.0k |
| Playwright MCP · "playwright" | npm | 7.5k |
Skills (22)
codegraphcontextlesson-quizself-assessmentlightpandamcp-knowledge-graphrepomixsequential-thinkingnuxtsync-to-codexautoresearchembedding-strategieshybrid-search-implementationlangchain-architecturellm-evaluationprompt-engineering-patternsrag-implementationsimilarity-search-patternsvector-index-tuningcompound-learningscreate-handoffagentic-engineeringskill-security-auditor
Subagents (28)
| e2e-runner model: sonnet | End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines fl |
| go-reviewer model: sonnet | Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects. |
| loop-operator model: sonnet | Operate autonomous agent loops, monitor progress, and intervene safely when loops stall. |
| python-reviewer model: sonnet | Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects. |
| refactor-cleaner model: sonnet | Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely r |
| rust-reviewer model: sonnet | Expert Rust code reviewer specializing in ownership, lifetimes, error handling, unsafe usage, and idiomatic patterns. Use for all Rust code changes. MUST BE USED for Rust projects. |
| typescript-reviewer model: sonnet | Expert TypeScript/JavaScript code reviewer specializing in type safety, async correctness, Node/web security, and idiomatic patterns. Use for all TypeScript and JavaScript code changes. MUST BE USED f |
| codebase-analyst | Analyzes a codebase using repomix + sequential-thinking + knowledge-graph. Returns structured tables covering architecture, runtime behaviors, and failure modes. Stores findings in .aim/ for future se |
| mcp-manager | Executes MCP tool calls via mcporter while keeping tool schemas out of the main context window. Use when any agent needs to run a specific MCP tool without polluting its own context. For general task |
| orchestrator | Runs the full coding workflow end-to-end for a given goal: clarify → analyze codebase → plan → implement → review → test. Spawns codebase-analyst and task-runner as subagents. Use when given a feature |
| role-analyzer model: opus | Root cause analysis expert. Use when investigating bugs, errors, performance degradation, or any complex problem where the cause is unknown. Evidence-First: 5 Whys + counter-evidence, systems thinking |
| role-architect model: opus | System architect. Use when evaluating architecture decisions, technology selection, scalability design, or creating Architecture Decision Records. Evidence-First design with MECE analysis and evolutio |
| role-reviewer model: sonnet | Code review expert. Use when reviewing PRs, checking code quality, or evaluating against Clean Code principles and official style guides. MECE review across correctness, readability, maintainability, |
| role-security model: opus | Security audit expert. Use when asked to check for vulnerabilities, run a security audit, or analyze code for OWASP Top 10 / LLM security risks. Evidence-First approach: STRIDE threat modeling, CVE ma |
| task-runner | Generic task executor that delegates work to a specified AI CLI tool based on role assignment. Receives structured task with role, tool, task_id, and context from the orchestrator. Use when the orches |
| codebase-analyst | Analyzes a codebase using repomix + sequential-thinking + knowledge-graph. Returns structured tables covering architecture, runtime behaviors, and failure modes. Stores findings in .aim/ for future se |
| mcp-manager | Executes MCP tool calls and CLI tasks while keeping tool schemas out of the main context window. Tries available AI CLIs in priority order before falling back to direct mcporter calls. Use when any ag |
| orchestrator | Runs the full coding workflow end-to-end for a given goal: clarify → analyze codebase → plan → implement → review → test. Spawns codebase-analyst and mcp-manager as subagents. Use when given a feature |
| e2e-runner model: sonnet | End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines fl |
| go-reviewer model: sonnet | Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects. |
| loop-operator model: sonnet | Operate autonomous agent loops, monitor progress, and intervene safely when loops stall. |
| python-reviewer model: sonnet | Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects. |
| refactor-cleaner model: sonnet | Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely r |
| rust-reviewer model: sonnet | Expert Rust code reviewer specializing in ownership, lifetimes, error handling, unsafe usage, and idiomatic patterns. Use for all Rust code changes. MUST BE USED for Rust projects. |
| typescript-reviewer model: sonnet | Expert TypeScript/JavaScript code reviewer specializing in type safety, async correctness, Node/web security, and idiomatic patterns. Use for all TypeScript and JavaScript code changes. MUST BE USED f |
| code-reviewer model: opus | Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanni |
| conductor-validator model: opus | Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context. |
| tdd-orchestrator model: opus | Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams |
Hooks (6)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Edit|Write|NotebookEdit | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/PostToolUse/counter.py" |
| UserPromptSubmit | * | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/UserPromptSubmit/gate.py" |
| Stop | * | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/Stop/stop.py" |
| Notification | * | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/Notification/notify.py" |
| PostToolUse | Edit|Write|MultiEdit | ./hooks/enforce-token-usage.sh |
| PostToolUse | Edit|Write|MultiEdit | ./hooks/run-typecheck.sh |
Slash commands (37)
/ui-brief/ui-build/ui-critique/ui-layout/ui-repair/ui-style/detect-team/init-project/role-debate/role/startup/implement/plan-only/workflow-install/workflow-uninstall/e2e/learn/loop-start/loop-status/xia-group/xia/debug/review/standup/autoresearch/autoresearch/predict/autoresearch/scenario/autoresearch/security/autoresearch/ship/implement/manage/new-track/revert/setup/status/tdd-cycle/predict-issues
Similar rigs
wasabeef/claude-code-cookbook
A collection of settings to make Claude Code more useful.
YOLO Cowboy 48.2k tok ·
cassler/awesome-claude-code-setup
Give Claude the super powers it deserves with this power user collection of bash scripts and slash commands
Pragmatist 31.8k tok ·
Cyvid7-Darus10/claude-code-config
My Claude Code configuration: 29 agents, 60 commands, 60 skills, 65 rules. Built on everything-claude-code + obra/superpowers.
Fort Knox 10.7k tok ·
Rene-Kuhm/claude-code-enterprise-config
Enterprise Claude Code configuration: 8 specialised agents, 20 invocable skills, 7 context rules, 6 commands, 8 automated hooks and 19 MCP server integrations, with an installer.
Fort Knox 75.1k tok ·