agentrigs
+ submit rig
~ / rigs / lucasandradeb / my-claude-code-config

lucasandradeb/my-claude-code-config

My personal Claude Code configuration — MCP servers, plugins, CLAUDE.md and setup guides

↗ GitHub ★ 2 MIT updated 2d ago personal setup Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.1k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit lucasandradeb/my-claude-code-config/agents ./rig-my-claude-code-config/agents
$ npx degit lucasandradeb/my-claude-code-config/commands ./rig-my-claude-code-config/commands
$ npx degit lucasandradeb/my-claude-code-config/skills ./rig-my-claude-code-config/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.

$ npx degit lucasandradeb/my-claude-code-config/skills/spec-driven .claude/skills/spec-driven
$ curl -fsSL --create-dirs -o .claude/agents/domain-analyst.md https://raw.githubusercontent.com/lucasandradeb/my-claude-code-config/master/agents/domain-analyst.md
$ curl -fsSL --create-dirs -o .claude/agents/pr-reviewer.md https://raw.githubusercontent.com/lucasandradeb/my-claude-code-config/master/agents/pr-reviewer.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 *)"
    ]
  }
}

Skills (1)

spec-driven

Subagents (2)

domain-analyst
model: sonnet
Template de subagente especializado em domínio de negócio para revisão de código. Adapte com o contexto específico do seu projeto — regras de negócio, tipos numéricos críticos, invariantes de domínio.
pr-reviewer
model: sonnet
Revisa uma única PR do GitHub e posta os comentários inline. Projetado para ser disparado em paralelo — um subagente por PR. Requer no brief: número da PR e owner/repo.

Slash commands (2)

/preflight/review

Similar rigs

Kalypsokichu-code/kalypso-claude-workflow
My Claude Code setup - three-tier permissions, hook router, slash commands, subagents, scaffolding. Opinionated.
★ 18 setup Claude Code 1 agents 11 hooks 6mo ago
Fort Knox 549 tok ·
errpoulos/claude-sprint-workflow
Multi-agent Claude Code workflow for Jira-integrated sprint management — plan, implement, QA, and release with AI orchestration
★ 0 project Claude Code 4 agents 3mo ago
Pragmatist 578 tok ·
kraulerson/solo-orchestrator
AI-assisted software development methodology for solo builders
★ 30 project Claude Code 4 skills 1 agents 5 hooks 9d ago
Automator 10.1k tok ·
marcuslannister/claude-code-settings
Claude Code settings, hooks, and skills
★ 0 setup Claude CodeCopilot 6 skills 7 agents 20 hooks today
YOLO Cowboy 1.7k tok ·
copied ✓