agentrigs
+ submit rig
~ / rigs / LuccaRomanelli / base-project

LuccaRomanelli/base-project

Reusable React + Supabase template with Claude Code agents, TDD workflow, and full testing infrastructure

↗ GitHub ★ 0 no license updated 8mo ago project Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~11.2k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add playwright -- bunx @playwright/mcp@latest
$ npx degit LuccaRomanelli/base-project/.claude ./rig-base-project  # 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 playwright -- bunx @playwright/mcp@latest
$ npx degit LuccaRomanelli/base-project/.claude/skills/dev .claude/skills/dev
$ npx degit LuccaRomanelli/base-project/.claude/skills/import-config .claude/skills/import-config
$ npx degit LuccaRomanelli/base-project/.claude/skills/prd .claude/skills/prd
$ npx degit LuccaRomanelli/base-project/.claude/skills/ralph .claude/skills/ralph
$ npx degit LuccaRomanelli/base-project/.claude/skills/start .claude/skills/start
$ curl -fsSL --create-dirs -o .claude/agents/dba.md https://raw.githubusercontent.com/LuccaRomanelli/base-project/main/.claude/agents/dba.md
$ curl -fsSL --create-dirs -o .claude/agents/devils-advocate.md https://raw.githubusercontent.com/LuccaRomanelli/base-project/main/.claude/agents/devils-advocate.md
$ curl -fsSL --create-dirs -o .claude/agents/frontend-developer.md https://raw.githubusercontent.com/LuccaRomanelli/base-project/main/.claude/agents/frontend-developer.md
$ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/LuccaRomanelli/base-project/main/.claude/agents/qa.md
$ curl -fsSL --create-dirs -o .claude/agents/security-specialist.md https://raw.githubusercontent.com/LuccaRomanelli/base-project/main/.claude/agents/security-specialist.md
$ curl -fsSL --create-dirs -o .claude/agents/software-architect.md https://raw.githubusercontent.com/LuccaRomanelli/base-project/main/.claude/agents/software-architect.md
$ curl -fsSL --create-dirs -o .claude/agents/supabase-backend.md https://raw.githubusercontent.com/LuccaRomanelli/base-project/main/.claude/agents/supabase-backend.md
$ curl -fsSL --create-dirs -o .claude/agents/tech-lead.md https://raw.githubusercontent.com/LuccaRomanelli/base-project/main/.claude/agents/tech-lead.md
$ curl -fsSL --create-dirs -o .claude/agents/test-specialist.md https://raw.githubusercontent.com/LuccaRomanelli/base-project/main/.claude/agents/test-specialist.md
$ curl -fsSL --create-dirs -o .claude/agents/ui-ux-specialist.md https://raw.githubusercontent.com/LuccaRomanelli/base-project/main/.claude/agents/ui-ux-specialist.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 (1)

serversourceest. tokens
Playwright MCP · "playwright" npm 7.5k

Skills (5)

devimport-configprdralphstart

Subagents (10)

dba
model: sonnet
|
devils-advocate
model: opus
|
frontend-developer
model: sonnet
|
qa
model: sonnet
|
security-specialist
model: sonnet
|
software-architect
model: opus
|
supabase-backend
model: sonnet
|
tech-lead
model: opus
|
test-specialist
model: sonnet
|
ui-ux-specialist
model: sonnet
|

Slash commands (2)

/create-pr/tdd

Similar rigs

ThinhHoang1/claude-code-agent-team
An AI dev team for Claude Code agent teams: 8 role agents, a HANDOFF protocol and 3 hook quality gates — with the TeammateIdle infinite-loop bug fixed and regression-tested.
★ 0 project Claude Code 8 agents 3 hooks 1d ago
Orchestrator 1.6k tok ·
Dev-Toolbelt/dev-team-agents
Multi-agent development harness for Claude Code, Codex CLI, and opencode — stack-agnostic, project-aware agents, commands, skills, and hooks for planning, building, reviewing, and documenting software.
★ 6 project Claude Code 3 skills 18 agents 4 hooks 7d ago
Orchestrator 15.5k tok ·
xhulz/nina
Harness orchestration for Claude Code: composes a gated multi-agent pipeline into projects from versioned layers, holds its loop caps with hooks, measures it from transcripts, and turns recurring mistakes into rules.
★ 1 project Claude Code 80 agents 1 hooks today
Orchestrator 9.3k tok ·
rohunj/claude-build-workflow
Automated workflow for building apps with Claude Code. Describe what you want, answer questions, let it build autonomously.
★ 231 project Claude CodeCodex 13 skills 9mo ago
Skill Collector 17.7k tok ·
copied ✓