MajidBabaeifar/towercab
From intent to production: spec, plan, code, deploy, live test and rollback, orchestrated around Claude Code. Inspired by Anthropic's AI native SDLC playbook.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit MajidBabaeifar/towercab/agents ./rig-towercab/agents $ npx degit MajidBabaeifar/towercab/skills ./rig-towercab/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 MajidBabaeifar/towercab/skills/intent .claude/skills/intent $ curl -fsSL --create-dirs -o .claude/agents/design.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/design.md $ curl -fsSL --create-dirs -o .claude/agents/features.md https://raw.githubusercontent.<redacted>.md $ curl -fsSL --create-dirs -o .claude/agents/merge-review.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/merge-review.md $ curl -fsSL --create-dirs -o .claude/agents/plan.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/plan.md $ curl -fsSL --create-dirs -o .claude/agents/repair.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/repair.md $ curl -fsSL --create-dirs -o .claude/agents/review-infra.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/review-infra.md $ curl -fsSL --create-dirs -o .claude/agents/review-security.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/review-security.md $ curl -fsSL --create-dirs -o .claude/agents/review.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/review.md $ curl -fsSL --create-dirs -o .claude/agents/risk.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/risk.md $ curl -fsSL --create-dirs -o .claude/agents/score.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/score.md $ curl -fsSL --create-dirs -o .claude/agents/shadow.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/shadow.md $ curl -fsSL --create-dirs -o .claude/agents/worker.md https://raw.githubusercontent.com/MajidBabaeifar/towercab/main/agents/worker.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (1)
Subagents (12)
| design model: mission | — |
| features model: agent | — |
| merge-review model: review | — |
| plan model: mission | — |
| repair model: mission | — |
| review-infra model: review | — |
| review-security model: review | — |
| review model: review | — |
| risk model: review | — |
| score model: agent | — |
| shadow model: agent | — |
| worker model: mission | — |
Similar rigs
Atypical-Consulting/kaldor
Intent/code review guard for Claude Code
Minimalist 84 tok · · Q15
timopruesse/.dotfiles
My dotfiles 🤡
Orchestrator 11.2k tok · · Q18
WaterTian/cc-bot
Develop project from group chat — by Claude Code. 接 AI 进群里开发项目。
YOLO Cowboy 3.3k tok · · Q0
AlmanacCode/codealmanac
A codebase wiki for AI coding agents. Captures what the code can't say: decisions, flows, invariants, gotchas.
Pragmatist 4.1k tok · · Q8