Sh1v4x/shipyard
Local control panel that drives Claude Code on your git worktrees, Linear tickets and GitHub pull requests.
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code
$ npx degit Sh1v4x/shipyard/agents ./rig-shipyard/agents 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.
$ curl -fsSL --create-dirs -o .claude/agents/reviewer-architecture.md https://raw.githubusercontent.com/Sh1v4x/shipyard/main/agents/reviewer-architecture.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer-performance.md https://raw.githubusercontent.com/Sh1v4x/shipyard/main/agents/reviewer-performance.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer-quality.md https://raw.githubusercontent.com/Sh1v4x/shipyard/main/agents/reviewer-quality.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer-security.md https://raw.githubusercontent.com/Sh1v4x/shipyard/main/agents/reviewer-security.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 *)"
]
}
} Subagents (4)
| reviewer-architecture model: sonnet | Reviews a PR diff for architecture and design (modules, responsibilities, dependencies, abstractions). Run in parallel with the other reviewers. |
| reviewer-performance model: sonnet | Reviews a PR diff for performance and scalability (queries, complexity, rendering, resources). Run in parallel with the other reviewers. |
| reviewer-quality model: sonnet | Reviews a PR diff for code quality and correctness (bugs, edge cases, readability, maintainability). Run in parallel with the other reviewers. |
| reviewer-security model: sonnet | Reviews a PR diff for security (input validation, injections, authentication, authorization, secrets, dependencies). Run in parallel with the other reviewers. |
Similar rigs
imtemp-dev/claude-bts
Bulletproof Technical Specification — catches spec errors before they become debugging sessions. A CLI tool for Claude Code.
Orchestrator 2.7k tok · · Q3
LucasSantana-Dev/sharekit
Share your AI coding setup — CLAUDE.md, skills, cursorrules — with one command. install / preview / rollback.
Orchestrator 9.6k tok · · Q23
thkt/dotclaude
Personal Claude Code configuration — 28 skills, 28 agents, deterministic multi-agent workflows, and quality-gate hooks
Fort Knox 3.4k tok · · Q42
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Minimalist 723 tok · · Q3