LeongJinZhou/ai-company
Personal AI software company kit for Claude Code: handbook, rules, staff agents, skills and plugin set
stack: JavaScript
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
$ git clone --depth 1 https://github.com/LeongJinZhou/ai-company 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 LeongJinZhou/ai-company/claude/skills/backend-standards .claude/skills/backend-standards $ npx degit LeongJinZhou/ai-company/claude/skills/brief-to-spec .claude/skills/brief-to-spec $ npx degit LeongJinZhou/ai-company/claude/skills/frontend-standards .claude/skills/frontend-standards $ npx degit LeongJinZhou/ai-company/claude/skills/lessons .claude/skills/lessons $ npx degit LeongJinZhou/ai-company/claude/skills/new-project .claude/skills/new-project $ npx degit LeongJinZhou/ai-company/claude/skills/product-sense .claude/skills/product-sense $ npx degit LeongJinZhou/ai-company/claude/skills/scale-standards .claude/skills/scale-standards $ npx degit LeongJinZhou/ai-company/claude/skills/security-checklist .claude/skills/security-checklist
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 (8)
Similar rigs
MTsatsarov/ai-setup
Claude Code marketplace: claude-kit, an interview-driven generator for per-project .claude/ setups
Minimalist 226 tok · · Q0
majejorex/secdev-suite
Your agent says it's secure. secdev makes it show the file:line. OWASP ASVS 5.0 / API Top 10 / MASVS checklist for Claude Code, Codex and Cursor.
Minimalist 752 tok · · Q3
just-be-dev/workspace
Where my work happens
Pragmatist 2.7k tok · · Q0
coolbress/plinth
A harness template for running a software project through an AI agent, for beginner engineers and non-engineers. Gated where a check can, guided where it can't: a Claude Code plugin, a project template and reusable CI.
Pragmatist 3.2k tok · · Q22