beardsservices-png/Beardsservices-claude-code-business-starter-kit
Agentic setup includes skills, mcp, etc
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit beardsservices-png/Beardsservices-claude-code-business-starter-kit/.claude ./rig-beardsservices-claude-code-business-starter-kit # 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.
$ npx degit beardsservices-png/Beardsservices-claude-code-business-starter-kit/.claude/skills/create-agent .claude/skills/create-agent $ npx degit beardsservices-png/Beardsservices-claude-code-business-starter-kit/.claude/skills/create-command .claude/skills/create-command $ npx degit beardsservices-png/Beardsservices-claude-code-business-starter-kit/.claude/skills/create-hook .claude/skills/create-hook $ npx degit beardsservices-png/Beardsservices-claude-code-business-starter-kit/.claude/skills/create-mcp .claude/skills/create-mcp $ npx degit beardsservices-png/Beardsservices-claude-code-business-starter-kit/.claude/skills/create-skill .claude/skills/create-skill
$ curl -fsSL --create-dirs -o .claude/agents/mcp-finder.md https://raw.githubusercontent.com/beardsservices-png/Beardsservices-claude-code-business-starter-kit/main/.claude/agents/mcp-finder.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 (5)
Subagents (1)
| mcp-finder model: sonnet | Searches online to find MCP servers. SPAWNED BY create-mcp skill after identifying user needs. Searches NPM, GitHub, and MCP directories to find the best options. |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Write|Edit | Check if a skill was just created or renamed in .claude/skills/. If so, update the CLAUDE.md routing table to include it. Only update if the skill is new or the name changed. |
Permissions
deny (0)
—
ask (0)
—
allow (5)
Read
Glob
Grep
Bash(git:*)
Bash(npm:*)
Similar rigs
openma-ai/open-managed-agents
Open Managed Agents — an open-source alternative to Claude Managed Agents and OpenAI Agents API. Deploy with Node.js or Docker, run on Cloudflare, or use hosted OpenMA. Choose your models, harnesses and sandboxes.
Pragmatist 6.2k tok ·
qa-aman/claude-skills
—
Minimalist 1.6k tok ·
nongjun/feishu-cursor-claw
Turn Feishu/Lark into a remote control for Cursor AI — your personal AI strategic partner via IM
Pragmatist 4.5k tok ·
topruss05-lgtm/claude
Personal Claude Code config: skills, system prompts, MCP, commands
Minimalist 650 tok ·