ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http sentry https://mcp.sentry.dev/mcp $ claude mcp add context7 -- npx -y @upstash/context7-mcp $ npx degit cc-claws/cc-code/.claude ./rig-cc-code # 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 --transport http sentry https://mcp.sentry.dev/mcp $ claude mcp add context7 -- npx -y @upstash/context7-mcp
$ npx degit cc-claws/cc-code/.claude/skills/issue-archive .claude/skills/issue-archive $ npx degit cc-claws/cc-code/.claude/skills/issue-create .claude/skills/issue-create $ npx degit cc-claws/cc-code/.claude/skills/issue-verify .claude/skills/issue-verify $ npx degit cc-claws/cc-code/.claude/skills/langfuse .claude/skills/langfuse $ npx degit cc-claws/cc-code/.claude/skills/llm-log-analyzer .claude/skills/llm-log-analyzer $ npx degit cc-claws/cc-code/.claude/skills/peri-style .claude/skills/peri-style $ npx degit cc-claws/cc-code/.claude/skills/slop-cleaner .claude/skills/slop-cleaner $ npx degit cc-claws/cc-code/.claude/skills/teacher .claude/skills/teacher
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/cc-claws/cc-code/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/hello-agent.md https://raw.githubusercontent.com/cc-claws/cc-code/main/.claude/agents/hello-agent.md $ curl -fsSL --create-dirs -o .claude/agents/web-researcher.md https://raw.githubusercontent.com/cc-claws/cc-code/main/.claude/agents/web-researcher.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 (2)
| server | source | est. tokens |
|---|---|---|
| Sentry | remote · remote | 4.5k |
| Context7 | npm | 1.2k |
Skills (8)
Subagents (3)
| code-reviewer | — |
| hello-agent | 一个简单的打招呼 agent |
| web-researcher | Web research specialist — searches and fetches web pages via npx @langgraph-js/web-fetch (bash) to produce structured Markdown reports with citations |
Similar rigs
AizenvoltPrime/claude-setup
—
Pragmatist 1.2k tok ·
br3ndonland/dotfiles
Computer setup and settings. Apple Silicon ready.
YOLO Cowboy 36.9k tok ·
codeverbojan/claude-code-kickstart
Production-grade agentic workflow template for Claude Code. 4-layer architecture, task playbooks, session memory, sub-agents, one-click install.
Orchestrator 10.2k tok ·
kicchann/claude-code-config
—
Automator 10.3k tok ·