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 takealook97/vat/.claude ./rig-vat # 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 takealook97/vat/.agents/skills/add-a-lint-rule .claude/skills/add-a-lint-rule $ npx degit takealook97/vat/.agents/skills/change-a-command-contract .claude/skills/change-a-command-contract $ npx degit takealook97/vat/.agents/skills/cut-a-release .claude/skills/cut-a-release $ npx degit takealook97/vat/cmd/vat/.agents/skills/before-cross-repo-work .claude/skills/before-cross-repo-work $ npx degit takealook97/vat/cmd/vat/.agents/skills/consult-the-brain-first .claude/skills/consult-the-brain-first $ npx degit takealook97/vat/examples/workspace/.agents/skills/keep-the-brain-current .claude/skills/keep-the-brain-current
$ curl -fsSL --create-dirs -o .claude/agents/docs-writer.md https://raw.githubusercontent.com/takealook97/vat/main/.claude/agents/docs-writer.md $ curl -fsSL --create-dirs -o .claude/agents/go-reviewer.md https://raw.githubusercontent.com/takealook97/vat/main/.claude/agents/go-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/rule-designer.md https://raw.githubusercontent.com/takealook97/vat/main/.claude/agents/rule-designer.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 (6)
add-a-lint-rulechange-a-command-contractcut-a-releasebefore-cross-repo-workconsult-the-brain-firstkeep-the-brain-current
Subagents (3)
| docs-writer model: sonnet | Keeps the documentation true to the code and free of restated obviousness. |
| go-reviewer model: opus | Reviews Go changes against this repository's safety and design rules. |
| rule-designer model: opus | Turns a described failure into a checkable lint or doctor rule, or rejects it. |
Similar rigs
Eyad-Alqaysi/claude-code-config
My personal Claude Code config — settings, global CLAUDE.md, slash commands, subagents, and hooks. Fork or copy what you like.
YOLO Cowboy 2.1k tok ·
alirezarezvani/claude-code-tresor
A world-class collection of Claude Code utilities: autonomous skills, expert agents, slash commands, and prompts that supercharge your development workflow
Orchestrator 6.4k tok ·
Yassinekrn/claude-setup
Personal Claude Code setup — orchestrator/subagent delegation policy, custom agents, and a colored PowerShell statusline (git branch, model+effort, tokens, cost, rate limits).
Orchestrator 1.2k tok ·
hwchany0ung/claude-agent-playbook
Claude Code multi-agent setup: agents, hooks, skills, commands
Orchestrator 783 tok ·