Frutzmann/claude-code-setup
No description.
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 Frutzmann/claude-code-setup/agents ./rig-claude-code-setup/agents $ npx degit Frutzmann/claude-code-setup/skills ./rig-claude-code-setup/skills $ npx degit Frutzmann/claude-code-setup/hooks ./rig-claude-code-setup/hooks
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 Frutzmann/claude-code-setup/skills/dev .claude/skills/dev $ npx degit Frutzmann/claude-code-setup/skills/ops .claude/skills/ops $ npx degit Frutzmann/claude-code-setup/skills/plan .claude/skills/plan $ npx degit Frutzmann/claude-code-setup/skills/review .claude/skills/review
$ curl -fsSL --create-dirs -o .claude/agents/adversary.md https://raw.githubusercontent.com/Frutzmann/claude-code-setup/main/agents/adversary.md $ curl -fsSL --create-dirs -o .claude/agents/dev-agent.md https://raw.githubusercontent.com/Frutzmann/claude-code-setup/main/agents/dev-agent.md $ curl -fsSL --create-dirs -o .claude/agents/verifier-agent.md https://raw.githubusercontent.com/Frutzmann/claude-code-setup/main/agents/verifier-agent.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 (4)
Subagents (3)
| adversary model: claude-opus-5-5 | Adversaire en lecture seule. Attaque contrats, tests en double échec et tickets déclarés finis. N'écrit jamais de code. |
| dev-agent model: claude-sonnet-5-5 | Code implementation worker. Use when executing a dev plan with must_haves — implements features, fixes bugs, refactors code. TDD in prod mode, lighter for poc and artifact deliveries. |
| verifier-agent model: claude-sonnet-5-5 | Verification specialist. Use when checking that delivered code matches plan must_haves — verifies existence, substance, wiring, and functionality with fresh context. |
Similar rigs
archcore-ai/archcore
Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.
Minimalist 337 tok ·
yashiel/claude-code-starter
Claude Code starter template: Next.js 15 + Appwrite + shadcn/ui with CLAUDE.md, security playbook, MCP setup, and custom skills
Pragmatist 7.8k tok ·
theNickNance/claude-code-setup
—
Pragmatist 3.5k tok ·
ribeirogab/specwright
A multi-host plugin for Claude Code, Codex, and OpenCode. It gives a repository one explicit, change-driven engineering workflow:
Pragmatist 1.6k tok ·