ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~3.8k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add alumnium -- mise :dev/mcp $ npx degit alumnium-hq/alumnium/.claude ./rig-alumnium # 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 alumnium -- mise :dev/mcp 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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| mise · "alumnium" | binary | 2.5k |
Permissions
deny (0)
—
ask (0)
—
allow (14)
mcp__alumnium
Bash(cat:*)
Bash(curl:*)
Bash(grep:*)
Bash(mise:*)
Bash(poetry poe:*)
Bash(poetry run behave:*)
Bash(poetry run pytest:*)
Bash(poetry run python:*)
Bash(npm pack:*)
Bash(npm run:*)
Bash(npx tsc:*)
Bash(wc:*)
WebFetch(domain:claude.ai)
Similar rigs
brainpad-whiterabbit/deguboard
A kanban board inside your Git repository for building software with AI agents: plans you approve, a quality gate on every PR, and measured agent runs.
Pragmatist 3.8k tok · · Q0
ziptie-soft/local-decider
Let a small local decision model answer routine coding-agent questions (permission prompts, command risk, model routing, turn outcomes) for Paseo, Claude Code and Codex. Shadow by default, fails open.
Pragmatist 5.8k tok · · Q3
bendrucker/dotfiles
dotfiles for zsh / macOS
Pragmatist 7.7k tok · · Q23
dayjobdoor/dotfiles
Ubuntu 26.04 dotfiles for coding-agent sandboxes, servers and an XFCE desktop over RDP, managed entirely by mise
MCP Hoarder 17.4k tok · · Q3