ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~41.2k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Context hog · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add chrome-devtools -- npx chrome-devtools-mcp@latest $ claude mcp add playwright -- npx @playwright/mcp@latest $ claude mcp add --transport http github https://api.githubcopilot.com/mcp/ $ claude mcp add --transport http notion https://mcp.notion.com/mcp $ npx degit tearoom6/dotfiles/.claude ./rig-dotfiles # 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 chrome-devtools -- npx chrome-devtools-mcp@latest $ claude mcp add playwright -- npx @playwright/mcp@latest $ claude mcp add --transport http github https://api.githubcopilot.com/mcp/ $ claude mcp add --transport http notion https://mcp.notion.com/mcp
$ curl -fsSL --create-dirs -o .claude/agents/create-pr-ja.md https://raw.githubusercontent.com/tearoom6/dotfiles/master/.claude/agents/create-pr-ja.md $ curl -fsSL --create-dirs -o .claude/agents/spec-to-implementation-planner.md https://raw.githubusercontent.com/tearoom6/dotfiles/master/.claude/agents/spec-to-implementation-planner.md
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 (4)
| server | source | est. tokens |
|---|---|---|
| Chrome DevTools MCP · "chrome-devtools" | npm | 9.0k |
| Playwright MCP · "playwright" | npm | 7.5k |
| GitHub MCP · "github" | remote · remote | 18.0k |
| Notion | remote · remote | 6.0k |
Subagents (2)
| create-pr-ja model: sonnet | Use this agent when you need to push code changes to a remote repository and create a draft pull request with an English title and Japanese body. This agent handles the complete workflow from pushing |
| spec-to-implementation-planner model: opus | Use this agent when you need to create a detailed implementation plan based on specification documents, requirements, or design documents. This agent analyzes specifications and produces structured, a |
Slash commands (1)
/create-pr-ja
Similar rigs
aws-samples/sample-specship
Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation, and anti-slop quality gates. Packaged as a Kiro Power.
Pragmatist 16.5k tok · · Q0
hacker1db/Dotfiles
My .Dotfiles, Tmux, nvim, zshrc and other fun things!
Pragmatist 27.5k tok · · Q5
adriamontoto/.dotfiles
🐧 These are my dotfiles.
Pragmatist 15.0k tok · · Q0
firu-daniel/autonomous-sdlc-harness
An autonomous software-delivery harness: a task prompt becomes a planned, implemented, reviewed and pushed branch, driven by a fleet of single-purpose agents.
Pragmatist 16.5k tok · · Q15