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 jmigual/dotfiles/home/dot_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.
$ npx degit jmigual/dotfiles/home/dot_claude/skills/orchestrate .claude/skills/orchestrate $ npx degit jmigual/dotfiles/home/dot_claude/skills/ship .claude/skills/ship $ npx degit jmigual/dotfiles/home/dot_codex/skills/setup-serena .claude/skills/setup-serena
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/jmigual/dotfiles/master/home/dot_claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/jmigual/dotfiles/master/home/dot_claude/agents/coder.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/jmigual/dotfiles/master/home/dot_claude/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/jmigual/dotfiles/master/home/dot_claude/agents/tester.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 *)"
]
}
} Skills (3)
Subagents (4)
| architect model: opus | Use for designing implementation plans, breaking work into shippable steps, choosing where logic belongs, sequencing dependencies, and surfacing trade-offs. Read-mostly — never edits src/ or tests/. I |
| coder model: sonnet | Use to implement a feature from a spec, fix a bug, or apply changes the architect has already planned. Full edit access. Expects a concrete spec — if scope is vague or there is no plan for the task, r |
| reviewer model: opus | Use to review uncommitted changes, a specific file, or recently completed work for correctness, simplicity, boundary hygiene, and invariant safety. Read-only. Invoke AFTER the coder finishes, BEFORE w |
| tester model: sonnet | Use to write or extend unit/integration tests, fill a coverage gap the reviewer surfaced, or verify a change by running the test suite and reporting results. Edit access, but restrict changes to test |
Similar rigs
Altafhossain72/claude-ship-pipeline
/ship: a 5-agent Claude Code pipeline (planner, coder, tester, reviewer, documenter) that ends with a reviewed local commit on a feature branch
Orchestrator 349 tok · · Q0
AegeanWorks/AIKit
Crash-resilient governance and delivery gates for AI coding agents: versioned task ledger, commit-level verification, secret scanning and per-project gates. Free for personal use under AL-1.1; commercial use under ACL-1.0.
Orchestrator 4.2k tok · · Q23
bpstack/harness
A reusable foundation for AI projects: rules, agents, templates, and commands.
Pragmatist 3.5k tok · · Q5
BillDX/spicy-to-dark-factory-starter
Workshop starter for 'From Spicy Autocomplete to Dark Factory: Agentic Coding in Practice' — a FastAPI mini-app with a full Claude Code harness (agents, slash commands, hooks, sandbox settings) and self-paced exercises.
Orchestrator 706 tok · · Q18