cmichels-engineering/claude-config
Portable Claude Code environment — settings, commands, agents, hooks, and project memory
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 cmichels-engineering/claude-config/agents ./rig-claude-config/agents $ npx degit cmichels-engineering/claude-config/commands ./rig-claude-config/commands $ npx degit cmichels-engineering/claude-config/skills ./rig-claude-config/skills $ npx degit cmichels-engineering/claude-config/hooks ./rig-claude-config/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 cmichels-engineering/claude-config/skills/security-review .claude/skills/security-review $ curl -fsSL --create-dirs -o .claude/agents/pr-architect-review.md https://raw.githubusercontent.com/cmichels-engineering/claude-config/dev/agents/pr-architect-review.md $ curl -fsSL --create-dirs -o .claude/agents/pr-code-review.md https://raw.githubusercontent.com/cmichels-engineering/claude-config/dev/agents/pr-code-review.md $ curl -fsSL --create-dirs -o .claude/agents/pr-security-scan.md https://raw.githubusercontent.com/cmichels-engineering/claude-config/dev/agents/pr-security-scan.md $ curl -fsSL --create-dirs -o .claude/agents/pr-style-check.md https://raw.githubusercontent.com/cmichels-engineering/claude-config/dev/agents/pr-style-check.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 (1)
Subagents (4)
| pr-architect-review model: sonnet | Performs architecture and design review for pull requests. Evaluates design patterns (incl. SOLID), modularity, scalability, API design, data models, integration points, and technical debt. Invoked by |
| pr-code-review model: sonnet | Performs code quality review for pull requests. Analyzes logic correctness, CLAUDE.md compliance, code clarity, resource management, concurrency, and performance. Invoked by /review-pr-team as the cod |
| pr-security-scan model: sonnet | Performs security and error-handling review for pull requests. Covers injection attacks, authentication/authorization, data exposure, cryptography, OWASP Top 10, and error-handling failures (silent fa |
| pr-style-check model: sonnet | Performs test coverage and code style review for pull requests. Covers test coverage gaps, test quality, naming conventions, formatting, documentation, and project pattern consistency. Findings are ad |
Slash commands (12)
/code-quality/grill-me/jira-context/k-pr-watch/k-quick-pr/k-resume/k-suspend/review-pr-team/screenshot/ship-it/teams-chat/worktree
Similar rigs
lamngockhuong/termote
Self-hosted PWA to control Claude Code, Codex, GitHub Copilot or any terminal from your phone or desktop. Single Go binary streaming tmux/psmux/Herdr sessions to xterm.js, native or in a container.
Pragmatist 20.9k tok ·
crewship-ai/crewship
Self-hosted runtime for AI coding agents. Real Linux containers, your hardware, your keys, your data.
Pragmatist 3.1k tok ·
thewaltero/mythos-router
The leaked Anthropic reasoning protocol. Running locally. Zero-drift coding with Strict Write Discipline and adaptive Claude Opus 5 thinking. Mythos
Minimalist 2.2k tok ·
ker0olos/ignite
The only AI coding app you'll need. Run agents in parallel. Hand off tasks that come back as pull requests. Draw on screenshots to show exactly what's wrong. Native macOS, sandboxed by default.
Pragmatist 16.8k tok ·