LuckJMG/.dotfiles
Personal development environment configuration for Linux with automated installation.
stack: Shell
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 LuckJMG/.dotfiles/agents ./rig-.dotfiles/agents 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 LuckJMG/.dotfiles/agents/skills/audit .claude/skills/audit $ npx degit LuckJMG/.dotfiles/agents/skills/data-storytelling .claude/skills/data-storytelling $ npx degit LuckJMG/.dotfiles/agents/skills/document-writing .claude/skills/document-writing $ npx degit LuckJMG/.dotfiles/agents/skills/git-commit .claude/skills/git-commit $ npx degit LuckJMG/.dotfiles/agents/skills/just .claude/skills/just $ npx degit LuckJMG/.dotfiles/agents/skills/orthodox-cpp .claude/skills/orthodox-cpp $ npx degit LuckJMG/.dotfiles/agents/skills/ponytail .claude/skills/ponytail $ npx degit LuckJMG/.dotfiles/agents/skills/project-docs .claude/skills/project-docs $ npx degit LuckJMG/.dotfiles/agents/skills/simple-english .claude/skills/simple-english
$ curl -fsSL --create-dirs -o .claude/agents/overengineering-audit.md https://raw.githubusercontent.com/LuckJMG/.dotfiles/main/agents/commands/overengineering-audit.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-audit.md https://raw.githubusercontent.com/LuckJMG/.dotfiles/main/agents/commands/refactor-audit.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 (9)
Subagents (2)
| overengineering-audit | Scan code for over-engineering, report what to cut, then apply the cuts you approve. Optional scope argument. |
| refactor-audit | Scan code for refactors and locality of behaviour, report, then apply the findings you approve. Optional scope argument. |
Similar rigs
mcp-box/mcpscore-plugin
Audit and fix the MCP server you're building from Claude Code, Codex or Cursor. Ask your agent to audit it and get a cited score from mcpscore, with fixes applied in your own code.
Minimalist 906 tok · · Q0
george-e-shaw-iv/dotclaude
Claude dotfiles with a script that merges common configuration with OS-specific configuration.
Minimalist 788 tok · · Q0
Miri-Labs/MoMo-Agent
24/7 Self-Hosted Personal Agent for Apple Watch, iPhone & Mac — $0 On-Device CoreML ASR, Obsidian-Style Memory Vault, Tailscale & Codex/Claude/Antigravity OAuth
Pragmatist 3.1k tok · · Q0
quisbaum-prog/occam
Occam's razor for Claude Code and Codex: a 30-line rule set. Benchmarks vs base: 51-55% lower estimated task cost on Opus/Sonnet 5.5 max with more tests passed. 8.3% fewer tokens in a Sol 6.1 max pilot. Raw data, Docker setup and comparison
Minimalist 67 tok · · Q0