nagamine-git/dotfiles
Chezmoi-managed dotfiles across 3 machines (Arch Linux — CachyOS/EndeavourOS — & macOS). Hyprland/Wayland, Zsh + Starship, Neovim, Ghostty, tmux, fcitx5, waybar
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 nagamine-git/dotfiles/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 nagamine-git/dotfiles/dot_claude/skills/daily-focus .claude/skills/daily-focus $ npx degit nagamine-git/dotfiles/dot_claude/skills/dev-radar .claude/skills/dev-radar $ npx degit nagamine-git/dotfiles/dot_claude/skills/session-title-refresh .claude/skills/session-title-refresh
$ curl -fsSL --create-dirs -o .claude/agents/deep-specialist.md https://raw.githubusercontent.com/nagamine-git/dotfiles/main/dot_claude/agents/deep-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/nagamine-git/dotfiles/main/dot_claude/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/nagamine-git/dotfiles/main/dot_claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/nagamine-git/dotfiles/main/dot_claude/agents/reviewer.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 (3)
Subagents (4)
| deep-specialist model: claude-fable-5-1 | Use proactively for ambiguous design, security or data-loss risks, cross-system root causes, or two failed fixes. Return a focused decision and verification plan. |
| implementer model: opus | Implements a bounded change in specified files and returns verification evidence. |
| researcher model: sonnet | Collects focused code and official documentation evidence without modifying files or executing code. |
| reviewer model: opus | Reviews a supplied diff and test evidence for concrete correctness and security regressions without executing code. |
Similar rigs
OMOCHInoHOSHI/dotfiles-claude
.claude
Pragmatist 293 tok ·
homeofe/improvements
Portable, LLM-agnostic framework for multi-model AI workflows: model routing, structured agent handoff (AAHP), and a phased agent pipeline. MIT.
Orchestrator 1.4k tok ·
Saba-Var/claude-ward
A read-only tripwire that watches Claude Code's local config and reports suspicious changes.
Pragmatist 1.8k tok ·
jaqubowsky/fleet
Runs Claude Code and pi agents in parallel on your Mac, one Docker sandbox per issue. A host agent hands out the work, watches every sandbox and brings back tested, reviewed pull requests.
Minimalist 341 tok ·