k-f-/dotfiles
dotfiles with Stow: Xresources, uxrvt, i3wm, emacs
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http github https://api.githubcopilot.com/mcp/ $ npx degit k-f-/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.
$ claude mcp add --transport http github https://api.githubcopilot.com/mcp/ $ npx degit k-f-/dotfiles/home/dot_claude/skills/legal .claude/skills/legal $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/k-f-/dotfiles/main/home/dot_claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/editor.md https://raw.githubusercontent.com/k-f-/dotfiles/main/home/dot_claude/agents/editor.md $ curl -fsSL --create-dirs -o .claude/agents/legal-judge.md https://raw.githubusercontent.com/k-f-/dotfiles/main/home/dot_claude/agents/legal-judge.md $ curl -fsSL --create-dirs -o .claude/agents/legal-researcher.md https://raw.githubusercontent.com/k-f-/dotfiles/main/home/dot_claude/agents/legal-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/plan-reviewer.md https://raw.githubusercontent.com/k-f-/dotfiles/main/home/dot_claude/agents/plan-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/synthesizer.md https://raw.githubusercontent.com/k-f-/dotfiles/main/home/dot_claude/agents/synthesizer.md $ curl -fsSL --create-dirs -o .claude/agents/writer.md https://raw.githubusercontent.com/k-f-/dotfiles/main/home/dot_claude/agents/writer.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 (1)
| server | source | est. tokens |
|---|---|---|
| GitHub MCP · "github" | remote · remote | 18.0k |
Skills (1)
Subagents (7)
| code-reviewer model: sonnet | Adversarial review of a diff, branch, PR, or recently edited files. Manual invocation only. |
| editor model: opus | Critiques existing prose: scores slop level 0–10, names AI-slop tells, proposes targeted edits with reasons. Use when the user asks to edit, tighten, de-slop, or critique a piece of writing they have |
| legal-judge model: opus | Adversarial vetting of legal research claims through one assigned lens: source-verification, jurisdiction, or currency. Launched as a three-judge panel by the /legal skill. Manual invocation OK with a |
| legal-researcher model: sonnet | Researches one assigned angle of a legal question with primary-source citations. Launched in parallel by the /legal skill. Manual invocation OK for a standalone research angle. |
| plan-reviewer model: sonnet | Reviews a finalized plan against the codebase it targets. Auto-invoked after ExitPlanMode. Manual invocation OK when reviewing a pasted plan or design doc. |
| synthesizer model: opus | Deep open-ended analysis combining agr archive search, file reads, and cross-source synthesis. Use for "have we decided this before", cost analysis, comparisons, summaries, and any question whose answ |
| writer model: opus | Drafts prose (essays, blog posts, shortform social posts, READMEs, memos) in Kyle's voice. Use when the user asks to write, draft, or compose prose. Do not use for code generation or commit messages. |
Similar rigs
junianwoo/claude-toad
One command. Your entire Claude Code setup. Done.
Pragmatist 18.7k tok · · Q15
HGInsights/claude-code-setup
Production-tested Claude Code harness configuration: hooks, skills, subagents, and automated review loops
Pragmatist 2.0k tok · · Q20
KhaiTrang1995/claude-code-structure
A ready-to-use Claude Code project scaffold — rules, commands, skills, agents, and hooks in one command.
Orchestrator 24.4k tok · · Q15
lee-to/ai-workspace
AI Workspace - Give your AI agents memory that spans across projects.
Pragmatist 19.7k tok · · Q0