~ / rigs / iguchi1124 / dotfiles

iguchi1124/dotfiles

No description.

↗ GitHub ★ 3 no license updated 7d ago personal setup Claude CodeCodex
stack: PythonShell
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.0k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 3/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit iguchi1124/dotfiles/.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 iguchi1124/dotfiles/.agents/skills/claude-setup .claude/skills/claude-setup
$ npx degit iguchi1124/dotfiles/.agents/skills/codex-setup .claude/skills/codex-setup
$ npx degit iguchi1124/dotfiles/.agents/skills/coordinator .claude/skills/coordinator
$ npx degit iguchi1124/dotfiles/.agents/skills/engineer .claude/skills/engineer
$ curl -fsSL --create-dirs -o .claude/agents/evaluator.md https://raw.githubusercontent.com/iguchi1124/dotfiles/main/.claude/agents/evaluator.md
$ curl -fsSL --create-dirs -o .claude/agents/generator.md https://raw.githubusercontent.com/iguchi1124/dotfiles/main/.claude/agents/generator.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/iguchi1124/dotfiles/main/.claude/agents/planner.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 (4)

Subagents (3)

evaluator
model: claude-fable-5-2
Checks changes against the plan, the conventions, and the spec, and returns PASS/FAIL with the findings. Writes no code. Use as the check on generator's output, or for "review this" / "confirm this is
generator
model: claude-opus-5-5
Implements a plan or ticket — code, tests, docs — and gets lint and tests passing. Use as the executor for a planner's plan, or to fix evaluator or reviewer findings. Handles "implement this", "write
planner
model: claude-fable-5-2
Breaks a task into verifiable steps and returns an implementation plan. Writes no code. Use for "plan this", "how should we proceed", "design this", or as the stage before generator. Suits vague reque

Similar rigs

copied ✓