bubbleShaker/claude-config
私の Claude Code 環境(~/.claude)の設定をバージョン管理する dotfiles リポジトリ
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http slack https://mcp.slack.com/sse $ npx degit bubbleShaker/claude-config/home/.claude ./rig-claude-config # 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 slack https://mcp.slack.com/sse $ npx degit bubbleShaker/claude-config/home/.claude/skills/collect-shorts .claude/skills/collect-shorts $ npx degit bubbleShaker/claude-config/home/.claude/skills/commit-push .claude/skills/commit-push $ npx degit bubbleShaker/claude-config/home/.claude/skills/csharp-best-practices .claude/skills/csharp-best-practices $ npx degit bubbleShaker/claude-config/home/.claude/skills/deploy-lambda .claude/skills/deploy-lambda $ npx degit bubbleShaker/claude-config/home/.claude/skills/dev-cycle .claude/skills/dev-cycle $ npx degit bubbleShaker/claude-config/home/.claude/skills/generate-video .claude/skills/generate-video $ npx degit bubbleShaker/claude-config/home/.claude/skills/hono-aws-lambda .claude/skills/hono-aws-lambda $ npx degit bubbleShaker/claude-config/home/.claude/skills/repo-publish .claude/skills/repo-publish $ npx degit bubbleShaker/claude-config/home/.claude/skills/upload-video .claude/skills/upload-video
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/bubbleShaker/claude-config/master/home/.claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/bubbleShaker/claude-config/master/home/.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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| Slack | remote · remote | 3.5k |
Skills (9)
collect-shortscommit-pushcsharp-best-practicesdeploy-lambdadev-cyclegenerate-videohono-aws-lambdarepo-publishupload-video
Subagents (2)
| researcher model: sonnet | 調査・探索の専任。新規プロジェクト着手前の技術調査、「何ができるか」の洗い出し、ライブラリ/API の比較、コードベースの広域把握が必要な時に使う。大量のファイル読み・Web 探索を独立コンテキストで行い、結論と research/ への md 要約を返す。実装はしない。 |
| reviewer model: opus | コード/差分のレビュー専任。実装が一区切りした時、PR を出す前、または「レビューして」と頼まれた時に使う。セキュリティ・クリーンアーキテクチャ・SOLID の観点で読み取り専用に検査し、指摘リストを返す。実装や修正は行わない。 |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| UserPromptSubmit | * | printf '%s\n' '<discipline-reminder>' '全作業は Issue 先行（実装・調査・設定・分析いずれも gh issue create してから着手）。' 'コードを書く前に方針と理由を説明し合意を得てから実装する（小さく刻む）。' 'レビューは reviewer サブエージェントに必ず委譲し、🔴must を解消してから PR。' '</discipline-reminder>' 2>/dev/null || true |
Similar rigs
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 ·
OMOCHInoHOSHI/dotfiles-claude
.claude
Pragmatist 293 tok ·
joaolozano-lendario/athena-os
A Claude Code Native System for Intelligent Workflow Architecture - Slash Commands for Smarter AI Workflows
Orchestrator 3.7k 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 ·