agentrigs
+ submit rig
~ / rigs / haoblackj / dotfiles

haoblackj/dotfiles

haoblackj's dotfiles

↗ GitHub ★ 0 no license updated today personal setup Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~3.4k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit haoblackj/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.

$ curl -fsSL --create-dirs -o .claude/agents/off-the-shelf-finder.md https://raw.githubusercontent.com/haoblackj/dotfiles/main/dot_claude/agents/off-the-shelf-finder.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/haoblackj/dotfiles/main/dot_claude/agents/researcher.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 *)"
    ]
  }
}

Subagents (2)

off-the-shelf-finder
model: sonnet
「これを自作する前に、既製品で置き換えられないか」を調べる役。対象の機能（スクリプト、フック、運用手順、設計案）を渡すと、公式機能・公式プラグイン・現行でメンテナンスされているコミュニティ製品のうち、その機能を「入れるだけで」満たすものを探し、有無と根拠を返す。何かを自作しそうになったとき、設計に入る前に必ず切る。
researcher
model: sonnet
外部の一次情報（公式ドキュメント、公式リポジトリ、実装者本人の発言、コミュニティで確立した実践）を調べ、結論と出典を返す調査役。設計や選択肢を出す前の裏取り、仕様や挙動の確認、ヘビーユーザの慣行調査に使う。生の文書を親の文脈へ流し込まないために切る。

Hooks (1)

eventmatcherruns
PostToolUseEdit|Write|MultiEdit~/.claude/hooks/chezmoi-auto-apply.sh

Permissions

deny (0)
—
ask (0)
—
allow (1)
Bash(chezmoi apply *)

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.
★ 12 project Claude CodeCodex 3 agents today
Minimalist 341 tok ·
ychampion/claude-self-learning
A Claude Code self learning plugin that autonomously researches any technology and generates reusable SKILL.md files with installation guides, code examples, and best practices.
★ 3 project Claude Code 1 skills 2 agents 8mo ago
Pragmatist 252 tok ·
syntax-syndicate/cc-solo-dev-template
Claude Code Solo Development Workflow Template - Ship like a team of 10, working solo with AI agents
★ 0 project Claude Code 3 agents 10mo ago
Minimalist 660 tok ·
OMOCHInoHOSHI/dotfiles-claude
.claude
★ 1 setup Claude Code 4 agents 3mo ago
Pragmatist 293 tok ·
copied ✓