agentrigs
+ submit rig
~ / rigs / shuymn / dotfiles

shuymn/dotfiles

my dotfiles.

↗ GitHub ★ 1 mit updated 7d ago personal setup Claude CodeCodex
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~1.4k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

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

$ curl -fsSL --create-dirs -o .claude/agents/fable-advisor.md https://raw.githubusercontent.com/shuymn/dotfiles/main/home/dot_claude/agents/fable-advisor.md
$ curl -fsSL --create-dirs -o .claude/agents/opus-worker.md https://raw.githubusercontent.com/shuymn/dotfiles/main/home/dot_claude/agents/opus-worker.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)

fable-advisor
model: claude-fable-5-1
Resolves focused, high-impact architecture or debugging uncertainty
opus-worker
model: claude-opus-5
Implements and verifies bounded tasks delegated by an orchestrator

Similar rigs

DeL-TaiseiOzaki/claude-code-orchestra
—
★ 199 project Claude CodeCodex 15 skills 4 agents 9 hooks 19d ago
YOLO Cowboy 6.6k tok ·
MindFortressInc/fable-approved-claude-config
Reeve CC Config — public Claude Code config: PRlaunch pre-PR quality pipeline with per-gate evidence ledger, Deep Review v6.9, outcome eval, babysit v3 PR sweeper, skillify repo->skill-library builder, safety-hook test suite.
★ 3 setup Claude Code 27 skills 1 agents 1d ago
Skill Collector 1.9k tok ·
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
★ 217k collection Claude CodeCursor 1 skills 6mo ago
Minimalist 723 tok ·
shareAI-lab/learn-claude-code
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
★ 78.0k project Claude Code 4 skills 11d ago
Minimalist 156 tok ·
copied ✓