agentrigs
+ submit rig
~ / rigs / mbchavez27 / dotfiles

mbchavez27/dotfiles

@mbchavezz on ig

↗ GitHub ★ 1 no license updated 4d ago personal setup Codex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.1k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/mbchavez27/dotfiles

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 mbchavez27/dotfiles/opencode/skills/git-conventional-commits .claude/skills/git-conventional-commits
$ npx degit mbchavez27/dotfiles/opencode/skills/lead-frontend-engineer .claude/skills/lead-frontend-engineer
$ npx degit mbchavez27/dotfiles/opencode/skills/lead-software-engineer .claude/skills/lead-software-engineer
$ npx degit mbchavez27/dotfiles/opencode/skills/nlp-ml-research-coder .claude/skills/nlp-ml-research-coder
$ npx degit mbchavez27/dotfiles/opencode/skills/research-writing-coach .claude/skills/research-writing-coach
$ npx degit mbchavez27/dotfiles/opencode/skills/scrum-master .claude/skills/scrum-master
$ npx degit mbchavez27/dotfiles/opencode/skills/sprint-planner .claude/skills/sprint-planner

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 *)"
    ]
  }
}

Skills (7)

git-conventional-commitslead-frontend-engineerlead-software-engineernlp-ml-research-coderresearch-writing-coachscrum-mastersprint-planner

Similar rigs

thenickz/agent-dotfiles
AI agent dotfiles: templates + portable skills (persistent memory, architecture, git, github) for Claude Code, opencode, and Codex
★ 0 setup Codex 4 skills 2mo ago
Minimalist 1.7k tok ·
aakashg/pm-claude-code-setup
Ready-to-use CLAUDE.md and starter skill for product managers using Claude Code.
★ 160 setup Claude Code 6 skills 7mo ago
Pragmatist 818 tok ·
tronghieu/agent-skills
Method-driven agent skills for knowledge work: strategy, research, critical thinking, data analysis, docs, slides. Works with Claude Code, Codex, Cursor and any agentskills.io-compatible agent.
★ 72 collection Claude CodeCodex 19 skills 9d ago
Skill Collector 1.9k tok ·
hamzafarooq/claude-code-starter
—
★ 145 project Claude CodeCodex 2 mcp 53 skills 10 agents 26d ago
Orchestrator 18.6k tok ·
copied ✓