agentrigs
+ submit rig
~ / rigs / HumanDealer / vibeproof

HumanDealer/vibeproof

Vibe-code anything. Ship like a senior. A drop-in rulebook + skills that turn any AI coding agent (Codex, Claude Code, Cursor) into a disciplined senior engineer — built for domain experts who build with AI.

↗ GitHub ★ 2 MIT updated 4mo ago project Claude CodeCodexCursor
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

Copy this rig

# review before running: this installs third-party code
$ npx degit HumanDealer/vibeproof/skills ./rig-vibeproof/skills
$ npx degit HumanDealer/vibeproof/hooks ./rig-vibeproof/hooks

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 HumanDealer/vibeproof/skills/code-review .claude/skills/code-review
$ npx degit HumanDealer/vibeproof/skills/debug-root-cause .claude/skills/debug-root-cause
$ npx degit HumanDealer/vibeproof/skills/plan .claude/skills/plan
$ npx degit HumanDealer/vibeproof/skills/save-learning .claude/skills/save-learning
$ npx degit HumanDealer/vibeproof/skills/ship .claude/skills/ship
$ npx degit HumanDealer/vibeproof/skills/spec .claude/skills/spec
$ npx degit HumanDealer/vibeproof/skills/tdd .claude/skills/tdd

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)

code-reviewdebug-root-causeplansave-learningshipspectdd

Similar rigs

brunella328/andon
Andon — a human-in-the-loop SDLC for AI coding agents. Pull the cord, stop the line: five-phase governance + craft skills as a Claude Code plugin（人與 AI 協作的產品開發流程）
★ 0 project Claude Code 14 skills today
Skill Collector 597 tok ·
selmakcby/claude-agents-skills
Multi-Agent Claude Code setup — 4 uzman ajan (planner · ui-agent · builder · reviewer) + skills + Next.js demo projesi. YouTube Bölüm 1 video materyalleri.
★ 136 collection Claude Code 6 skills 8 agents 6mo ago
Orchestrator 1.5k tok ·
rness-dev/rness
One source of truth for every AI coding agent. The standards, decisions, specs and plans of your organization, written into the AGENTS.md of every repository. Claude Code, Codex, Cursor and GitHub Copilot already read it.
★ 2 project Claude CodeCodex 1 mcp 5 skills 4 hooks 2d ago
Automator 5.6k tok ·
csvenke/dotfiles
❄️ My dotfiles
★ 1 setup Codex 2 mcp 4 skills 2mo ago
Pragmatist 4.0k tok ·
copied ✓