mikeyobrien/ralph-orchestrator
An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit mikeyobrien/ralph-orchestrator/.claude ./rig-ralph-orchestrator # 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.
$ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/code-assist .claude/skills/code-assist $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/code-task-generator .claude/skills/code-task-generator $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/evaluate-presets .claude/skills/evaluate-presets $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/find-code-tasks .claude/skills/find-code-tasks $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/pdd .claude/skills/pdd $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/playwriter .claude/skills/playwriter $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/pr-demo .claude/skills/pr-demo $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/ralph-tools .claude/skills/ralph-tools $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/release-bump .claude/skills/release-bump $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/review-pr .claude/skills/review-pr $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/test-driven-development .claude/skills/test-driven-development $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/tmux-terminal .claude/skills/tmux-terminal $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/tui-debug-in-pane .claude/skills/tui-debug-in-pane $ npx degit mikeyobrien/ralph-orchestrator/.claude/skills/tui-validate .claude/skills/tui-validate $ npx degit mikeyobrien/ralph-orchestrator/skills/ralph-docs .claude/skills/ralph-docs $ npx degit mikeyobrien/ralph-orchestrator/skills/ralph-hats .claude/skills/ralph-hats $ npx degit mikeyobrien/ralph-orchestrator/skills/ralph-loop .claude/skills/ralph-loop
$ curl -fsSL --create-dirs -o .claude/agents/code-assist.md https://raw.githubusercontent.com/mikeyobrien/ralph-orchestrator/main/.claude/agents/code-assist.md $ curl -fsSL --create-dirs -o .claude/agents/ralph-e2e-verifier.md https://raw.githubusercontent.com/mikeyobrien/ralph-orchestrator/main/.claude/agents/ralph-e2e-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/ralph-loop-runner.md https://raw.githubusercontent.com/mikeyobrien/ralph-orchestrator/main/.claude/agents/ralph-loop-runner.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 *)"
]
}
} Skills (17)
code-assistcode-task-generatorevaluate-presetsfind-code-taskspddplaywriterpr-demoralph-toolsrelease-bumpreview-prtest-driven-developmenttmux-terminaltui-debug-in-panetui-validateralph-docsralph-hatsralph-loop
Subagents (3)
| code-assist model: opus | Use this agent when implementing code tasks from task files, working through structured implementation plans, or executing code changes that follow the spec-to-implementation workflow. This agent foll |
| ralph-e2e-verifier model: opus | Use this agent when you need to run the Ralph orchestrator end-to-end test suite, analyze diagnostic outputs, and generate comprehensive reports of findings. This includes validating backend connectiv |
| ralph-loop-runner model: haiku | Use this agent when you need to execute a Ralph orchestration loop end-to-end and verify its completion. This includes testing prompts against the Ralph system, validating that orchestration completes |
Similar rigs
harshal2802/pdd-skill
A Practical Framework for Building with AI
Minimalist 1.0k tok ·
tasnimAlam/dot-files
vim ( neovim ), zsh, doom emacs, kitty, fish shell and other configuration files.
Pragmatist 110 tok ·
alondmnt/dotfiles
Claude Code configuration, skills, and dotfiles
Minimalist 1.2k tok ·
brobertsaz/claude-os
—
Minimalist 2.1k tok ·