RascalTwo/ai-setup
Agent-agnostic AI coding setup (Claude Code + Codex): rules, skills, r2-sdlc pipeline, deterministic installer.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit RascalTwo/ai-setup/subagents/.claude ./rig-ai-setup # 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 RascalTwo/ai-setup/skills/ai-setup-audit .claude/skills/ai-setup-audit $ npx degit RascalTwo/ai-setup/skills/analyze-github-workflow-failure .claude/skills/analyze-github-workflow-failure $ npx degit RascalTwo/ai-setup/skills/aws-creds .claude/skills/aws-creds $ npx degit RascalTwo/ai-setup/skills/browser-capture .claude/skills/browser-capture $ npx degit RascalTwo/ai-setup/skills/confluence-editor .claude/skills/confluence-editor $ npx degit RascalTwo/ai-setup/skills/delegate-to-codex .claude/skills/delegate-to-codex $ npx degit RascalTwo/ai-setup/skills/diagnose-azure-container-app .claude/skills/diagnose-azure-container-app $ npx degit RascalTwo/ai-setup/skills/diagnose-terraform-unknown-error .claude/skills/diagnose-terraform-unknown-error $ npx degit RascalTwo/ai-setup/skills/documandments .claude/skills/documandments $ npx degit RascalTwo/ai-setup/skills/end-session .claude/skills/end-session $ npx degit RascalTwo/ai-setup/skills/extract-gdrive-transcript .claude/skills/extract-gdrive-transcript $ npx degit RascalTwo/ai-setup/skills/extract-video-subtitles .claude/skills/extract-video-subtitles $ npx degit RascalTwo/ai-setup/skills/github-attach-media .claude/skills/github-attach-media $ npx degit RascalTwo/ai-setup/skills/grill-me-viz .claude/skills/grill-me-viz $ npx degit RascalTwo/ai-setup/skills/okta-api .claude/skills/okta-api $ npx degit RascalTwo/ai-setup/skills/omnissa-horizon-vdi .claude/skills/omnissa-horizon-vdi $ npx degit RascalTwo/ai-setup/skills/ping-api .claude/skills/ping-api $ npx degit RascalTwo/ai-setup/skills/plus-ultra .claude/skills/plus-ultra $ npx degit RascalTwo/ai-setup/skills/port-terraform-provider-to-ansible .claude/skills/port-terraform-provider-to-ansible $ npx degit RascalTwo/ai-setup/skills/port-terraform-provider-to-k8s-operator .claude/skills/port-terraform-provider-to-k8s-operator $ npx degit RascalTwo/ai-setup/skills/port-terraform-provider-to-powershell-dsc .claude/skills/port-terraform-provider-to-powershell-dsc $ npx degit RascalTwo/ai-setup/skills/pr-split .claude/skills/pr-split $ npx degit RascalTwo/ai-setup/skills/pr-viz .claude/skills/pr-viz $ npx degit RascalTwo/ai-setup/skills/publish-markdown-to-confluence .claude/skills/publish-markdown-to-confluence $ npx degit RascalTwo/ai-setup/skills/r2-gauntlet .claude/skills/r2-gauntlet $ npx degit RascalTwo/ai-setup/skills/r2-handoff .claude/skills/r2-handoff $ npx degit RascalTwo/ai-setup/skills/r2-pr .claude/skills/r2-pr $ npx degit RascalTwo/ai-setup/skills/r2-sdlc-documentation-philosophy .claude/skills/r2-sdlc-documentation-philosophy $ npx degit RascalTwo/ai-setup/skills/r2-sdlc .claude/skills/r2-sdlc $ npx degit RascalTwo/ai-setup/skills/r2-testing-paradigm .claude/skills/r2-testing-paradigm $ npx degit RascalTwo/ai-setup/skills/read-image-locally .claude/skills/read-image-locally $ npx degit RascalTwo/ai-setup/skills/read-video-locally .claude/skills/read-video-locally $ npx degit RascalTwo/ai-setup/skills/render-image-in-terminal .claude/skills/render-image-in-terminal $ npx degit RascalTwo/ai-setup/skills/reorder-github-project-board-by-depth .claude/skills/reorder-github-project-board-by-depth $ npx degit RascalTwo/ai-setup/skills/slack-in-browser .claude/skills/slack-in-browser $ npx degit RascalTwo/ai-setup/skills/spawn-herdr-tab .claude/skills/spawn-herdr-tab $ npx degit RascalTwo/ai-setup/skills/steelman .claude/skills/steelman $ npx degit RascalTwo/ai-setup/skills/sync-webex-to-google-calendar .claude/skills/sync-webex-to-google-calendar $ npx degit RascalTwo/ai-setup/skills/timeline-studio-tasks .claude/skills/timeline-studio-tasks $ npx degit RascalTwo/ai-setup/skills/tldraw-canvas .claude/skills/tldraw-canvas
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/RascalTwo/ai-setup/main/subagents/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/docs-currency-reviewer.md https://raw.githubusercontent.com/RascalTwo/ai-setup/main/subagents/.claude/agents/docs-currency-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/fidelity-reviewer.md https://raw.githubusercontent.com/RascalTwo/ai-setup/main/subagents/.claude/agents/fidelity-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/qa-validator.md https://raw.githubusercontent.com/RascalTwo/ai-setup/main/subagents/.claude/agents/qa-validator.md $ curl -fsSL --create-dirs -o .claude/agents/reuse-reviewer.md https://raw.githubusercontent.com/RascalTwo/ai-setup/main/subagents/.claude/agents/reuse-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/RascalTwo/ai-setup/main/subagents/.claude/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-reviewer.md https://raw.githubusercontent.com/RascalTwo/ai-setup/main/subagents/.claude/agents/test-reviewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (45)
ai-setup-auditanalyze-github-workflow-failureaws-credsbrowser-captureconfluence-editordelegate-to-codexdiagnose-azure-container-appdiagnose-terraform-unknown-errordocumandmentsend-sessionextract-gdrive-transcriptextract-video-subtitlesgithub-attach-mediagrill-me-vizokta-apiomnissa-horizon-vdiping-apiplus-ultraport-terraform-provider-to-ansibleport-terraform-provider-to-k8s-operatorport-terraform-provider-to-powershell-dscpr-splitpr-vizpublish-markdown-to-confluencer2-gauntletr2-handoffr2-prr2-sdlc-documentation-philosophyr2-sdlcr2-testing-paradigmread-image-locallyread-video-locallyrender-image-in-terminalreorder-github-project-board-by-depthslack-in-browserspawn-herdr-tabsteelmansync-webex-to-google-calendartimeline-studio-taskstldraw-canvastranscribe-mediatrigger-github-deployui-narrationvizwait-for-github-workflow
Subagents (7)
| code-reviewer | Tier-2 quality reviewer for the r2-sdlc pipeline. Reviews production code changes for quality — simplicity, adherence to nearby style idioms, and Goldilocks documentation (inline comments + doc string |
| docs-currency-reviewer | Tier-2 quality reviewer for the r2-sdlc pipeline. Reviews project-level markdown (READMEs, docs/, inline .md files) for staleness after code changes. Flags docs that reference renamed/removed things, |
| fidelity-reviewer | Tier-1 correctness reviewer for the r2-sdlc pipeline. Checks whether the implementation matches the persisted design document — touched the files it was supposed to, implemented the planned behaviors, |
| qa-validator | Tier-1 correctness reviewer for the r2-sdlc pipeline. Validates whether the implementation actually solves the original user ask (from understood.md). Exercises the feature behaviorally — runs command |
| reuse-reviewer | Tier-2 quality reviewer for the r2-sdlc pipeline. Reviews the diff for "don't reinvent the wheel" concerns — hand-rolled code that already exists in the repo, in the language standard library, or in a |
| security-reviewer | Tier-2 quality reviewer for the r2-sdlc pipeline. Reviews the diff for security issues — injection risks, hardcoded secrets, insecure defaults, auth/authz bypasses, unsafe deserialization, crypto misu |
| test-reviewer | Tier-2 quality reviewer for the r2-sdlc pipeline. Reviews added/modified tests against the r2-testing-paradigm skill's reference/reviewing.md rubric. Does NOT check implementation code, design fidelit |
Similar rigs
flsteven87/claude-code-setup
Personal Claude Code configuration — settings, hooks, skills, commands, rules
YOLO Cowboy 6.3k tok ·
Joan266/claude-dotfiles
—
Pragmatist 831 tok ·
Iski08/dotclaude
Multi-agent config for Claude Code with specialized agents and templates to speed code review, refactoring, security audits, tech-lead guidance, and UX evaluations across CI pipelines. 🐙
Orchestrator 677 tok ·
peterkimpro/claude-code-powerpack
Drop-in Claude Code config for efficient AI-assisted development. Includes CLAUDE.md template, permission allowlist, agents, skills, and memory system.
Pragmatist 4.4k tok ·