S-jooyoung/oh-my-joy
AI says it's done. OMJ makes it prove it. One workflow for Claude Code and Codex: interview → plan with an independent critique → approve once → build, review, and verify with recorded evidence. Figma-to-code with real browser checks built
field: Developer tools workflow: Frontend & designPlanning & specsPR / code reviewCI/CD & deployGit & commits runs claude in CI
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 S-jooyoung/oh-my-joy/.claude ./rig-oh-my-joy # 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 S-jooyoung/oh-my-joy/.agents/skills/release-checklist .claude/skills/release-checklist $ npx degit S-jooyoung/oh-my-joy/.agents/skills/release .claude/skills/release $ npx degit S-jooyoung/oh-my-joy/skills/critic .claude/skills/critic $ npx degit S-jooyoung/oh-my-joy/skills/deep-interview .claude/skills/deep-interview $ npx degit S-jooyoung/oh-my-joy/skills/design-qa .claude/skills/design-qa $ npx degit S-jooyoung/oh-my-joy/skills/fix .claude/skills/fix $ npx degit S-jooyoung/oh-my-joy/skills/frontend-fundamentals .claude/skills/frontend-fundamentals $ npx degit S-jooyoung/oh-my-joy/skills/implementer .claude/skills/implementer $ npx degit S-jooyoung/oh-my-joy/skills/ralplan .claude/skills/ralplan $ npx degit S-jooyoung/oh-my-joy/skills/review .claude/skills/review $ npx degit S-jooyoung/oh-my-joy/skills/setup .claude/skills/setup $ npx degit S-jooyoung/oh-my-joy/skills/ship .claude/skills/ship $ npx degit S-jooyoung/oh-my-joy/skills/spec .claude/skills/spec $ npx degit S-jooyoung/oh-my-joy/skills/sync .claude/skills/sync $ npx degit S-jooyoung/oh-my-joy/skills/ultragoal .claude/skills/ultragoal $ npx degit S-jooyoung/oh-my-joy/skills/verify .claude/skills/verify
$ curl -fsSL --create-dirs -o .claude/agents/critic.md https://raw.githubusercontent.com/S-jooyoung/oh-my-joy/main/agents/critic.md $ curl -fsSL --create-dirs -o .claude/agents/design-qa.md https://raw.githubusercontent.com/S-jooyoung/oh-my-joy/main/agents/design-qa.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/S-jooyoung/oh-my-joy/main/agents/implementer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (16)
release-checklistreleasecriticdeep-interviewdesign-qafixfrontend-fundamentalsimplementerralplanreviewsetupshipspecsyncultragoalverify
Subagents (3)
| critic | Read-only reviewer that ralplan, ultragoal, and review spawn in a fresh context — architect lens (structure, scope, alternatives, hidden root causes) or critic lens (executability and acceptance proof |
| design-qa | Mechanical quality gate after FE implementation — checks (never fixes) typecheck, lint, token hardcoding, Figma fidelity, a11y basics, and (when the project declares them) Story existence and i18n key |
| implementer | Executor for one goal from a user-approved OMJ ralplan — frontend mode (uSpec sections, Figma nodes, a route) or general mode (objective, acceptance criteria, verification commands). Use only under th |
Slash commands (11)
/release/deep-interview/fix/ralplan/review/setup/ship/spec/sync/ultragoal/verify
Similar rigs
romerma/mstack
Rigorous, verifiable agent workflows for Claude Code: gates that are code, not prose
Orchestrator 1.6k tok · · Q0
CMaintz/cmaintz-skills
Claude Code skills and hooks for the Foundry engineering gate — pre-PR review and structural-smell habits.
Skill Collector 3.3k tok · · Q0
JuuuuHong/kiro-bridge
Claude Code plugin that bridges to Kiro CLI — structured context handoff, spec-driven delegation, ACP-ready transport
Minimalist 217 tok · · Q0
SavenkoSy/sin-flow
Ticket-to-PR flow for a live codebase, as a Claude Code plugin: setup, sync, ingest, plan, exec, review and learning stages.
Orchestrator 1.4k tok · · Q3