CloudAI-X/claude-workflow-v2
Universal Claude Code workflow plugin with agents, skills, hooks, and commands
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 CloudAI-X/claude-workflow-v2/agents ./rig-claude-workflow-v2/agents $ npx degit CloudAI-X/claude-workflow-v2/commands ./rig-claude-workflow-v2/commands $ npx degit CloudAI-X/claude-workflow-v2/skills ./rig-claude-workflow-v2/skills $ npx degit CloudAI-X/claude-workflow-v2/hooks ./rig-claude-workflow-v2/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 CloudAI-X/claude-workflow-v2/skills/analyzing-projects .claude/skills/analyzing-projects $ npx degit CloudAI-X/claude-workflow-v2/skills/convex-backend .claude/skills/convex-backend $ npx degit CloudAI-X/claude-workflow-v2/skills/database-design .claude/skills/database-design $ npx degit CloudAI-X/claude-workflow-v2/skills/designing-apis .claude/skills/designing-apis $ npx degit CloudAI-X/claude-workflow-v2/skills/designing-architecture .claude/skills/designing-architecture $ npx degit CloudAI-X/claude-workflow-v2/skills/designing-tests .claude/skills/designing-tests $ npx degit CloudAI-X/claude-workflow-v2/skills/devops-infrastructure .claude/skills/devops-infrastructure $ npx degit CloudAI-X/claude-workflow-v2/skills/error-handling .claude/skills/error-handling $ npx degit CloudAI-X/claude-workflow-v2/skills/managing-git .claude/skills/managing-git $ npx degit CloudAI-X/claude-workflow-v2/skills/optimizing-performance .claude/skills/optimizing-performance $ npx degit CloudAI-X/claude-workflow-v2/skills/parallel-execution .claude/skills/parallel-execution $ npx degit CloudAI-X/claude-workflow-v2/skills/security-patterns .claude/skills/security-patterns $ npx degit CloudAI-X/claude-workflow-v2/skills/vercel-react-best-practices .claude/skills/vercel-react-best-practices $ npx degit CloudAI-X/claude-workflow-v2/skills/web-design-guidelines .claude/skills/web-design-guidelines
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/CloudAI-X/claude-workflow-v2/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/CloudAI-X/claude-workflow-v2/main/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/docs-writer.md https://raw.githubusercontent.com/CloudAI-X/claude-workflow-v2/main/agents/docs-writer.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/CloudAI-X/claude-workflow-v2/main/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/refactorer.md https://raw.githubusercontent.com/CloudAI-X/claude-workflow-v2/main/agents/refactorer.md $ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/CloudAI-X/claude-workflow-v2/main/agents/security-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/test-architect.md https://raw.githubusercontent.com/CloudAI-X/claude-workflow-v2/main/agents/test-architect.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 (14)
analyzing-projectsconvex-backenddatabase-designdesigning-apisdesigning-architecturedesigning-testsdevops-infrastructureerror-handlingmanaging-gitoptimizing-performanceparallel-executionsecurity-patternsvercel-react-best-practicesweb-design-guidelines
Subagents (7)
| code-reviewer model: sonnet | Expert code review specialist. Use PROACTIVELY after writing or modifying code, before commits, when asked to review changes, PR review, code quality check, lint, or standards audit. Focuses on qualit |
| debugger model: sonnet | Expert debugging specialist for errors, test failures, crashes, segmentation faults, memory leaks, timeouts, race conditions, deadlocks, and unexpected behavior. Use PROACTIVELY when encountering any |
| docs-writer model: sonnet | Technical documentation specialist. Use for creating README files, API documentation, architecture docs, inline comments, user guides, changelogs, migration guides, release notes, FAQs, and troublesho |
| orchestrator model: opus | Master coordinator for complex multi-step tasks. Use PROACTIVELY when a task involves 2+ modules, requires delegation to specialists, needs architectural planning, or involves GitHub PR workflows. MUS |
| refactorer model: sonnet | Code refactoring specialist for improving code quality, reducing technical debt, eliminating code smells, reducing complexity, and applying design patterns. Use PROACTIVELY when code needs restructuri |
| security-auditor model: sonnet | Security specialist for vulnerability detection, secure coding review, and security hardening. Use PROACTIVELY when handling authentication, authorization, encryption, secrets, credentials, OAuth, JWT |
| test-architect model: sonnet | Testing strategy specialist for designing test suites, writing tests, and ensuring comprehensive coverage. Use PROACTIVELY when adding new features, fixing bugs, improving test coverage, creating test |
Slash commands (26)
/add-tests/architect/bootstrap-repo/code-simplifier/commit-push-pr/commit/dependency-upgrade/lint-check/lint-fix/mentor/metrics/parallel-analyze/parallel-review/plan/quick-fix/rapid/refactor-guided/review/run-tests/save-session-learnings/security-scan/summarize-changes/sync-branch/tutorial/validate-build/verify-changes
Similar rigs
Yassinekrn/claude-setup
Personal Claude Code setup — orchestrator/subagent delegation policy, custom agents, and a colored PowerShell statusline (git branch, model+effort, tokens, cost, rate limits).
Orchestrator 1.2k tok ·
harrissohail6/claude-code-config
Ultimate Claude Code configuration - 10 agents, 10 skills, 12 plugins, email notifications
YOLO Cowboy 31.3k tok ·
emmanuelnurit/claude-config
Configuration Claude Code avec agents BMAD, skills et commands pour developpement Thelia
Orchestrator 5.0k tok ·
getclawe/clawe
Multi-agent coordination system: think Trello for OpenClaw agents.
Pragmatist 3.3k tok ·