By sitien173
Superpowers-CCCG: Skills-driven development workflow with CCCG multi-model orchestration (Claude orchestrator + Codex backend + Cursor DevOps + Gemini frontend)
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements and design before implementation.
Execute plan in batches with review checkpoints
Create detailed implementation plan with bite-sized tasks
Explores user intent, requirements and design through collaborative dialogue before implementation. Use when: creating features, building components, adding functionality, modifying behavior, or starting any creative work. Keywords: design, requirements, spec, ideation, planning
Routes work to Codex (backend), Gemini (frontend), and Cursor (DevOps) via MCP tools. Claude is orchestrator-only — all code goes through external models. Use when: any implementation task, UI/components/styles, APIs/databases/auth/security/performance, DevOps/CI/scripts, or tasks mentioning Codex/Gemini/Cursor/CCCG/multi-model. Keywords: codex mcp, gemini mcp, cursor mcp, cross-validation, implementation, api, database, auth, security, performance, ui, component, devops, ci/cd
Find root cause before attempting fixes through four-phase investigation. Use when: encountering bugs, test failures, unexpected behavior, build errors, or performance issues. Keywords: debug, root cause, error, failure, investigate, diagnose
Executes plans by dispatching fresh subagent per task with two-stage review (spec then quality). Use when: executing implementation plans in current session with independent tasks. Keywords: subagent, task execution, fresh context, iterative development
Dispatches multiple agents concurrently for independent problem domains. Use when: facing 2+ independent tasks, multiple unrelated failures, or parallel investigations needed. Keywords: parallel, concurrent, multiple agents, batch processing
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Executables (bin/) — files in this plugin's bin/directory are added to the Bash tool's PATH while the plugin is enabled.
Executes directly as bash, bypassing the AI model
Executes directly as bash, bypassing the AI model
Superpowers-CCCG is a fork/enhanced variant of obra/superpowers. It keeps the same skills-driven workflow, and adds CCCG multi-model orchestration: Claude is the pure orchestrator (never writes code), routing implementation to Codex MCP (backend), Gemini MCP (frontend), and Cursor MCP (DevOps), with Opus as the reviewer for every code-changing path.
CCCG = Claude + Codex + Cursor + Gemini
mcp__codex__codex, mcp__gemini__gemini, mcp__cursor__cursor.BLOCKED rather than guessing. All coding tasks are BLOCKED if no external models are available.claude --version)gemini --version)codex --version)agent binary available in PATH (or %LOCALAPPDATA%\cursor-agent\agent.cmd on Windows)uv / uvx available — install via:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"curl -LsSf https://astral.sh/uv/install.sh | shclaude plugin marketplace add https://github.com/sitien173/superpowers-cccg
claude plugin install superpowers-cccg
After installation, configure the MCP servers so the orchestrator can route work to them.
# Backend specialist
claude mcp add codex -s user --transport stdio -- uvx --from git+https://github.com/GuDaStudio/codexmcp.git codexmcp
# Frontend specialist
claude mcp add gemini -s user --transport stdio -- uvx --from git+https://github.com/GuDaStudio/geminimcp.git geminimcp
# DevOps specialist
claude mcp add cursor -s user --transport stdio -- uvx --from git+https://github.com/sitien173/cursormcp.git cursormcp
You typically do not call MCP tools manually. Tell Claude what you want, and the workflow decides when to invoke external models.
Note: prompts sent to external models are expected to be English for consistency (you can still chat with Claude in any language).
| Task type | Routing | MCP Tool |
|---|---|---|
| Backend (APIs, DB, auth, perf) | CODEX | mcp__codex__codex |
| Frontend (UI/components/styles) | GEMINI | mcp__gemini__gemini |
| DevOps (CI/CD, scripts, Dockerfiles, infrastructure) | CURSOR | mcp__cursor__cursor |
| Full-stack / unclear / high impact | CROSS_VALIDATION | multiple |
| Orchestration only (docs, coordination) | CLAUDE | none |
The routing/checkpoint rules live in skills/coordinating-multi-model-work/.
Cursor model policy:
claude-4.6-sonnet-medium-thinking.claude-4.5-opus-high-thinking.| Checkpoint | When | Purpose |
|---|---|---|
| CP1 | Before first Task call | Assess routing, invoke external model early |
| CP2 | Mid-execution | Triggered by uncertainty, stalled debugging, 2+ failures |
| CP3 | Before claiming completion | Final domain + code quality review |
npx claudepluginhub sitien173/superpowers-cccgSuperpowers-CCG: 3-gate (Plan → Execute → Review) workflow.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review