CCG - Claude-Codex-Gemini Tri-Model Orchestration

CCG routes through the canonical /ask skill (/ask codex + /ask gemini), then Claude synthesizes both outputs into one answer.

Use this when you want parallel external perspectives without launching tmux team workers.

When to Use

Backend/analysis + frontend/UI work in one request
Code review from multiple perspectives (architecture + design/UX)
Cross-validation where Codex and Gemini may disagree
Fast advisor-style parallel input without team runtime orchestration

Requirements

Codex CLI: npm install -g @openai/codex (or @openai/codex)
Gemini CLI: npm install -g @google/gemini-cli
omc ask command available
If either CLI is unavailable, continue with whichever provider is available and note the limitation

How It Works

1. Claude decomposes the request into two advisor prompts:
   - Codex prompt (analysis/architecture/backend)
   - Gemini prompt (UX/design/docs/alternatives)

2. Claude runs via CLI (skill nesting not supported):
   - `omc ask codex "<codex prompt>"`
   - `omc ask gemini "<gemini prompt>"`

3. Artifacts are written under `.omc/artifacts/ask/`

4. Claude synthesizes both outputs into one final response

Execution Protocol

When invoked, Claude MUST follow this workflow:

1. Decompose Request

Split the user request into:

Codex prompt: architecture, correctness, backend, risks, test strategy
Gemini prompt: UX/content clarity, alternatives, edge-case usability, docs polish
Synthesis plan: how to reconcile conflicts

2. Invoke advisors via CLI

Note: Skill nesting (invoking a skill from within an active skill) is not supported in Claude Code. Always use the direct CLI path via Bash tool.

Run both advisors:

omc ask codex "<codex prompt>"
omc ask gemini "<gemini prompt>"

3. Collect artifacts

Read latest ask artifacts from:

.omc/artifacts/ask/codex-*.md
.omc/artifacts/ask/gemini-*.md

4. Synthesize

Return one unified answer with:

Agreed recommendations
Conflicting recommendations (explicitly called out)
Chosen final direction + rationale
Action checklist

Fallbacks

If one provider is unavailable:

Continue with available provider + Claude synthesis
Clearly note missing perspective and risk

If both unavailable:

Fall back to Claude-only answer and state CCG external advisors were unavailable

Invocation

/oh-my-claudecode:ccg <task description>

Example:

/oh-my-claudecode:ccg Review this PR - architecture/security via Codex and UX/readability via Gemini

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

72/100

Grade

B

Good

Safety

68

Quality

76

Clarity

78

Completeness

64

Summary

CCG orchestrates parallel code analysis by routing requests to external OpenAI Codex and Google Gemini advisors via CLI, then synthesizes their outputs into a unified recommendation. It decomposes user requests into domain-specific prompts, invokes both tools concurrently, and reconciles conflicting advice with explicit rationale.

Detected Capabilities

External API orchestration (Codex + Gemini CLI invocation)Parallel prompt decomposition and routingArtifact file reading from .omc/artifacts/ask/Output synthesis and conflict reconciliationFallback handling when providers are unavailable

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

parallel code reviewmulti-perspective analysisarchitecture and ux feedbackcodex gemini synthesiscross-validate design decisions

Risk Signals

WARNING

Invokes external CLI tools (omc ask codex/gemini) with dynamic prompt injection via bash variables

Execution Protocol section, step 2

INFO

Reads artifact files from .omc/artifacts/ directory without validation of file content or source

Execution Protocol section, step 3

INFO

Relies on external CLI availability (Codex, Gemini) with limited error handling documentation

Requirements section and Fallbacks

WARNING

No explicit guardrails documented for escaping or sanitizing prompts passed to bash CLI invocations

Execution Protocol section, step 2

Use Cases

Get architecture and UX feedback on the same PR simultaneously
Validate design decisions across multiple AI perspectives before implementation
Code review requiring both backend/security and frontend/usability analysis
Cross-check correctness and clarity without manual context-switching

Quality Notes

Clear decomposition strategy: codex handles architecture/backend, gemini handles UX/design — excellent separation of concerns
Well-documented fallback behavior for missing providers prevents silent failure
Artifact path hardcoded (.omc/artifacts/ask/) — good predictability but inflexible if directory structure changes
Missing critical implementation detail: how to properly escape/quote prompts in bash to prevent injection when they contain special characters
No guidance on handling malformed or unexpected artifact file formats
Execution Protocol explicitly notes skill nesting is unsupported — good guardrail against recursive calls
Synthesis plan mentions conflict reconciliation but no concrete examples of common conflicts (e.g., Codex security vs. Gemini UX concerns)
No documented limits on prompt size or advisor response size — could impact large PRs or complex requests

Model: claude-haiku-4-5-20251001Analyzed: Apr 20, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.1

Content updated

2026-04-20

Latest

v1.0

No changelog

2026-04-12

ccg