
Ccg
- 461 installs
- 38.3k repo stars
- Updated August 4, 2026
- yeachan-heo/oh-my-claudecode
ccg is a Claude Code orchestration skill that queries OpenAI Codex and Google Gemini in parallel via omc /ask commands, then has Claude synthesize both outputs for multi-model code review and architecture feedback.
About
ccg is a Claude-Codex-Gemini tri-model orchestration skill from yeachan-heo/oh-my-claudecode that routes through the canonical /ask skill with /ask codex and /ask antigravity (or Gemini), then has Claude synthesize both outputs into one answer. Developers invoke it for parallel external perspectives on code review, architecture validation, and cross-domain requests combining backend analysis with frontend or UX feedback without launching tmux team workers. CCG is rated level 5 and suits fast advisor-style parallel input when Codex and Antigravity may disagree. Reach for ccg when multi-model cross-validation is needed in a single request.
- Parallel queries to Codex and Gemini via omc ask
- Claude synthesizes all three model outputs into unified response
- No tmux team workers required for multi-model feedback
- Graceful degradation when a provider is unavailable
Ccg by the numbers
- 461 all-time installs (skills.sh)
- +6 installs in the week ending Jul 27, 2026 (Skillselion tracking)
- Ranked #1,870 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/yeachan-heo/oh-my-claudecode --skill ccgAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 461 |
|---|---|
| repo stars | ★ 38.3k |
| Last updated | August 4, 2026 |
| Repository | yeachan-heo/oh-my-claudecode ↗ |
How do you get multi-model code review in Claude Code?
Queries OpenAI Codex and Google Gemini in parallel via the omc ask command, then has Claude synthesize their outputs for multi-model code review and architecture feedback.
Who is it for?
Claude Code developers using oh-my-claudecode who want parallel Codex and Gemini perspectives on architecture, code review, or cross-stack requests without tmux team workers.
Skip if: Developers needing a single-model review only or workflows that do not have omc /ask codex and /ask antigravity configured.
When should I use this skill?
A developer requests code review or architecture feedback and wants parallel Codex plus Gemini input synthesized by Claude in one response.
What you get
Synthesized tri-model review answer combining parallel Codex and Gemini outputs with Claude reconciliation of disagreements.
- synthesized multi-model review
- architecture feedback summary
By the numbers
- Orchestrates three models: Claude, OpenAI Codex, and Google Gemini
- Rated level 5 in oh-my-claudecode skill hierarchy
Files
CCG - Claude-Codex-Gemini Tri-Model Orchestration
CCG routes through the canonical /ask skill (/ask codex + /ask antigravity), 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 Antigravity/Gemini may disagree
- Fast advisor-style parallel input without team runtime orchestration
Requirements
- Codex CLI:
npm install -g @openai/codex(or@openai/codex) - Antigravity CLI (Google's successor to the Gemini CLI): install the
agybinary
per the official Antigravity instructions (inspect any installer before running it). Verify: agy --version
- Gemini CLI remains supported for enterprise/API-key use cases:
npm install -g @google/gemini-cli omc askcommand 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)
- Antigravity prompt (UX/design/docs/alternatives) — use gemini for enterprise
2. Claude runs via CLI (skill nesting not supported):
- `omc ask codex "<codex prompt>"`
- `omc ask antigravity "<antigravity prompt>"`
(or `omc ask gemini "<gemini prompt>"` for enterprise)
3. Artifacts are written under `.omc/artifacts/ask/`
4. Claude synthesizes both outputs into one final responseExecution Protocol
When invoked, Claude MUST follow this workflow:
1. Decompose Request
Split the user request into:
- Codex prompt: architecture, correctness, backend, risks, test strategy
- Antigravity 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 (use antigravity or gemini depending on your setup):
omc ask codex "<codex prompt>"
omc ask antigravity "<antigravity prompt>"Enterprise fallback:
omc ask gemini "<gemini prompt>"3. Collect artifacts
Read latest ask artifacts from:
.omc/artifacts/ask/codex-*.md
.omc/artifacts/ask/antigravity-*.md
.omc/artifacts/ask/gemini-*.md4. 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 AntigravityRelated skills
How it compares
Pick ccg over single-model review when parallel Codex and Gemini perspectives need Claude synthesis without standing up tmux team workers.
FAQ
How does ccg combine Codex and Gemini outputs?
ccg routes /ask codex and /ask antigravity (or Gemini) in parallel through the omc /ask skill, then Claude synthesizes both responses into one answer. The skill reconciles disagreements for architecture and code review requests.
When should developers use ccg instead of tmux team workers?
Developers should use ccg for fast advisor-style parallel input when Codex and Antigravity perspectives are enough. ccg avoids launching tmux team workers while still delivering tri-model cross-validation on backend, frontend, and UX questions.