Agent Skills
› davepoon/buildwithclaude
› dispatch
dispatch
GitHub将任务委派给OpenAI Codex或Google Antigravity CLI，获取不同模型的独立审查与观点。支持会话追踪、结果综合及冲突调和，适用于代码评审、架构验证及跨模型决策辅助，无需额外API密钥。
Trigger Scenarios
请求其他模型进行代码审查或二次意见
需要跨模型交叉验证分析结果
委托研究、图像生成等旁路任务
在多模型间调和分歧以做出最终决策
Install
npx skills add davepoon/buildwithclaude --skill dispatch -g -y
SKILL.md
Frontmatter
{
"name": "dispatch",
"category": "development-code",
"description": "Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code. Say 'check with codex' or 'ask gemini for a second opinion' and Claude runs the other agent, keeps a topic-aware session, and critiques the result."
}
Dispatch
Delegate tasks to external AI CLIs from inside Claude Code. Say "check with codex", "ask gemini for a second opinion", or "validate this before I merge" and Claude runs the other agent, keeps a topic-aware conversation, and critiques the result rather than echoing it.
Supports OpenAI Codex CLI and Google Antigravity CLI (multi-model: Gemini, Claude, GPT-OSS). No API keys — both CLIs use their own auth (OAuth / Google sign-in).
Source: sparklingneuronics/sparkling-skills (MIT)
When to Use This Skill
- Getting a second opinion from a different model family before merging
- Cross-checking Claude's analysis against Codex or Gemini
- Delegating a side task (research, review, image generation) to another CLI
- Triangulating a decision across multiple models and having Claude reconcile disagreements
- Resuming a prior delegation thread without restating context
What This Skill Does
- Routes to the right CLI based on the tool you name — "codex" invokes Codex CLI, "gemini" or "agy" invokes Antigravity CLI
- Picks sensible defaults — Codex: gpt-5.5, read-only sandbox; Antigravity: Gemini 3.5 Flash (or the model you name)
- Synthesizes the result — Claude summarizes findings, states where it agrees or disagrees, and recommends next steps
- Tracks topics — each delegation gets its own external session, resumed by ID on follow-ups
Examples
Second opinion on code
User: ask codex to review my uncommitted changes before I merge
Claude: [runs codex review --uncommitted, synthesizes findings]
Codex flagged three things. I agree with #1 (missing null check)
but #2 and #3 are false positives. Want me to fix the null check?
Cross-model challenge
User: ask gemini to challenge this architecture
Claude: [runs agy with Gemini 3.1 Pro, compares with own analysis]
Gemini raises a valid concern about hot-partition risk that I
hadn't flagged. Its other two points don't apply here.
Resume a thread
User: continue with codex — is the top issue real?
Claude: [resumes the same codex session with a delta bridge]
Codex confirms the null-check issue — it traced the code path.
Requirements
- Claude Code (the plugin runs inside it)
- For Codex:
codexCLI +codex login(OAuth) - For Antigravity:
agyCLI + Google sign-in (free account)
Install: claude install-plugin sparklingneuronics/sparkling-skills
Version History
- 502fc01 Current 2026-07-05 15:03
