Individual skill

codex-model-routing-team

在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team 或持久项目协作。简单问答、状态查询、单文件小改、强顺序任务和发布/付款/删除/账户操作不得自动触发。

skills/codex-model-routing-team/SKILL.md

Read pinned source

Source commit 8a3eda4276f2d297f22f478598fb962b88a7140e

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: Yes
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 160
Repository last updated: Jul 17, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skill Repository topic
background-agents Repository topic
codex Repository topic
developer-tools Repository topic
knowledge-work Repository topic
model-routing Repository topic
multi-agent Repository topic
workflow-orchestration Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

LICENSEasset · 1,076 bytes
SKILL.mdcore · 6,020 bytes
agents/interface.yamlasset · 800 bytes
agents/openai.yamlasset · 334 bytes
evals/upstream-skill-integration.jsonasset · 1,313 bytes
references/durable-mode.mddoc · 1,602 bytes
references/routing-policy.mddoc · 3,077 bytes
references/task-packet.mddoc · 1,244 bytes
references/thread-lifecycle.mddoc · 3,623 bytes
references/upstream-skill-adapter.mddoc · 2,514 bytes
references/validation-cases.mddoc · 1,949 bytes

Read excerpt


# Codex 模型路由团队

把主 Agent 保持为任务总负责人，通过 Codex App 独立后台任务实现真实的 `model` 与 `thinking` 路由。禁止使用原生 `spawn_agent` 代替本流程。

## Do not use

简单问答、状态查询、单文件小改、强顺序任务，以及发布、付款、删除、账户或生产操作不得自动派遣。

## 上游 Skill 模式

当 Deep Research、PPT、课程生产或其他上游 Skill 已经定义任务拆分、阶段顺序、文件路径和验收标准时，读取 [上游 Skill 适配协议](references/upstream-skill-adapter.md)。上游 Skill 保持业务流程主权；本 Skill 只负责模型路由、Thread 创建、并发额度、运行读取和归档。

禁止重复执行 Scale、改写上游阶段依赖或创建第二套事实源。安全上限仍然生效；预算不足时收敛 Worker 数量并明确报告。