一支通过规范驱动开发流程协作的Codex代理团队。全栈开发者母公司协调动态规模的专家池：编码、DevOps、评审和解决方案......
概览
一个可共享的混合Codex开发团队示例配置。它结合了项目范围自定义代理、仓库本地插件、提示快捷方式、生命周期钩子、命令规则和规格模板，实现计划-构建-审查工作流程。 该仓库是一个示例配置，不是生产准备的控制平面。在实际项目中使用前，务必仔细审查每一条代理指令、钩子、规则、插件文件和安全说明。 示例围绕主线程协调器和五个可选角色代理构建： 这些显式 ID 保留了批准的设置。公共仓库有意不复制私有model_provider、凭证、区域、配置文件或项目信任配置;采用者必须配置一个暴露这些模型 ID 的提供者。.codex/config.toml 还默认主线程为 openai.gpt-5.6-sol at xhigh。
概述（AI 翻译）
一个可共享的混合Codex开发团队示例配置。它结合了项目范围自定义代理、仓库本地插件、提示快捷方式、生命周期钩子、命令规则和规格模板，实现计划-构建-审查工作流程。
跳转到快速开始。
这个仓库是一个示例配置，不是生产准备的控制平面。在实际项目中使用之前，务必仔细审查每一条代理指令、钩子、规则、插件文件和安全提示。
概述
该示例围绕主线程协调器和六个可选角色代理构建。 这些已发布的职位与截至2026年10月6日的定义一致：
| 代理 | 角色 | 模型 | 推理努力 | 主要用途 |
|---|---|---|---|---|
fullstack-agent |
首席协调员 | openai.gpt-6-astra |
中型 | 规格、委派、生成计划与评测整合 |
coding-agent |
实现工程师 | openai.gpt-6.1-sol |
高 | 有范畴的生产代码、测试、重构与修复 |
devops-agent |
基础设施与交付专家 | openai.gpt-6.1-sol |
高 | CI/CD、容器、IaC、环境布线和运行手册 |
review-agent |
独立标准评审者 | 'openai。 |
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
Codex Agent Team Sample
A shareable sample configuration for a hybrid Codex development team. It combines project-scoped custom agents, a repo-local plugin, prompt shortcuts, lifecycle hooks, command rules, and spec templates for a plan-build-review workflow.
Jump to Quick Start.
This repository is a sample configuration, not a production-ready control plane. Review every agent instruction, hook, rule, plugin file, and security note before using it on real projects.
Overview
The sample is built around a main-thread coordinator and six optional role agents. These published roles mirror their maintained definitions as of October 6, 2026:
| Agent | Role | Model | Reasoning Effort | Primary Use |
|---|---|---|---|---|
fullstack-agent |
Lead coordinator | openai.gpt-6-astra |
medium | Specs, delegation, spawn plans, and review consolidation |
coding-agent |
Implementation engineer | openai.gpt-6.1-sol |
high | Scoped production code, tests, refactors, and fixes |
devops-agent |
Infrastructure and delivery specialist | openai.gpt-6.1-sol |
high | CI/CD, containers, IaC, environment wiring, and runbooks |
review-agent |
Independent standard reviewer | openai.gpt-6-astra |
high | Security, data, resource-changing IaC, delivery, and new logic review |
review-lite-agent |
Independent lightweight reviewer | openai.gpt-6.1-sol |
medium | Mechanical, docs-only, and narrow low-risk fix verification |
sa-agent |
AWS Solutions Architect teammate | openai.gpt-6.1-sol |
medium | Architecture, reliability, cost, security, and operational design |
.codex/config.toml defaults the main thread to openai.gpt-6.1-sol at
medium, with 14 threads and depth 2. These are the maintained team’s exact
model IDs and effort settings. This public repo omits private provider/backend
configuration, credentials, region, profile, project trust,
and account-specific settings. Configure a provider exposing these IDs before
running agents; catalog-valid IDs do not guarantee account permission to invoke.
The sync includes current agent prompts, global guidance, the five team workflow
skills, their Testing Standards reference, referenced standalone skills and
spec templates. Public packaging retains repo-relative hook wiring, the
marketplace, public plugin metadata and the additional pip-install approval
rule. Personal default approval rules, installed caches, session state, logs,
auth files and past task/review artifacts are excluded.
The plugin version is 0.1.1+codex.20261005; restart the Codex thread after
installing the refreshed public bundle.
推荐工具
换一个关键词，或者移除筛选条件。
安装
npx skillfish add aws-samples/sample-codex-agent-team