codex-cli

Run multiple AI coding accounts at the same time.

Pre-compaction hooks + a CAS-guarded task pointer that keep Codex agents on-goal across context auto-compaction — no mainline drift, no duplicate work, no conflicting progress in long runs.

A Claude Code plugin for Siemens TIA Portal engineering automation.

修复 Codex 沙箱模式的 Bug：批量检查并修复Windows文件/文件夹的所有者，清理未知用户和权限，拦截本不应该有的巨量写入请求。 | Fix bugs in Codex sandbox mode: check and repair the owners of Windows files/folders in batches, clean up unknown users and permissions, and intercept a huge amount of write requests that should not be there.

Codex 0.135.0 Windows x64 全量离线安装包，支持 Win10/Win11/Windows Server，内置 Codex CLI、Node.js、npm 离线缓存和 NSIS 一键安装器

Orchestrator plugin: composes planning-with-files, DESIGN.md, memory routing, agent teams, and session handoff into one contract for any modern coding agent. Cross-IDE.

MediaUse Skills, web operations into semantic CLI actions, AI agents can run with near-zero token cost and higher stability.

Codex 桌面版为 DeepSeek-V4-Flash 开启 Max 推理档位的完整排障与配置指南 / Complete guide to enable Max reasoning effort for DeepSeek-V4-Flash in Codex desktop

Production engineering and design skills for OpenAI Codex.

💪 Integrate the Azure Bicep MCP server with Claude, Codex, LM Studio, GitHub Copilot App, and more.

A liquid-glass traffic-light island for monitoring background Codex CLI sessions on Windows.

Windows 本地 Codex 历史记录 / 会话恢复工具：同步 SQLite 与 JSONL 中的 model_provider，解决切换官方账号、中转站 API Key 或自定义 provider 后原有任务不可见的问题。

基于 JDArmy/BREAK 的黑灰产情报分析 Skill，面向风控、反欺诈和业务安全团队。

Delegate coding tasks to agents, collect artifacts, and verify results locally with standalone supervision skills for Claude, Codex, and Kimi automation.

One-click, cross-platform Codex CLI and GUI installer for GPT-5.6 Luna with Ultra reasoning on Windows, macOS, and Linux.

One powershell script - Launch ChatGPT/Codex Desktop via your local proxy on Windows. 走代理设置的 Codex 桌面端启动脚本，从此告别系统代理 / TUN

Chinese-first concise mode SKILL.md for Claude Code / Codex CLI / Cursor — shorter, denser replies without losing technical accuracy.

Destructive command guardrails for OpenAI Codex agents and subagents. Blocks rm -rf, dangerous Git operations, pushes, and selected GitHub writes without sacrificing workspace autonomy.

Hardened Docker sandbox for OpenAI Codex CLI with workspace-only mounts, per-project auth, and allowlisted network egress