[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-openai-codex-app-feature-tour-2026-en":3,"article-related-openai-codex-app-feature-tour-2026-en":24,"series-tools-5ac1e437-102b-4e95-8c01-b2a2ffafb523":67},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":10,"image_url":11,"cover_image":11,"category":12,"language":13,"translated_content":10,"related_article_id":14,"keywords":15,"key_takeaways":10,"views":21,"created_at":22,"published_at":22,"topic_cluster_id":23},"5ac1e437-102b-4e95-8c01-b2a2ffafb523","openai-codex-app-feature-tour-2026-en","OpenAI Codex APP Feature Tour: Sandbox, Worktree, and Skills","\u003Cp>OpenAI's Codex APP has stopped being a code assistant. By late 2026 it bundles an OS-level sandbox, deep Git integration, a cloud execution environment, native Skills, and MCP support into a single desktop app — making it arguably the most feature-complete AI Agent client on the market and, in several workflows, ahead of \u003Ca href=\"\u002Ftag\u002Fclaude-code\">Claude Code\u003C\u002Fa>.\u003C\u002Fp>\n\n\u003Cp>Here is what Codex now ships, and the design choice that separates it from the alternatives.\u003C\u002Fp>\n\n\u003Ch2>The Sandbox Is the Foundation, Not an Add-On\u003C\u002Fh2>\n\n\u003Cp>The single deepest difference between Codex and Claude Code is the role of the sandbox. Claude Code treats sandboxing as an optional protective layer; Codex treats the sandbox as the bedrock of its entire permission system. The current project folder \u003Cem>is\u003C\u002Fem> the sandbox: by default Codex can freely read and modify files inside it, but cannot touch files outside, and has no network access.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777620216349-r0tr.png\" alt=\"OpenAI Codex APP Feature Tour: Sandbox, Worktree, and Skills\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\n\n\u003Cp>These constraints are not enforced by the model's good behavior. They are enforced by OS-level mechanisms — for example macOS's built-in Seatbelt Sandbox. When Codex needs to step outside the sandbox (an \"escalate\" operation), it must request permission.\u003C\u002Fp>\n\n\u003Cp>Permissions ship in three tiers: manual approval, automatic review (a small model evaluates risk and waves through low-risk operations), and full access. Auto-review is the recommended default — it captures most of the safety benefit without the friction of approving every action.\u003C\u002Fp>\n\n\u003Ch2>Plan Mode, Steer, and Parallel Tasks\u003C\u002Fh2>\n\n\u003Cp>Codex runs in a three-pane layout: a left task list, a center conversation, and a right multi-function panel (browser, annotation, file tree). Multiple projects run side by side; task status is signaled by colored dots — gray for in-progress, green for awaiting approval, blue for done.\u003C\u002Fp>\n\n\u003Cp>Two capabilities matter here. \u003Cstrong>Plan Mode\u003C\u002Fstrong> stops Codex from acting immediately; instead it produces a structured plan with question cards so the user can align on scope and approach before execution. \u003Cstrong>Steer\u003C\u002Fstrong> lets the user grab the wheel mid-execution and correct direction without waiting for the current task to finish — directly avoiding the common Agent failure mode of \"watching it run the wrong way for ninety seconds.\"\u003C\u002Fp>\n\n\u003Ch2>Git Worktree and Cloud Execution\u003C\u002Fh2>\n\n\u003Cp>Git integration in Codex goes further than most agent clients. The UI exposes Git Worktree directly — copy the project to a new folder under a fresh branch, run a Codex task there in parallel with the main folder, and merge back when ready. Multiple agents can work the same repository without stepping on each other.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777620217163-xovl.png\" alt=\"OpenAI Codex APP Feature Tour: Sandbox, Worktree, and Skills\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\n\n\u003Cp>Cloud execution is the second axis. Push the project to GitHub, switch to Codex Web (the mobile browser works), issue an instruction, and a cloud container clones, modifies, and submits the result as a pull request. For travel or away-from-laptop work, this collapses the iteration loop.\u003C\u002Fp>\n\n\u003Ch2>AGENTS.md, Skills, and MCP: Three Layers of Extensibility\u003C\u002Fh2>\n\n\u003Cp>Codex stacks extensibility into three layers:\u003C\u002Fp>\n\n\u003Cul>\n\u003Cli>\u003Cstrong>AGENTS.md\u003C\u002Fstrong> — a memory file at the project root, auto-loaded into every conversation. A global version at \u003Ccode>~\u002F.codex\u002FAGENTS.md\u003C\u002Fcode> applies to all projects on the machine.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Skills\u003C\u002Fstrong> — packaged workflows, conventions, or specialized capabilities. Install from the official marketplace (Remotion video generation, for example), grab third-party versions from GitHub, or build your own with the bundled Skill Creator.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>MCP (Model Context Protocol)\u003C\u002Fstrong> — a standard protocol for plugging in external services such as Supabase, Gmail, or GitHub. Codex handles OAuth via a \u003Ccode>codex mcp login\u003C\u002Fcode> CLI flow.\u003C\u002Fli>\n\u003C\u002Ful>\n\n\u003Cp>The architecture mirrors Claude Code's Skills and MCP model, but Codex ships a more polished marketplace and a smoother first-run install experience.\u003C\u002Fp>\n\n\u003Ch2>Computer Use and Scheduled Automation\u003C\u002Fh2>\n\n\u003Cp>Computer Use is currently macOS-only. It lets the agent drive the entire desktop through a virtual cursor — open a chat app, send a message, browse a GitHub kanban, summarize ticket progress, and report back. Combined with Codex's built-in automation scheduler, the same flow can be turned into a cron-like job (a 5pm daily report to your manager, for example).\u003C\u002Fp>\n\n\u003Cp>An underrated detail: during automated runs Codex writes accumulated context to \u003Ccode>memory.md\u003C\u002Fcode>, feeding the next execution. It is a pattern worth borrowing for any production agent.\u003C\u002Fp>\n\n\u003Ch2>Why It Matters\u003C\u002Fh2>\n\n\u003Cp>Codex APP embodies OpenAI's stance on Agent tooling: harness model capability with OS-level mechanisms, then expose high-level abstractions — Plan, Steer, Worktree, Skills — to keep the user in control. As AI Agents move from demo to daily-driver developer tool, this \"powerful but reined in\" philosophy will outrun designs that chase pure autonomy.\u003C\u002Fp>","OpenAI's Codex APP has matured beyond a code completion tool into one of the most feature-complete AI Agent desktop clients in 2026. Backed by an OS-level sandbox, three-tier permission gating, native Git Worktree support, and a layered extensibility model spanning AGENTS.md, Skills, and MCP, it now pulls ahead of Claude Code on multi-task and long-horizon developer workflows. The capabilities below and the design choices behind them show OpenAI's emerging stance on production-grade agent tooling.","oracore-original",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777620216349-r0tr.png","tools","en","2f33e665-dbac-443a-87f0-15f6fda191b2",[16,17,18,19,20],"OpenAI","Codex","AI Agent","Claude Code","Developer Tools",18,"2026-05-01T07:22:46.938948+00:00","a7343b93-37cc-4634-a2bc-707f6275bdb6",{"tags":25,"relatedLang":26,"relatedPosts":30},[],{"id":14,"slug":27,"title":28,"language":29},"openai-codex-app-feature-tour-2026-zh","OpenAI Codex APP 完整功能盤點","zh",[31,37,43,49,55,61],{"id":32,"slug":33,"title":34,"cover_image":35,"image_url":35,"created_at":36,"category":12},"730d012d-2979-4f5e-b881-545cfa17aa52","rustrover-2026-1-4-right-default-ide-rust-en","RustRover 2026.1.4 is the right default IDE for Rust teams","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783211563197-9rof.png","2026-07-05T00:32:20.046071+00:00",{"id":38,"slug":39,"title":40,"cover_image":41,"image_url":41,"created_at":42,"category":12},"fcbbb173-58d2-4218-a111-452a7238377e","claude-design-synced-prototypes-setup-en","Claude Design setup for synced prototypes","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783191767986-jvz3.png","2026-07-04T19:02:22.032457+00:00",{"id":44,"slug":45,"title":46,"cover_image":47,"image_url":47,"created_at":48,"category":12},"a3df178b-7492-4b4b-8ab6-1de524c2fbdd","rust-196-turns-ranges-into-safer-copies-en","Rust 1.96 turns ranges into safer copies","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783190002602-30jh.png","2026-07-04T18:32:53.529817+00:00",{"id":50,"slug":51,"title":52,"cover_image":53,"image_url":53,"created_at":54,"category":12},"b55fbd0c-846b-4592-953e-e581e1dd4918","ai-data-operations-vs-mlops-what-each-owns-en","AI Data Operations vs MLOps: what each owns","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783168368731-aeq1.png","2026-07-04T12:32:19.952613+00:00",{"id":56,"slug":57,"title":58,"cover_image":59,"image_url":59,"created_at":60,"category":12},"6f72b385-bc6c-47cf-b466-8eb40fed86a7","opentag-turns-slack-threads-into-actions-en","OpenTag turns Slack threads into actions","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783148604415-put0.png","2026-07-04T07:02:50.733486+00:00",{"id":62,"slug":63,"title":64,"cover_image":65,"image_url":65,"created_at":66,"category":12},"fa7e59ac-8216-4826-84a1-3ae5a7fc4f57","gpu-vram-needed-llm-fine-tuning-2026-en","GPU VRAM Needed for LLM Fine-Tuning in 2026","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783128777001-pdg7.png","2026-07-04T01:32:34.039474+00:00",[68,73,78,83,88,93,98,103,108,113],{"id":69,"slug":70,"title":71,"created_at":72},"8008f1a9-7a00-4bad-88c9-3eedc9c6b4b1","surepath-ai-mcp-policy-controls-en","SurePath AI's New MCP Policy Controls Enhance AI Security","2026-03-26T01:26:52.222015+00:00",{"id":74,"slug":75,"title":76,"created_at":77},"27e39a8f-b65d-4f7b-a875-859e2b210156","mcp-standard-ai-tools-2026-en","MCP Standard in 2026: Integrating AI Tools","2026-03-26T01:27:43.127519+00:00",{"id":79,"slug":80,"title":81,"created_at":82},"165f9a19-c92d-46ba-b3f0-7125f662921d","rag-2026-transforming-enterprise-ai-en","How RAG in 2026 is Transforming Enterprise AI","2026-03-26T01:28:11.485236+00:00",{"id":84,"slug":85,"title":86,"created_at":87},"6a2a8e6e-b956-49d8-be12-cc47bdc132b2","mastering-ai-prompts-2026-guide-en","Mastering AI Prompts: A 2026 Guide for Developers","2026-03-26T01:29:07.835148+00:00",{"id":89,"slug":90,"title":91,"created_at":92},"3ab2c67e-4664-4c67-a013-687a2f605814","garry-tan-open-sources-claude-code-toolkit-en","Garry Tan Open-Sources a Claude Code Toolkit","2026-03-26T08:26:20.245934+00:00",{"id":94,"slug":95,"title":96,"created_at":97},"66a7cbf8-7e76-41d4-9bbf-eaca9761bf69","github-ai-projects-to-watch-in-2026-en","20 GitHub AI Projects to Watch in 2026","2026-03-26T08:28:09.752027+00:00",{"id":99,"slug":100,"title":101,"created_at":102},"9f332fda-eace-448a-a292-2283951eee71","practical-github-guide-learning-ml-2026-en","A Practical GitHub Guide to Learning ML in 2026","2026-03-27T01:16:50.125678+00:00",{"id":104,"slug":105,"title":106,"created_at":107},"1b1f637d-0f4d-42bd-974b-07b53829144d","aiml-2026-student-ai-ml-lab-repo-review-en","AIML-2026 Is a Bare-Bones Student Lab Repo","2026-03-27T01:21:51.661231+00:00",{"id":109,"slug":110,"title":111,"created_at":112},"6d1bf3f6-e191-4d30-b55b-8a0722fa6afe","ai-trending-github-repos-and-research-feeds-en","AI Trending Tracks Repos and Research Feeds","2026-03-27T01:31:35.709532+00:00",{"id":114,"slug":115,"title":116,"created_at":117},"010539a1-4c3a-4bd3-937a-26616422ee0d","awesome-ai-for-science-research-tools-map-en","Awesome AI for Science Is Becoming a Real Research Map","2026-03-27T01:46:50.89513+00:00"]