[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-openai-codex-app-feature-tour-2026-en":3,"tags-openai-codex-app-feature-tour-2026-en":28,"related-lang-openai-codex-app-feature-tour-2026-en":29,"related-posts-openai-codex-app-feature-tour-2026-en":33,"series-tools-5ac1e437-102b-4e95-8c01-b2a2ffafb523":70},{"id":4,"title":5,"content":6,"summary":7,"source":8,"source_url":9,"author":9,"image_url":10,"keywords":11,"language":17,"translated_content":9,"views":18,"is_premium":19,"created_at":20,"updated_at":20,"cover_image":10,"published_at":20,"rewrite_status":21,"rewrite_error":9,"rewritten_from_id":9,"slug":22,"category":23,"related_article_id":24,"status":25,"google_indexed_at":26,"x_posted_at":27,"tweet_text":9,"title_rewritten_at":9,"title_original":9,"key_takeaways":9,"topic_cluster_id":9,"embedding":9,"is_canonical_seed":19},"5ac1e437-102b-4e95-8c01-b2a2ffafb523","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",[12,13,14,15,16],"OpenAI","Codex","AI Agent","Claude Code","Developer Tools","en",0,false,"2026-05-01T07:22:46.938948+00:00","done","openai-codex-app-feature-tour-2026-en","tools","2f33e665-dbac-443a-87f0-15f6fda191b2","published","2026-05-01T09:00:06.869+00:00","2026-05-01T10:00:02.752+00:00",[],{"id":24,"slug":30,"title":31,"language":32},"openai-codex-app-feature-tour-2026-zh","OpenAI Codex APP 完整功能盤點","zh",[34,40,46,52,58,64],{"id":35,"slug":36,"title":37,"cover_image":38,"image_url":38,"created_at":39,"category":23},"a6c1d84d-0d9c-4a5a-9ca0-960fbfc1412e","why-gemini-api-pricing-is-cheaper-than-it-looks-en","Why Gemini API pricing is cheaper than it looks","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778869846824-s2r1.png","2026-05-15T18:30:26.595941+00:00",{"id":41,"slug":42,"title":43,"cover_image":44,"image_url":44,"created_at":45,"category":23},"8b02abfa-eb16-4853-8b15-63d302c7b587","why-vidhub-huiyuan-hutong-bushi-quan-shebei-tongyong-en","Why VidHub 会员互通不是“买一次全设备通用”","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778789439875-uceq.png","2026-05-14T20:10:26.046635+00:00",{"id":47,"slug":48,"title":49,"cover_image":50,"image_url":50,"created_at":51,"category":23},"abe54a57-7461-4659-b2a0-99918dfd2a33","why-buns-zig-to-rust-experiment-is-right-en","Why Bun’s Zig-to-Rust experiment is the right move","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778767895201-5745.png","2026-05-14T14:10:29.298057+00:00",{"id":53,"slug":54,"title":55,"cover_image":56,"image_url":56,"created_at":57,"category":23},"f0015918-251b-43d7-95af-032d2139f3f6","why-openai-api-pricing-is-product-strategy-en","Why OpenAI API pricing is a product strategy, not a footnote","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778749841805-uyhg.png","2026-05-14T09:10:27.921211+00:00",{"id":59,"slug":60,"title":61,"cover_image":62,"image_url":62,"created_at":63,"category":23},"7096dab0-6d27-42d9-b951-7545a5dddf33","why-claude-code-prompt-design-beats-ide-copilots-en","Why Claude Code’s prompt design beats IDE copilots","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778742651754-3kxk.png","2026-05-14T07:10:30.953808+00:00",{"id":65,"slug":66,"title":67,"cover_image":68,"image_url":68,"created_at":69,"category":23},"1f1bff1e-0ebc-4fa7-a078-64dc4b552548","why-databricks-model-serving-is-right-default-en","Why Databricks Model Serving is the right default for production infe…","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778692290314-gopj.png","2026-05-13T17:10:32.167576+00:00",[71,76,81,86,91,96,101,106,111,116],{"id":72,"slug":73,"title":74,"created_at":75},"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":77,"slug":78,"title":79,"created_at":80},"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":82,"slug":83,"title":84,"created_at":85},"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":87,"slug":88,"title":89,"created_at":90},"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":92,"slug":93,"title":94,"created_at":95},"d6653030-ee6d-4043-898d-d2de0388545b","evolving-world-prompt-engineering-en","The Evolving World of Prompt Engineering","2026-03-26T01:29:42.061205+00:00",{"id":97,"slug":98,"title":99,"created_at":100},"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":102,"slug":103,"title":104,"created_at":105},"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":107,"slug":108,"title":109,"created_at":110},"231306b3-1594-45b2-af81-bb80e41182f2","claude-code-vs-cursor-2026-en","Claude Code vs Cursor in 2026","2026-03-26T13:27:14.177468+00:00",{"id":112,"slug":113,"title":114,"created_at":115},"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":117,"slug":118,"title":119,"created_at":120},"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"]