OpenAI Codex

Developers proposed agent-specific browser auth for Codex, Devin, Claude, and Cursor so agents can use selected passkeys, TOTPs, and passwords without exposing full vaults. Related posts warned that Claude Connectors may broaden tool access.

Developers shared workflows that turn idle AI accounts into scheduled assistants for commits, research, repo cleanup, and notes. Shared designs add spend caps, Apple Notes routing, Obsidian output, and coworker controls.

Meng To released code and prompts for a scrolling bookshelf demo refined through many Codex prompts. Karpathy separately used Claude Opus 5 to turn the opening of LOTR into a 5,500-line Three.js render.

Allie Miller described using Codex Voice Mode for trackers, email, reminders, scheduling, and document work. Min Choi’s ElevenLabs setup shows a browser agent that listens, streams replies, and handles interruptions.

Meng To used Opus 5 through Codex and Claude Code to rebuild Sakura Crossing as a single-file Three.js scene. Other demos show one-prompt Fallout-style RPGs and a Pool Rooms survival-horror level.

Peter Yang shared Jason Liu’s workflow for mining past sessions into skills, adding a /write-like-me skill, pinning durable threads, importing browser sign-ins, and bundling related skills as plugins. One example edited a launch video from Slack feedback.

Creators shared playable game prototypes built with coding agents, including Codex rebuilding Octane in Blender, a Red Alert clone, a Three.js arena shooter, and a Claude Code tank game. Other demos used single-file browser-game scaffolds.

Shared workflows used Codex, Claude Code, and Fable for release testing, inbox triage, product-plan review, and adversarial code review. OpenClaw’s QA prompt split testing across 12 subagents.

New Opus 5, Codex, and Fable demos showed agents creating 3D worlds, Blender assets, Godot ports, and one-shot games. Pushback focused on whether the clips become games worth playing.

Bolt.new and related AI frontend workflows let teams store brand rules or design-system skills once instead of pasting them into every prompt. Taste Skill was cited with 67,000 GitHub stars after heavy Codex use.

LLMJunky described a ChatGPT Work/Codex setup where agents in parallel threads exchange session IDs to work on the same codebase, wait, and request updates. Users also asked for better natural-language search across session history.

LLMJunky said Codex used Palmier with FFmpeg to choose frame ranges, speed up a clip, add overlays, animate an icon, and place text. He still handled some zoom effects manually.

OpenAI staff said the new ChatGPT Voice is powered by GPT-Live-1 for more natural conversations. The launch also refreshed the ChatGPT shader with Blender prototypes translated to Metal and WebGL using Codex.

Kitze described using a $60 Hetzner server, four $200 Codex accounts behind codex-lb, self-hosted Paperclip workspaces, and a GPT-5.5 manager to run about 30 isolated tasks. The setup routes parallel coding work across isolated workspaces and paid Codex accounts.

Meng To showed Taste with Codex or Claude Code rebuilding landing pages from screenshots and videos. Voila also launched a tool that inspects UI and turns edits into code, copy, prompts, tasks, or agent handoffs.

Kaigani posted generated-video QC tests where Gemini caught subtle errors and said they are deliberately glitching clips for a benchmark. The work follows earlier Codex frame-analysis tests and focuses on detecting defects in generated video.

Kai Gani described using Sora 2 castings for character-cameo references, then reported Codex/GPT 5.5 caught an anatomy-placement error in generated video frames. The check used contact sheets and still frames, not audio or motion.

Posts report Fable 5 remains included in Claude only through July 7 before moving to $10/$50 per million-token credits. Watch usage closely: tests show roughly 2x Opus consumption in subagent and one-shot app workflows.

A creator walkthrough mapped HyperFrames into a five-step process: gather assets, write a storyboard, mine the launch repo, review static frames, then build and polish the final clip. Keep edits in HTML until the last pass, then use Studio for copy, spacing, color, and motion tweaks.

ClaudeDevs said it raised 5-hour and weekly usage caps for the weekend across every plan. The change lands as users report token burn, overage charges, and heavier Claude Code sessions driven by long agent runs and goal-checked workflows.

David Holz said he shot and edited the Midjourney Medical launch video himself and built its realtime browser visualization with three.js/WebGL, Claude, and Codex. That turns the hardware reveal into a creator-side production case study, even if the process is still a one-off launch build.

New Claude Code and Codex tests showed open-ended /goal runs drifting or stopping too early, while planning-first and verifier loops forced rechecks before completion. The more reliable setup improves long build workflows, but it costs more turns and tokens.

Users documented Codex handling self-service signups, repo-maintenance loops, and folder overwrite failures on June 14. Watch the wrapper update closely, since it also added rate-limit reset banking and browser dev mode around the same workflow.

Steipete showed Codex running inside Crabbox, opening accounts and completing live web signups while building and end-to-end testing the same project. The setup extends coding agents into real browser actions, but it can also trigger payment and verification messages during automated runs.

Magnific turned its MCP connector live on all paid plans and added a Slack-to-image workflow with auto layers and resize exports. The rollout matters because image generation, editing, and asset reuse can stay inside chat-driven creative workflows, with credits consumed per MCP request.

Creator demos showed OpenAI Codex building, running, and testing iOS apps through a Mac-only simulator plugin, and a companion thread listed Figma, illustration, video, and local model workflows. Separate posts also showed Codex sessions moving onto iPhone home screens and PM-built internal tools, so developers can test whether the plugin fits their stack.

Anthropic staff said Claude Code usage has shifted toward auto mode, routines, and phone-based coding one year after GA, and they pointed users to /usage for token breakdowns. The thread matters because it shows Anthropic’s intended daily-driver workflow as community comparisons with Codex intensify.

Markproduct shares a long-form spec that Claude 4.8 turns into a live animated hero section, while another creator pairs GPT-5.5 with OpenAI Sites for a password-manager landing page. These posts matter because layout, motion, fonts, and CSS behavior are being packaged into reusable website briefs.

Creators showed Codex building a retro 2D RPG, handling browser-based social posting, and replacing parts of the PRD workflow with working prototypes. Users also reported thread-sorting and design limits in the app, so watch where it still breaks down.

Figma posted a plugin that turns Codex output into editable canvas designs, and OpenAI also showed an iOS testing loop inside Codex. Watch for Codex to move beyond chat into app-building workflows, with more creator-built tools likely to follow.

Spiral 4.0 added a stylometry-based Style Engine for matching a writer or brand voice and shipped MCP plus CLI access for agent workflows. It also now plugs into Claude Code, Codex, and OpenClaw, and the base price drops to $15.

Creators used Codex to generate After Effects JSX edits, build reusable skills, and push Codex Sites toward autonomous app updates. That moves Codex from app scaffolds into repeatable motion-design workflows, though builders still flag setup friction and weak frontend polish.

OpenAI rolled out Codex Sites so plans, docs, dashboards, and creative concepts can become interactive apps with shareable URLs. The launch also added role-specific plugins, so teams can use the same workspace for thumbnail pulls, transcription, and other nontechnical tasks.

Codex users shared 56-hour task runs, PM-to-PR workflows, and a new black-box session recorder for tracking drift, token use, and incomplete responses. The longer autonomous sessions matter because browser auth gaps, passkey failures, and tool-selection bugs become real blockers once Codex is used beyond quick code generation.

Peter Yang published a /slides skill for Claude Code that turns rough outlines into animated HTML decks with 12 layouts, three templates, live charts, and screenshot-based self-fixes. It matters because presentation polish becomes a repeatable prompt-to-HTML pipeline that also runs in Codex.

Cursor says Composer 2.5 is 90% off in the SDK this weekend. Same-day posts also split between fast one-shot SDK builds and complaints about dropped connections, project controls, and agent follow-through compared with Codex, so test reliability before committing.

Skilled launched a CLI and TUI that scans installed skills across Claude Code, Codex, Droid, OpenCode and Grok Build. It surfaces dead skills, single-project dependencies and usage by agent or project, so teams can clean up skill sprawl.

Posts said Codex usage limits were reset across paid plans as users shared Mac app feedback, browser control, and repo-review results. The examples show Codex being used as a daily driver for debugging and code audit work, so watch the limits if you rely on it for regular use.

Anthropic's ClaudeDevs account said it reset everyone's 5-hour and weekly rate limits. The reset landed alongside paid-user complaints about slow sessions and visible switching pressure toward Codex, without a root-cause or permanent policy change attached.

ChatGPT opened a Codex mobile preview that lets users review outputs, approve commands, inspect diffs, and steer long-running agent work from a phone. It matters because Codex jobs no longer stay desktop-bound, though early users say the flow can still depend on a battery-draining host machine and a clunky app UI.

Creators shared a Codex and GPT Image 2 workflow that outputs static HTML landing pages whose scenes shift by season and local time. The setup gives humans a cleaner format to review, tweak, and navigate than Markdown when agents generate multi-scene pages.

Creators used GPT Image 2 for storyboard sheets, brand books, posters, and campaign visuals across Firefly, Paper, Codex, and Leonardo. The shift turns it into a preproduction tool, but tests still report inconsistent guideline adherence without extra context.

OpenAI Codex CLI v0.129.0 adds Vim mode, redesigned resume flows, stronger plugin management, and hook controls, while GOALS also reached the Linux app. The update makes long-running refactors and persistent task loops more structured across CLI and app use.

Users report OpenAI increased Codex limits about 10x on the May 5 reset, with much longer /goal sessions and more computer-use demos. That should extend unattended runs for app migrations and visual prototyping.

Weekend builder posts showed OpenAI Codex using /goal to keep working across turns, with Linux clients and ephemeral runner tools extending longer sessions. It matters for vibe-coders packaging Codex into unattended loops, but usage limits and community wrappers still vary by plan and platform.

Multiple practitioners showed Codex reviewing every main-branch commit, spawning fix loops, and opening browser sessions when APIs or web apps blocked the normal path. The workflow matters because Codex is being used as a browser-native coworker for coding, writing, analytics, and media plugins, but the pattern is emerging from user experiments rather than a formal OpenAI release.

Codex App Server added a Fedora RPM package for Linux installs as users pushed Codex into browser control, 3D-print setup, and rapid game prototypes. Watch for more repeatable desktop workflows as Codex moves beyond chat-only experiments.

OpenAI launched GPT-5.5 in ChatGPT and Codex for coding, computer use, docs, sheets, and longer tool-driven tasks. Early tests showed stronger games and frontend builds, while pricing jumped again and Opus 4.7 comparisons started immediately.

Creators used GPT Image 2 to turn single photos into brand books, generate 360 panoramas, lay out recipe pages and shortcut charts, and produce scannable QR codes or plate-solvable star fields. That matters because the model is now being used for structured design work, not just single hero images.

OpenAI updated Codex with Mac app control, background computer use, image tools, ongoing tasks, and 90+ plugins, while Remotion added a one-click skill. Agents can now work inside desktop creative apps and stacks without blocking the visible cursor.