💥NEW: CODEX POWER USER GUIDE
3 rules that Codex power users follow to build better and get more done.
Rule 1: The Verify Rule
- Give Codex a way to verify its own work using browser use, computer use, and tests (and TDD).
- Frame your prompts as a goal (outcome + constraints + when to finish) instead of a task.
- Require Codex to gather evidence (test outputs, screenshots, exit codes) to prove success.
Rule 2: The Context Rule
- Onboard Codex like you would a new employee or teammate.
- Use Plugins to connect Codex to the tools and systems you use for development and knowledge work.
- Create your own Agent Skills to encode business processes and workflows + make them legible to Codex.
- Login to SaaS tools via Codex's in-app browser.
- Combine plugins, browser use and skills with Scheduled Tasks to put meaningful work on autopilot.
Rule 3: The Orchestrator Rule
- Let Codex prompt and manage itself (Codex is better at prompting Codex than me or you).
- Give Codex an outcome and ask it to spin up one or more threads to achieve it.
- Use ChatGPT Voice Mode to talk to Codex like a chief of staff, have it spin up new threads to do work and report back with results.
- Ask Codex to use subagents for planning, implementation and review.
Any Codex tips or best practices I missed that you'd add?
Watch my full full video guide (with examples and demos):
Every AI Agent Concept Explained Simply in 29 Minutes
Keeping up with AI agents is intimidating because of all the technical jargon (Harness? Loop?). So I made a video where I explain the 15 essential concepts you need to build and work with agents like Claude Code, Codex, and Grokbot. Every concept is explained in simple terms without any technical background assumed.
Watch if you're technical but like no-jargon explanations, or non-technical and looking to finally demystify how AI Agents work:
Every AI Agent Concept Explained Simply in 29 Minutes
Keeping up with AI agents is intimidating because of all the technical jargon (Harness? Loop?). So I made a video where I explain the 15 essential concepts you need to build and work with agents like Claude Code, Codex, and Grokbot. Every concept is explained in simple terms without any technical background assumed.
Watch if you're technical but like no-jargon explanations, or non-technical and looking to finally demystify how AI Agents work:
Gearing up for a big launch (more details soon) and planning it with Claude Code + @linear is such a joy.
Not only does this make project management easier, but the best part is that ALL my agents (Claude Code, GrokBot and Codex) all have read/ write access to Linear (via the connector / MCP) so I can ask any one of them to take action on a card or update context for me.
Gearing up for a big launch (more details soon) and planning it with Claude Code + @linear is such a joy.
Not only does this make project management easier, but the best part is that ALL my agents (Claude Code, GrokBot and Codex) all have read/ write access to Linear (via the connector / MCP) so I can ask any one of them to take action on a card or update context for me.
I spent 30 mins doing a pen and paper braindump this morning, then sent a picture of the paper to Claude (Opus 5.5).
It not only perfectly transcribed and organized everything, but it understood shorthand and acronyms in the context of my business and other chats (I was very impressed).
Ended by creating Linear issues for everything so that we can have Codex, Claude and GrokBot easily access and take action on them.
What a time to be alive.
My very unofficial and very vibes based Agent ranking (October 2026 edition)
Best coding agent: Claude Code with Opus 5.5 (Desktop App)
Best browser use and computer use agent: ChatGPT Codex (Desktop App)
Best personal / business agent: GrokBot
Those cover 95% of my agent work
@ericzakariasson@bot@poteto That is the workaround I use now :) I don't really want to have the daily routine though (feels odd for some reason), but maybe that's just me.
Claude has this option to set a private GitHub repo as a marketplace URL fwiw.
My very unofficial and very vibes based Agent ranking (October 2026 edition)
Best coding agent: Claude Code with Opus 5.5 (Desktop App)
Best browser use and computer use agent: ChatGPT Codex (Desktop App)
Best personal / business agent: GrokBot
Those cover 95% of my agent work
Day 25/
We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today.
We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage.
And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.
@DanielPrevoznik I tend to be careful not to try automated browser use on sites I've heard folks get into trouble for around ToS violations (eg. Meta Ads, Google Ads etc)
Otherwise, it's mostly various small biz / creator SaaS platforms that don't have good MCPs / CLIs yet.
I spent 30 mins doing a pen and paper braindump this morning, then sent a picture of the paper to Claude (Opus 5.5).
It not only perfectly transcribed and organized everything, but it understood shorthand and acronyms in the context of my business and other chats (I was very impressed).
Ended by creating Linear issues for everything so that we can have Codex, Claude and GrokBot easily access and take action on them.
What a time to be alive.
The X Subscription might be the most value-dense subscription of 2026.
Insane to get access to Cursor, GrokBot, X all in just one subscription (very reasonably priced I might add).
The X Subscription might be the most value-dense subscription of 2026.
Insane to get access to Cursor, GrokBot, X all in just one subscription (very reasonably priced I might add).