@DivyanshT91162: You can clone Andrej Karpathy’s entire AGENTS.md workflow into Codex in under 2 minutes. Just: 1. Open his repo 2. Copy…
Summary
A tweet explains how to clone Andrej Karpathy's AGENTS.md workflow into Codex by pasting the 65-line file into Global Custom Instructions, making Codex behave more like a structured autonomous coding agent.
View Cached Full Text
Cached at: 05/25/26, 08:48 AM
You can clone Andrej Karpathy’s entire AGENTS.md workflow into Codex in under 2 minutes.
Just:
- Open his repo
- Copy the 65-line AGENTS.md file
- Paste it into Codex → Global Custom Instructions
That’s it.
Now Codex starts behaving way more like a structured autonomous coding agent instead of a normal chatbot.
The wild part is how much better outputs get from a tiny config file.
Similar Articles
@Av1dlive: If you haven't set up Agents.md in Codex yet you can just copy the homework from Andrej Karpathy. Here's the exact setu…
A quick tip showing how to copy Andrej Karpathy's 65-line Agents.md config into Codex Global Custom Instructions for an effective minimalist setup.
@Saccc_c: Haven't configured Agents.md in Codex yet? You can directly copy Karpathy's homework — a 65-line minimal configuration that is concise and effective, perfect as a starting point for your global Agents.md rules. How to do it: directly copy this specification from the repository into Codex App's global custom...
Sharing Andrej Karpathy's 65-line minimal Agents.md configuration that can be directly copied into Codex App's global custom instructions as a starting point to improve AI coding agent behavior.
Codex for Everyday Work: AI Agents Beyond Coding
OpenAI's Codex has evolved from a coding tool into a general-purpose AI agent, now used by knowledge workers for research, coordination, and data analysis, reducing hours of work into minutes.
@daniel_mac8: Codex Pro tip: turn Codex into a research engineer. Take any new agent paper and: 1. Ask: “How would this work in Codex…
A tip for Codex users to implement agent research papers directly into their Codex environment using goal mode and local config, with SkillOpt as an example that improved a GPT-5.5 agent by +24.8 points.
@Av1dlive: 2 OpenAI engineers just gave a masterclass on how to build and ship apps using Codex they spent 16 mins on how Codex tu…
OpenAI engineers showcase Codex as an agent harness for software engineering, capable of reviewing code, splitting work across sub-agents, and running workflows autonomously, effectively turning one person into a full engineering team.