Codex CLI

I got it to connect by starting codex CLI with `codex remote-control` but it seems to be limited/sandboxed to a specific directory. In my case, I run all coding agents under a specific user, `agent`, and when I access it over remote from my phone, I seem to be limited to the working directory `/var/lib/agent/Documents/Code` with no obvious way to change this. It won't let me go to my existing project directories (including the directory where I started `codex remote-control`). I haven't tried symbolic links or anything complicated yet, as this is mostly just a novelty to me.

These can also be observed through OTEL telemetries. I use headless codex exec a lot, but struggles with its built-in telemetry support, which is insufficient for debugging and optimization. Thus I made codex-plus (https://github.com/aperoc/codex-plus) for myself which provides a CLI entry point that mirrors the codex exec interface but is implemented on top of the TypeScript SDK (@openai/codex-sdk). It exports the full session log to a remote OpenTelemetry collector after each run which can then be debugged and optimized through codex-plus-log-viewer.

The standard $20 plan, on my existing Godot code: https://github.com/InvadingOctopus/comedot Most of those commits since the last few months are thanks to Codex reviews (but the code is not AI generated): 5.5 since it came out, and 5.4 etc before that, almost always on Extra High because it's for a framework that underlies the other stuff I do so I want make to sure everything's correct. Sometimes I have to run multiple passes on the same task: I rarely continue any session beyond 4-5 prompts to avoid "bloat" or accumulate "stale context", so sometimes Codex finds different stuff in subsequent reviews of the same file/subsystem. The project is modular enough where each file can be considered standalone with only 1-2 dependencies, and I already used to write a lot of comments everywhere (something some people laughed at), so maybe that helps the AI along?

I think this is particularly evident with AI. The early adopters started years ago and they've seen improvements over time that they started attributing them to their own skill. They tell you that if you didn't spend years prompting the AI, it will be difficult to catch up. However, the exact opposite is happening. As the models get better, the need for the perfect prompt starts waning. Prompt engineering is a skill that is obsoleting faster than handwriting code. I personally started using codex in march and honestly, the hardest part was finding and setting up the sandbox. (I use limactl with qemu and kvm). Meanwhile the agentic coding part just works.