I find Codex CLI to be very good too, but it’s missing tons of features that I use in Claude Code daily that keep me from switching full time.
- Good bash command permission system
- Rollbacks coupled with conversation and code
- Easy switching between approval modes (Claude had a keybind that makes this easy)
- Ability to send messages while it’s working (Codex just queues them up for after it’s done, Claude injects them into the current task)
- Codex is very frustrating when I have to keep allowing it to run the same commands over and over, Claude this works well when I approve it to run a command for the session
- Agents (these are very useful for controlling context)
- A real plan mode (crucial)
- Skills (these are basically just lazy loaded context and are amazing)
- The sandboxing in codex is so confusing, commands fail all the time because they try to log to some system directory or use internet access which is blocked by default and hard to figure out
- Codex prefers python snippets to bash commands which is very hard to permission and audit
When Codex gets to feature parity, I’ll seriously look at switching, but until then it’s just a really good model wrapped in an okay harness
I don't think anyone can reasonably argue against Claude Code being the most full-featured and pleasant to use of the CLI coding agent tools. Maybe some people like the Codex user experience for idiosyncratic reasons, but it (like Gemini CLI) still feels to me rather thrown together - a Claude Clone with a lot of rough edges.
But these CLI tools are still fairly thin wrappers around an LLM. Remember: they're "just an LLM in a while loop with access to tool calls." (I exaggerate, and I love Claude Code's more advanced features like "skills" as much as anyone, but at the core, that's what they are.) The real issue at stake is what is the better LLM behind the agent: is GPT-5 or Sonnet 4.5 better at coding. On that I think opinion is split.
Incidentally, you can run Claude Code with GPT-5 if you want a fair(er) comparison. You need a proxy like LiteLLM and you will have to use the OpenAI api and pay per-token, but it's not hard to do and quite interesting. I haven't used it enough to make a good comparison, however.
> but it (like Gemini CLI) still feels to me rather thrown together - a Claude Clone with a lot of rough edges.
I think this is because they see it as a checkbox whereas Anthropic sees it as a primary feature. OpenAI and Google just have to invest enough to kill Anthropic off and then decide what their own vision of coding agents looks like.
Thick or thin, the wrapper so that users aren't manually copy and pasting code around is material to it being used and useful. Plus the systems prompt is custom to each tool and greatly affect how well the tool works.
You can actually use Codex right from Claude Code as an MCP without that proxy stuff and it works really well, especially for review or solving things Claude couldn't. Best of both worlds!
Yeah I think the argument is the tooling vs agent. Maybe the OpenAI agent is performing better now, but the tooling is significantly better from anthropic.
The anthropic (ClaudeCode) tooling is best-in-class to me. You listed many features that I have become so reliant on now, that I consider them the Ante that other competitors need to even be considered.
I have been very impressed with the Anthropic agent for code generation and review. I have found the OpenAI agent to be significantly lacking by comparison. But to be fair, the last time I used OpenAI's agent for code was about a month ago, so maybe it has improved recently (not at all unreasonable in this space). But at least a month ago when using them side-by-side the codex CLI was VERY basic compared to the wealth of features and UI in the ClaudeCode CLI. The agents for Claude were also so much better than OpenAI, that it wasn't even close. OpenAI has always delivered me improper code (non-working or invalid) at a very high rate, whereas Claude is generally valid code, the debate is just whether it is the desired way to build something.
Code is amazing. I'm not sure why OpenAI isn't using it as their default CLI. I was cancelling my membership and stumbled upon it right before, now I'm dropping my other subs to move to this.
I am not sure copying your competitors feature-by-feature is always a good strategy. It can make the onboarding of your competitor's users easier, but lead to a worse product overall.
This is especially the case in a fast moving field such as this. You would not want to get stuck in the same local minimum as your competitor.
I would rather we have competing products that try different things to arrive at a better solution overall.
I'm using opencode which I think is now very close to covering all the functionality of claude code. You can use GPT5 Codex with it along with most other models.
to fix having to approve commands over and over - use windows WSL. codex does not play nice with permissions/approvals on windows. WSL solves that completely
- Good bash command permission system
- Rollbacks coupled with conversation and code
- Easy switching between approval modes (Claude had a keybind that makes this easy)
- Ability to send messages while it’s working (Codex just queues them up for after it’s done, Claude injects them into the current task)
- Codex is very frustrating when I have to keep allowing it to run the same commands over and over, Claude this works well when I approve it to run a command for the session
- Agents (these are very useful for controlling context)
- A real plan mode (crucial)
- Skills (these are basically just lazy loaded context and are amazing)
- The sandboxing in codex is so confusing, commands fail all the time because they try to log to some system directory or use internet access which is blocked by default and hard to figure out
- Codex prefers python snippets to bash commands which is very hard to permission and audit
When Codex gets to feature parity, I’ll seriously look at switching, but until then it’s just a really good model wrapped in an okay harness