CritiqueCode vs Codex
OpenAI Codex CLI is a terminal coding agent with review, exec, and optional cloud handoff. CritiqueCode is Critique’s author agent with forced review. If you already like Codex, keep it and add a sidecar.
CritiqueCode vs Codex
Keep, switch, or combine.
critique.sh
Pick OpenAI Codex when you want OpenAI’s local terminal agent (codex): inspect, edit, run tools on the machine, optional /review, codex exec for scripts, and the CLI/cloud loop OpenAI documents. Pick CritiqueCode when you want Critique to author the change in an interactive Pi session, then force independent review before “done” means anything. If you already use Codex, do not install CritiqueCode as a sidecar. Install @critiquedotsh/cli (binary critique) and keep Codex as the author. CritiqueCode is @critiquedotsh/harness (binary critique-code).
CritiqueCode vs Codex usually hides two different questions. One is “which terminal agent should write the patch?” The other is “who is allowed to treat that patch as finished?” Those are not the same product decision.
Codex CLI is good at the first question. Official OpenAI docs describe a local coding agent that inspects files, makes edits, runs the tools already on your machine, and stays in one terminal loop. You can run it interactively, call codex exec from scripts, run /review without writing the tree, and (if you want OpenAI’s product) hand work to Codex cloud from the CLI. Teams should keep it when that is the author they already pay for and know how to steer.
CritiqueCode is built for the second question. It is an interactive author session that implements, then the Author Coordinator forces runLocalCritiqueCodeReview. Author transcripts never become Evidence. /review and /ship own promotion. Read the product intro in CritiqueCode and the install contract in the CritiqueCode docs. For the three-way IDE vs CLI vs forced-review map, see Cursor vs Codex vs CritiqueCode. For the wider verification argument, see best coding agent 2026.
CritiqueCode vs Codex at a glance
| Dimension | OpenAI Codex CLI | CritiqueCode |
|---|---|---|
| Job | OpenAI’s local coding agent: inspect, edit, run installed tools, automate repeatable work from the terminal. | Critique author agent: implement in session, then forced review and verified repair before promotion. |
| Runtime | Interactive TUI (codex with no subcommand). Also IDE extension, desktop app (codex app), and Codex web/cloud as OpenAI documents them. | Interactive Pi author session in the target repo. Process uses cwd. Slash commands stay in the TUI and are never sent to the model. |
| Review | /review can inspect uncommitted changes, a commit, or a base branch without modifying the working tree. Still the same product family reviewing Codex-shaped work. | After a claimed unit of work, or a write-budget trip, the Author Coordinator forces runLocalCritiqueCodeReview as the only review entry. |
| Evidence | Session transcript, tests it ran, git checkpoints around a task, and whatever /review reports. The same product that wrote the change can also narrate why it is done. | Author check output and author transcripts are never Evidence and never leak into specialist or adjudicator prompts. Promotion stays on /review and /ship. |
| Automation | codex exec for non-interactive scripts and CI. Skills, plugins, MCP (codex mcp), live search (--search), resume (codex resume), images (--image). | You approve each critique_run. The model cannot run a process, pick a working directory, or request network on its own. |
| Install | Official installer (curl -fsSL https://chatgpt.com/codex/install.sh | sh on macOS/Linux), Windows install script, npm install -g @openai/codex, Homebrew cask codex, or a GitHub release binary. Then cd into a project and run codex. | npm install --global @critiquedotsh/harness, then cd into the repo you want to edit and run critique-code. Keys live in ~/.critique/code/. |
| Auth and models | First run: Sign in with ChatGPT or another method OpenAI documents. Choose model and reasoning effort with /model. Config defaults live in ~/.codex/config.toml. | OpenRouter default when OPENROUTER_API_KEY is set, else Critique Inference critique/auto, then Anthropic, OpenAI, LLM Gateway, Vercel AI Gateway, or a custom OpenAI-compatible endpoint. |
What CritiqueCode actually does
You run critique-code in the repository you want to change. You talk to it like other terminal coding agents: describe the work, approve tool use, watch files get written. The model can call critique_run. You approve or deny each request in the TUI. The model cannot run a process, pick a working directory, or request network on its own.
That is the author half. The controller half is the point of the product. When the author claims a unit of work complete, the Author Coordinator captures a Change Capsule and runs local CritiqueCode review. Specialists never author the product. none_promoted is not a correctness proof. Quiet review is still not a guarantee.
/review and /ship, not because the author said the tests were green.What Codex CLI is, from OpenAI’s docs
OpenAI’s Codex CLI docs describe a local terminal agent: inspect files, make edits, run the tools already installed on the machine, and automate repeatable work without leaving the terminal. You stay in control of model, reasoning effort, permissions, and commands. Interactive mode is the default. codex exec is the non-interactive path for scripts and pipelines.
Install paths OpenAI documents: the standalone macOS/Linux installer (curl -fsSL https://chatgpt.com/codex/install.sh | sh), the Windows PowerShell installer, npm (@openai/codex), Homebrew (brew install --cask codex), or a GitHub release binary. Open a project directory and run codex. First run: Sign in with ChatGPT or another available method. Permissions live on /permissions. You can inspect the active sandbox and writable roots before continuing. OpenAI’s GitHub README notes native Windows support exists, and WSL2 is recommended when you want more mature sandbox behavior.
The CLI is not only a chat box. Official docs cover /init for AGENTS.md, /status, /model, /review (uncommitted, commit, or base-branch presets without writing the tree), skills and plugins, MCP (codex mcp), live web search (--search), images (--image), session resume (codex resume), subagents, shell completions, and codex cloud to submit work to a configured environment and apply the result locally. That is a strong, documented product. This post does not invent extra capabilities, and it does not argue that you should throw it away.
Many teams should keep Codex. If the agent already matches how you write software, the expensive mistake is ripping it out because a comparison table exists. The cheaper move is to put an independent finish pass next to it. Codex /review is useful. It is still Codex reviewing Codex-shaped work inside the same product family.
If you already use Codex, install the sidecar
This is the mix-up that will waste a Saturday. Critique ships two packages in the same npm org. They are not aliases. They are not a rename.
| You already have | Install | Binary | Job | |
|---|---|---|---|---|
| Codex (keep it) | Codex CLI as the author | @critiquedotsh/cli | critique | Sidecar reviewer. Independent finish pass. Not CritiqueCode. |
| Want Critique to author | No existing author, or you want Critique’s loop | @critiquedotsh/harness | critique-code | Author agent with forced local review and verified repair. |
The local path is the whole recommendation. Run Codex (or CritiqueCode) in the repo on disk. If you keep Codex, the sidecar is critique. If you want Critique to write the change, the binary is critique-code. That is the split. It is documented in CritiqueCode and in the introducing CritiqueCode post. This comparison does not recommend a remote execution host as a substitute for either CLI.
- 1Do you already use Codex CLI and like the author loop?Keep Codex. Install
@critiquedotsh/cliand usecritiqueas the independent sidecar. Do not replace Codex with CritiqueCode unless you want Critique to author. - 2Do you want the author itself to be forced through Critique review?Install
@critiquedotsh/harness,cdinto the target repo, and runcritique-code. You approvecritique_run. The coordinator forcesrunLocalCritiqueCodeReview./reviewand/shipown promotion. - 3Were you told to “just use CritiqueCode” on top of Codex as a plugin?Wrong product. Sidecar for an existing agent is
@critiquedotsh/cli(critique). CritiqueCode is the author binarycritique-code. - 4Do you want OpenAI’s
codex exec, plugins, MCP, or Codex cloud handoff?Stay on Codex CLI for those surfaces. CritiqueCode vs Codex is a local author-and-review contract. Add the sidecar if you want an independent finish pass after Codex.
FAQ
critique as the sidecar. Switch to critique-code only when you want Critique to implement, then survive forced review.