codex

A project command that delegates a review or coding task to the OpenAI Codex command-line tool, which runs Codex from a terminal.

In plain words
What is it for?
Reviewing uncommitted or branch changes, sending a custom review request, and delegating a specified task to Codex in read-only mode.
Why use it?
It standardizes how the project asks Codex to review changes or perform work, including safer defaults for reviewing files.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/mathaix/openclawmachines/codex
Clone the repo
git clone --depth 1 https://github.com/mathaix/OpenClawMachines

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 363 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00363
Opus 5 $0.00000 $0.00181
Sonnet 5 $0.00000 $0.00073
Haiku 4.5 $0.00000 $0.00036

Measured yesterday against content hash 621425fd458e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/codex.md · 50 lines

What it actually says

Delegate a task to OpenAI Codex CLI for review or execution.

Arguments

  • $ARGUMENTS — the prompt or instructions to send to Codex. If empty, defaults to reviewing the current branch changes.

Instructions

Review mode (default when no arguments or arguments mention "review")

If the user provides no arguments, or the arguments are about reviewing something:

codex review --base main --title "Review from Claude Code"

If the user specifies a custom review prompt:

codex review --base main "CUSTOM_PROMPT_HERE"

If reviewing uncommitted changes specifically:

codex review --uncommitted

Exec mode (when arguments describe a task to perform)

If the user provides a task prompt (not a review), use exec mode:

codex exec --sandbox read-only "PROMPT_HERE"

Use read-only sandbox by default for safety. Only use workspace-write if the user explicitly asks Codex to make changes.

Choosing the mode

  • No arguments → codex review --uncommitted (review current changes)
  • Arguments mention a file path (e.g., docs/plans/foo.md) → codex exec --sandbox read-only "Review the design document at [path]. Check for technical feasibility, gaps, and inconsistencies. Categorize findings as CRITICAL, IMPORTANT, or MINOR."
  • Arguments are a general task → codex exec --sandbox read-only "ARGUMENTS"

Running

Run the codex command via the Bash tool. The command may take a few minutes. Use a 600000ms (10 minute) timeout.

Report the full output back to the user.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 50 lines · 0 tokens per session scan A 621425fd458e

Subscribe to this mod's changes

codex is a command published in the GitHub repository mathaix/OpenClawMachines (57 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 363 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.