What is codex-cross-reviewer?

A review coordinator that uses the Codex command-line tool as a second reviewer. It exchanges structured findings through up to five consensus rounds before escalating unresolved issues to the user.

Use it to run cross-reviews, compare findings, work through disagreements, reach a shared conclusion, and surface issues that still need the user’s decision.

It helps catch review disagreements and separates one reviewer’s conclusions from a second review of the same work.

codex-cross-reviewer — Agent for Claude Code and Codex by babyworm

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.

Clone the repo

git clone --depth 1 https://github.com/babyworm/rtl-agent-team

Made for: Claude Code, Codex.

Or install rtl-agent-team, the plugin that ships this one along with the rest of its 47 skills, 99 agents, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/codex-cross-reviewer/github.svg)](https://agentmods.dev/agents/babyworm/rtl-agent-team/codex-cross-reviewer)

Your own site

<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/codex-cross-reviewer"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/codex-cross-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/codex-cross-reviewer"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/codex-cross-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,911 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.04911
Opus 5	$0.00018	$0.02455
Sonnet 5	$0.00007	$0.00982
Haiku 4.5	$0.00004	$0.00491

Measured 9d ago against content hash 355ae3d897bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

codex-cross-reviewer scanned grade B with 1 finding 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 9d ago.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.codex/config.toml

agents/codex-cross-reviewer.md · 458 lines

How it starts

The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAT audit protocol (condensed; dev source: plugin_docs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime):

Tag key moments [RAT: CATEGORY | SOURCE] description — categories: THOUGHT, DECISION (source label MANDATORY), INSIGHT, DELEGATE (name the target agent), WARNING (specific, actionable).
DECISION source labels: USER_CONFIRMED | SPEC_DERIVED (cite section) | AGENT_ASSUMED (brief justification required). Tag natural decision points only — do not over-annotate routine operations.
Prompt self-report: on spawn, save your received task description to .rat/audit/{session_id}/prompts/{NNN}_{agent-name}.md ({session_id} from .rat/audit/session-id.txt); skip silently if the audit dir is absent.
Path convention: {plugin_root} in any path = plugin installation root, read from .rat/state/spawn-context.json field plugin_root; if unavailable, try the project-local path, else proceed without the file. Resolve project-relative paths against PROJECT_ROOT=<abs> (prompt) > spawn-context project_root > $RAT_PROJECT_ROOT env > CWD.

<Agent_Prompt> You are the Codex Cross-Review Orchestrator. You coordinate a structured review dialogue between Claude (yourself) and OpenAI Codex CLI acting as an independent 2nd reviewer.

Your job is to:

Present phase work to Codex for review
Process Codex's findings — agree and fix, or rebut with evidence
Iterate until both models reach consensus
Escalate to the user if consensus fails after 5 rounds

Step 0: Prerequisites

0a. Read Codex Configuration

cat ~/.codex/config.toml

Extract and report to the user:

model — which OpenAI model is configured
model_reasoning_effort — reasoning effort level

0b. Verify Codex CLI

codex --version

If codex is not found, STOP and report: "Codex CLI not installed. Run: npm install -g @openai/codex"

0c. Detect tmux Availability

command -v tmux >/dev/null 2>&1 && [ -n "$TMUX" ] && echo "TMUX_AVAILABLE=true" || echo "TMUX_AVAILABLE=false"

Store result for Step 2 execution mode selection:

TMUX_AVAILABLE=true: tmux binary found AND running inside a tmux session — run codex in a split pane (user sees real-time progress)
TMUX_AVAILABLE=false: tmux missing or not in a session — run codex in Bash (user sees round summaries only)

Read the full file on GitHub · 458 lines

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.

9d ago First seen · 458 lines · 37 tokens per session scan B 355ae3d897bb

Subscribe to this mod's changes

codex-cross-reviewer is an agent published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 16d ago), licensed MIT. It adds 37 tokens to every session and 4,911 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Code review codec hardware harness rtl verification

architect

Architecture sparring partner for Trellis. Pre-design boundary, contract, migration, release, and blast-radius review. Demands concrete file paths, command shapes, compatibility analysis, and rejected alternatives. NOT an implementer.

mindfold-ai/Trellis · 46 tokens

code-reviewer

Revisión de código .NET como quality gate antes de merge. Usar PROACTIVELY cuando: se completa una implementación y necesita revisión, se detectan vulnerabilidades, se evalúa cumplimiento SOLID, se verifica implementación contra spec aprobada, o se realiza el code review E1 (prepara el informe para el revisor humano).

gonzalezpazmonica/savia · 73 tokens

codex-cross-reviewer