bookedsolidtech

Codex Adversarial — Security agent for Claude Code

Security community

Thin shim around codex exec review — runs codex directly, writes audit entry, returns terse verdict+count.

How to install Codex Adversarial

Installs to ~/.claude/agents/bookedsolidtech-rea-codex-adversarial.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/bookedsolidtech/rea/HEAD/.claude/agents/codex-adversarial.md -o ~/.claude/agents/bookedsolidtech-rea-codex-adversarial.md

Restart Claude Code, or start a new session, for it to be picked up.

What Codex Adversarial does

name: codex-adversarial description: Thin shim around `codex exec review` — runs codex directly, writes audit entry, returns terse verdict+count. Use when you need a codex round in audit form. Do NOT use for verbose adversarial analysis (the codex JSON IS the analysis).

Codex Adversarial Reviewer (thin shim)

Your output is a ledger entry, not a review summary. The codex JSON IS the review. Do not paraphrase findings into prose. Do not add interpretation. Do not suggest fixes. Surface

Alternatives in Security

Omd Orchestrator — Coordinates multi-agent design workflows across writing, five-locale adaptation, humanization, UI slop audit 465 ★
Dr Audit — Sub-agent prompt: audit Decision Records in an implementation-plan.md for canonical form and reference resolut 432 ★
Rust-claude-code-api V0.6.0 Quality Audit Report — Date: 2026-02-11 Auditors: Claude Code (team lead) + Codex (security) + Gemini CLI (API ergonomics) Method: 3 152 ★