adversarial-review

adversarial-review is a command for Claude Code from Kenmege/codex-claude-companion. It costs 12 tokens per session (356 once invoked), scanned A, original, Apache-2.0.

A read-only code review that asks Claude to challenge the current design and look for overlooked problems.

In plain words
What is it for?
Use it for a deeper review of a Git workspace, with optional controls for Claude's tools, budget, extra directories, and prompt.
Why use it?
It checks how code is used across the repository, including downstream callers and missing tests, so design weaknesses are easier to spot.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions Codex.

Good fit Use it for a deeper review of a Git workspace, with optional controls for Claude's tools, budget, extra directories, and prompt.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kenmege/codex-claude-companion/adversarial-review
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/Kenmege/codex-claude-companion

Made for: Claude Code.

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.

agentmods badge for adversarial-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/adversarial-review/github.svg)](https://agentmods.dev/commands/kenmege/codex-claude-companion/adversarial-review)
Your own site
<a href="https://agentmods.dev/commands/kenmege/codex-claude-companion/adversarial-review"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/adversarial-review/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.

agentmods 80×15 button for adversarial-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/kenmege/codex-claude-companion/adversarial-review"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/adversarial-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 356 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00356
Opus 5 $0.00006 $0.00178
Sonnet 5 $0.00002 $0.00071
Haiku 4.5 $0.00001 $0.00036

Measured 12d ago against content hash 874fe4f51e62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

adversarial-review 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 12d 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.

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.

commands/adversarial-review.md · 50 lines

What it actually says

/claude-review:adversarial-review

Preflight

  1. Prefer the helper binary codex-claude if it is available on PATH.
  2. If it is not available, tell the user to install the helper with npm install -g codex-claude-companion after npmjs publish, or from a cloned checkout with npm install -g ..

Plan

Runs an agentic adversarial review pass. Claude (Opus alias default, xhigh effort) gets read-only Read/Glob/Grep/Bash/Task/WebFetch/WebSearch tools so it can verify call sites, downstream consumers, and test gaps before challenging the design. Returns the helper output without paraphrasing it.

Commands

Use the exact argument tail the user supplied after /claude-review:adversarial-review.

  • Preferred: codex-claude adversarial-review <user-arguments>

Useful flags:

  • --legacy to disable agentic mode (structured-output only).
  • --mcp-config, --max-budget-usd, --add-dir, --system-prompt-extra for workspace-specific control.

Keep this command read-only. The agent is restricted to read-only tools.

Verification

If the helper exits non-zero, report that failure exactly and stop.

Summary

Return the helper stdout verbatim.

Next Steps

If the user wants a persistent record, suggest --background plus /claude-review:status. If they want the most exhaustive lane, suggest /claude-review:elite-review.

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. 12d ago First seen · 50 lines · 12 tokens per session scan A 874fe4f51e62

Subscribe to this mod's changes

adversarial-review is a command published in the GitHub repository Kenmege/codex-claude-companion (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 12 tokens to every session and 356 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.