adversarial-review

adversarial-review is a command for Claude Code from faeton/claude-grok-plugin. It costs 17 tokens per session (294 once invoked), scanned A, original, MIT.

A read-only command that sends a focused code review to Grok, xAI's AI assistant, with extra instructions about what to inspect.

In plain words
What is it for?
Use it to review a selected scope, branch base, or model with a specific concern, then receive the review output.
Why use it?
It provides a separate review of the code without changing files, which can help uncover issues such as race conditions.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the grok plugin — 3 skills, 8 commands, 1 agent shipped together

Good fit Use it to review a selected scope, branch base, or model with a specific concern, then receive the review output.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add faeton/claude-grok-plugin
Claude Code
/plugin install grok

Made for: Claude Code.

Or install grok, the plugin that ships this one along with the rest of its 3 skills, 8 commands, 1 agent.

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/faeton/claude-grok-plugin/adversarial-review.svg)](https://agentmods.dev/commands/faeton/claude-grok-plugin/adversarial-review)
Your own site
<a href="https://agentmods.dev/commands/faeton/claude-grok-plugin/adversarial-review"><img src="https://agentmods.dev/badge/commands/faeton/claude-grok-plugin/adversarial-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 294 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 $0.00017 $0.00294
Opus 5 $0.00009 $0.00147
Sonnet 5 $0.00003 $0.00059
Haiku 4.5 $0.00002 $0.00029

Measured 8d ago against content hash a73b7631d1d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

plugins/grok/commands/adversarial-review.md · 28 lines

What it actually says

Run a Grok review with extra adversarial focus instructions. Same read-only guarantees as /grok:review; do not fix issues in this turn.

Raw slash-command arguments: $ARGUMENTS

  • Any non-flag text is the focus instruction for the reviewer (e.g. "hunt for race conditions in the new worker pool"). It is forwarded as the trailing positional text.
  • --scope, --base, --model pass through.
  • Execution mode (--wait / --background / ask once) follows the same rules as /grok:review.

Foreground:

node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" adversarial-review $ARGUMENTS

Background:

node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" adversarial-review --background $ARGUMENTS

Return the command stdout verbatim. If the companion reports a failure, return it verbatim.

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. 8d ago First seen · 28 lines · 17 tokens per session scan A a73b7631d1d0

Subscribe to this mod's changes

adversarial-review is a command published in the GitHub repository faeton/claude-grok-plugin (1 stars, last pushed 23d ago), licensed MIT. It adds 17 tokens to every session and 294 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.