agentmods.dev

adversarial-review

adversarial-review is a command for Claude Code from LovelaceLoom/grok-plugin-cc. It costs 15 tokens per session (434 once invoked), scanned A, original, Apache-2.0.

A command that asks Grok to perform an adversarial review of the current code changes. Adversarial review means deliberately looking for ways a change could fail.

In plain words
What is it for?
Use it to review a local code diff for failure modes without applying fixes or patches.
Why use it?
It challenges confidence in a change by focusing on risks such as security boundaries, simultaneous operations, rollback problems, and damaged data.

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 — 8 skills, 21 commands, 2 agents, 3 hooks shipped together

not rated 5repo 1mo ago A scan 15 tokens original Apache-2.0

Good fit Use it to review a local code diff for failure modes without applying fixes or patches.

Compare 6 commands from other repositories ↓
View source ↗ LovelaceLoom/grok-plugin-cc
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 LovelaceLoom/grok-plugin-cc
Claude Code
/plugin install grok

Made for: Claude Code.

Or install grok, the plugin that ships this one along with the rest of its 8 skills, 21 commands, 2 agents, 3 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.

agentmods badge for adversarial-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/lovelaceloom/grok-plugin-cc/adversarial-review/github.svg)](https://agentmods.dev/commands/lovelaceloom/grok-plugin-cc/adversarial-review)
Your own site
<a href="https://agentmods.dev/commands/lovelaceloom/grok-plugin-cc/adversarial-review"><img src="https://agentmods.dev/badge/commands/lovelaceloom/grok-plugin-cc/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/lovelaceloom/grok-plugin-cc/adversarial-review"><img src="https://agentmods.dev/badge/commands/lovelaceloom/grok-plugin-cc/adversarial-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 434 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 $0.00015 $0.00434
Opus 5 $0.00008 $0.00217
Sonnet 5 $0.00003 $0.00087
Haiku 4.5 $0.00002 $0.00043

Measured 9d ago against content hash 6b4598305fdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 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.

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 · 42 lines

What it actually says

Run a Grok ADVERSARIAL review of the local diff. Unlike /grok:review, the prompt explicitly instructs Grok to try to break confidence in the change — defaulting to skepticism and prioritizing trust-boundary, concurrency, rollback, and data-integrity failures.

Raw slash-command arguments: $ARGUMENTS

Core constraint:

  • This command is review-only.
  • Do not fix issues, apply patches, or suggest that you are about to make changes.
  • Your only job is to run the adversarial review and return Grok's output verbatim to the user.

Execution mode rules:

  • If --wait is present, run in foreground.
  • If --background is present, run in a Claude background task.
  • Otherwise, estimate the size as in /grok:review and ask the user with AskUserQuestion (one call, two options, recommended first).

Foreground flow:

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

Return stdout verbatim. Do not paraphrase or add commentary.

Background flow:

Bash({
  command: `node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" adversarial-review "$ARGUMENTS"`,
  description: "Grok adversarial review",
  run_in_background: true
})

Then tell the user: "Grok adversarial review started in the background. Check /grok:status for progress."

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. 9d ago First seen · 42 lines · 15 tokens per session scan A 6b4598305fdd

Subscribe to this mod's changes

adversarial-review is a command published in the GitHub repository LovelaceLoom/grok-plugin-cc (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 434 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.

Claude CodeCode reviewai-assistantai-toolsclaude-code-plugindeveloper-tools
Related

Other commands, from other repositories

review

Multi-agent code review with parallel validation.

Joncik91/ucai · 7 tokens

gemini-validate

Get a Gemini second opinion on a plan, diff, or claim.

azmym/gemini-plugin · 13 tokens

open-pr

Create a pull request for the current branch following the the team's standard PR template.

carloshpdoc/ios-workflow-claude · 0 tokens

apollo-review

Review the completed migration for $ARGUMENTS against the original investigation and produce a detailed report.

carloshpdoc/ios-workflow-claude · 0 tokens

code-review

Review code quality applying DRY, SOLID, naming, and formatting standards.

carloshpdoc/ios-workflow-claude · 18 tokens

review-pr

Review the pull request $ARGUMENTS and post inline comments using the authenticated GitHub user.

carloshpdoc/ios-workflow-claude · 0 tokens