adversarial-review

adversarial-review is a command for coding agents from dysfunc/ai-plugins-cc. It costs 12 tokens per session (842 once invoked), scanned A, a copy of adversarial-review, Apache-2.0.

A command that asks Gemini to challenge the design and assumptions behind an implementation.

In plain words
What is it for?
Use it for a review-only critique of implementation choices, design decisions, and real-world risks.
Why use it?
It can expose weak tradeoffs, hidden assumptions, and ways an approach might fail beyond ordinary bug checking.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the gemini plugin — 3 skills, 4 commands, 1 agent shipped together

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.

agentmods
npx agentmods add commands/dysfunc/ai-plugins-cc/adversarial-review
Clone the repo
git clone --depth 1 https://github.com/dysfunc/ai-plugins-cc

Or install gemini, the plugin that ships this one along with the rest of its 3 skills, 4 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/dysfunc/ai-plugins-cc/adversarial-review.svg)](https://agentmods.dev/commands/dysfunc/ai-plugins-cc/adversarial-review)
Your own site
<a href="https://agentmods.dev/commands/dysfunc/ai-plugins-cc/adversarial-review"><img src="https://agentmods.dev/badge/commands/dysfunc/ai-plugins-cc/adversarial-review.svg" alt="Measured on agentmods" 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 842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 97% copy Near-identical to another mod 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 $0.00012 $0.00842
Opus 5 $0.00006 $0.00421
Sonnet 5 $0.00002 $0.00168
Haiku 4.5 $0.00001 $0.00084

Measured 4d ago against content hash 6e47c23b62ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

Origin

This is a copy

97% identical to adversarial-review — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/gemini/commands/adversarial-review.md · 67 lines

What it actually says

Run an adversarial Gemini review through the shared plugin runtime. Position it as a challenge review that questions the chosen implementation, design choices, tradeoffs, and assumptions. It is not just a stricter pass over implementation defects.

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 review and return Gemini's output verbatim to the user.
  • Keep the framing focused on whether the current approach is the right one, what assumptions it depends on, and where the design could fail under real-world conditions.

Execution mode rules:

  • If the raw arguments include --wait, do not ask. Run in the foreground.
  • If the raw arguments include --background, do not ask. Run in a Claude background task.
  • Otherwise, estimate the review size before asking:
    • For working-tree review, start with git status --short --untracked-files=all.
    • For working-tree review, also inspect both git diff --shortstat --cached and git diff --shortstat.
    • For base-branch review, use git diff --shortstat <base>...HEAD.
    • Treat untracked files or directories as reviewable work for auto or working-tree review even when git diff --shortstat is empty.
    • Only conclude there is nothing to review when the relevant scope is actually empty.
    • Recommend waiting only when the scoped review is clearly tiny, roughly 1-2 files total and no sign of a broader directory-sized change.
    • In every other case, including unclear size, recommend background.
    • When in doubt, run the review instead of declaring that there is nothing to review.
  • Then use AskUserQuestion exactly once with two options, putting the recommended option first and suffixing its label with (Recommended):
    • Wait for results
    • Run in background

Argument handling:

  • Preserve the user's arguments exactly.
  • Do not strip --wait or --background yourself.
  • Do not weaken the adversarial framing or rewrite the user's focus text.
  • The companion script parses --wait and --background, but Claude Code's Bash(..., run_in_background: true) is what actually detaches the run.
  • /gemini:adversarial-review uses the same review target selection as /gemini:review.
  • It supports working-tree review, branch review, and --base <ref>.
  • It does not support --scope staged or --scope unstaged.
  • Unlike /gemini:review, it can still take extra focus text after the flags.

Foreground flow:

  • Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/gemini-companion.mjs" adversarial-review "$ARGUMENTS"
  • Return the command stdout verbatim, exactly as-is.
  • Do not paraphrase, summarize, or add commentary before or after it.
  • Do not fix any issues mentioned in the review output.

Background flow:

  • Launch the review with Bash in the background:
Bash({
  command: `node "${CLAUDE_PLUGIN_ROOT}/scripts/gemini-companion.mjs" adversarial-review "$ARGUMENTS"`,
  description: "Gemini adversarial review",
  run_in_background: true
})
  • Do not call BashOutput or wait for completion in this turn.
  • After launching the command, tell the user: "Gemini adversarial review started in the background. Check /gemini: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. 4d ago First seen · 67 lines · 12 tokens per session scan A 6e47c23b62ab

Subscribe to this mod's changes

adversarial-review is a command published in the GitHub repository dysfunc/ai-plugins-cc (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 842 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to adversarial-review, differing in 18 lines, and is treated as a copy.