adversarial-review

adversarial-review is a command for Claude Code from contrapuntal/antigravity-cli-plugin-cc. It costs 14 tokens per session (818 once invoked), scanned A, original, Apache-2.0.

A review command that asks Antigravity to challenge the current implementation plan and design choices. It returns the review without changing the code.

In plain words
What is it for?
Use it to question architecture, trade-offs, design decisions, and how the implementation may behave in real-world conditions.
Why use it?
It helps expose weak assumptions, unsuitable approaches, and problems that a defect-only code review may miss.

Command for Claude Code

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

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 ask-antigravity plugin — 4 commands, 1 agent shipped together

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 contrapuntal/antigravity-cli-plugin-cc
Claude Code
/plugin install ask-antigravity

Made for: Claude Code.

Or install ask-antigravity, the plugin that ships this one along with the rest of its 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/contrapuntal/antigravity-cli-plugin-cc/adversarial-review.svg)](https://agentmods.dev/commands/contrapuntal/antigravity-cli-plugin-cc/adversarial-review)
Your own site
<a href="https://agentmods.dev/commands/contrapuntal/antigravity-cli-plugin-cc/adversarial-review"><img src="https://agentmods.dev/badge/commands/contrapuntal/antigravity-cli-plugin-cc/adversarial-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 818 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00818
Opus 5 $0.00007 $0.00409
Sonnet 5 $0.00003 $0.00164
Haiku 4.5 $0.00001 $0.00082

Measured 6d ago against content hash 68fbe2b35f7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/ask-antigravity/commands/adversarial-review.md · 62 lines

What it actually says

Run an adversarial Antigravity 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 Antigravity'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:
    • Use git status --short --untracked-files=all to see scope.
    • Use git diff --shortstat --cached and git diff --shortstat for working-tree changes.
    • Use git diff --shortstat <base>...HEAD if --base <ref> was passed.
    • Treat untracked files as reviewable work even when diff stats are empty.
    • Recommend waiting only when the scoped review is clearly tiny (~1-2 files, no directory-scale change). Otherwise recommend background.
    • When in doubt, run the review rather than declaring 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 accepts --wait and --background but treats them as no-ops; Claude Code's Bash(..., run_in_background: true) is what actually detaches the run.
  • Free-form focus text after the flags is forwarded to Antigravity as the user-focus area.

Foreground flow:

  • Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/antigravity-companion.mjs" adversarial-review "$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 "${CLAUDE_PLUGIN_ROOT}/scripts/antigravity-companion.mjs" adversarial-review "$ARGUMENTS"`,
  description: "Antigravity adversarial review",
  run_in_background: true
})
  • Do not call BashOutput or wait for completion in this turn.
  • After launching, tell the user the adversarial review is running in the background and the output will appear in chat when it finishes.
  • While waiting, completion arrives as a BashOutput notification from the harness. Do not poll temp directories, do not search for sidecar files (this plugin does not create any), and do not invoke agy or the companion script directly to "check status" — that runs a separate agy session and does not surface the in-flight one.
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. 6d ago First seen · 62 lines · 14 tokens per session scan A 68fbe2b35f7f

Subscribe to this mod's changes

adversarial-review is a command published in the GitHub repository contrapuntal/antigravity-cli-plugin-cc (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 14 tokens to every session and 818 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.