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.
/plugin marketplace add contrapuntal/antigravity-cli-plugin-cc/plugin install ask-antigravityWrote 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.
[](https://agentmods.dev/commands/contrapuntal/antigravity-cli-plugin-cc/adversarial-review)<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>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.
| Model | Per session | Once 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 |
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.
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:
$ARGUMENTS
Core constraint:
- This command is review-only.
- Do not fix issues, apply patches, or suggest that you are about to make changes.
- Your only job is to run the review and return Antigravity's output verbatim to the user.
- Keep the framing focused on whether the current approach is the right one, what assumptions it depends on, and where the design could fail under real-world conditions.
Execution mode rules:
- If the raw arguments include
--wait, do not ask. Run in the foreground. - If the raw arguments include
--background, do not ask. Run in a Claude background task. - Otherwise, estimate the review size before asking:
- Use
git status --short --untracked-files=allto see scope. - Use
git diff --shortstat --cachedandgit diff --shortstatfor working-tree changes. - Use
git diff --shortstat <base>...HEADif--base <ref>was passed. - Treat untracked files as reviewable work even when diff stats are empty.
- Recommend waiting only when the scoped review is clearly tiny (~1-2 files, no directory-scale change). Otherwise recommend background.
- When in doubt, run the review rather than declaring there is nothing to review.
- Use
- Then use
AskUserQuestionexactly once with two options, putting the recommended option first and suffixing its label with(Recommended):Wait for resultsRun in background
Argument handling:
- Preserve the user's arguments exactly.
- Do not strip
--waitor--backgroundyourself. - Do not weaken the adversarial framing or rewrite the user's focus text.
- The companion script accepts
--waitand--backgroundbut treats them as no-ops; Claude Code'sBash(..., run_in_background: true)is what actually detaches the run. - Free-form focus text after the flags is forwarded to Antigravity as the user-focus area.
Foreground flow:
- Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/antigravity-companion.mjs" adversarial-review "$ARGUMENTS"
- Return the command stdout verbatim, exactly as-is.
- Do not paraphrase, summarize, or add commentary before or after it.
- Do not fix any issues mentioned in the review output.
Background flow:
- Launch the review with
Bashin the background:
Bash({
command: `node "${CLAUDE_PLUGIN_ROOT}/scripts/antigravity-companion.mjs" adversarial-review "$ARGUMENTS"`,
description: "Antigravity adversarial review",
run_in_background: true
})
- Do not call
BashOutputor 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
BashOutputnotification from the harness. Do not poll temp directories, do not search for sidecar files (this plugin does not create any), and do not invokeagyor the companion script directly to "check status" — that runs a separate agy session and does not surface the in-flight one.
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.
- 6d ago First seen · 62 lines · 14 tokens per session scan A 68fbe2b35f7f
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.
Other commands, from other repositories
8eyes-copilot
Start a multi-agent review mission (Copilot CLI adapter notes).
review
Manage AO code reviews of a worker's PR.
tldr-review
One-line TLDR PR review comments (verdict first, no filler).
pr-review
Generate a PR review report aggregating quality scan, coverage, complexity, and breaking changes.
pr-manager
Comprehensive pull request management with ruv-swarm coordination for automated reviews, testing, and merge workflows.
gemini-validate
Get a Gemini second opinion on a plan, diff, or claim.