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.
npx agentmods add commands/dysfunc/ai-plugins-cc/adversarial-reviewgit clone --depth 1 https://github.com/dysfunc/ai-plugins-ccWrote 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/dysfunc/ai-plugins-cc/adversarial-review)<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>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 | $0.00012 | $0.00842 |
| Opus 5 | $0.00006 | $0.00421 |
| Sonnet 5 | $0.00002 | $0.00168 |
| Haiku 4.5 | $0.00001 | $0.00084 |
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.
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.
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 --cachedandgit 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 --shortstatis 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.
- For working-tree review, start with
- 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 parses
--waitand--background, but Claude Code'sBash(..., run_in_background: true)is what actually detaches the run. /gemini:adversarial-reviewuses the same review target selection as/gemini:review.- It supports working-tree review, branch review, and
--base <ref>. - It does not support
--scope stagedor--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 "$ARGUMENTS"
- Return the command stdout verbatim, exactly as-is.
- Do not paraphrase, summarize, or add commentary before or after it.
- Do not fix any issues mentioned in the review output.
Background flow:
- Launch the review with
Bashin the background:
Bash({
command: `node "${CLAUDE_PLUGIN_ROOT}/scripts/gemini-companion.mjs" adversarial-review "$ARGUMENTS"`,
description: "Gemini adversarial review",
run_in_background: true
})
- Do not call
BashOutputor wait for completion in this turn. - After launching the command, tell the user: "Gemini adversarial review started in the background. Check
/gemini:statusfor progress."
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.
- 4d ago First seen · 67 lines · 12 tokens per session scan A 6e47c23b62ab
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.
Other commands, from other repositories
ask
Query multiple AI agents (Gemini, OpenAI, Grok, Perplexity, Kimi, and a local ollama model) for diverse perspectives on architecture decisions, technology choices, debugging dead-ends, and security tradeoffs. Use this whenever the user names the council directly, whatever the topic — ask the council, council review…
result
Fetch, list, or cancel background council jobs started with --async.
status
Check connectivity and configuration status of all council providers.
media
Understand an audio / video / image file — Antigravity (agy/Gemini) transcribes and analyzes it, returning a timestamped digest while the full transcript goes to a file.
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.
cloud-run-debug
Diagnose a failing Cloud Run service — Antigravity (agy/Gemini) digests the error logs cheaply, Claude infers the root cause and proposes a fix. Read-only by default; --apply writes the fix to a branch.