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 zachdunn/grok-plugin-claude-code/plugin install grok-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/zachdunn/grok-plugin-claude-code/adversarial-review)<a href="https://agentmods.dev/commands/zachdunn/grok-plugin-claude-code/adversarial-review"><img src="https://agentmods.dev/badge/commands/zachdunn/grok-plugin-claude-code/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 | $0.00320 |
| Opus 5 | $0.00007 | $0.00160 |
| Sonnet 5 | $0.00003 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
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 Grok review — same as /grok-cc:review but Grok assumes the change is wrong until proven otherwise and hunts hard for correctness, security, and edge-case bugs.
Raw slash-command arguments:
$ARGUMENTS
Core constraint:
- Review-only. Do not fix issues or apply patches. Return Grok's output verbatim.
Execution mode:
- Follow the same fg/bg logic as
/grok-cc:review: honor an explicit--wait/--background; otherwise estimate size withgit status/git diff --shortstat(orgit diff --shortstat <base>...HEAD) andAskUserQuestiononce, recommending background for anything non-trivial.
Run the review with --adversarial always set:
node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" review --adversarial <args>
- Pass the user's other arguments through unchanged. For a backgrounded run, use
run_in_background: true. - Return the companion's stdout as-is, findings first, ordered by severity.
If the companion reports Grok is unavailable, tell the user to run /grok-cc:setup.
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 · 31 lines · 14 tokens per session scan A cf4f92ad994b
adversarial-review is a command published in the GitHub repository zachdunn/grok-plugin-claude-code (30 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 320 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 2026-08-30.
Other commands, from other repositories
login
Sign in to Grok Build CLI using the default install path.
rescue
Hand a question or code review to xAI's Grok via the grok-consult subagent.
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
sync
Manually trigger plan-sync to update downstream task specs after implementation drift.
uninstall
Remove flow-next files from project.
test
Run Postman collection tests, analyze results, diagnose failures, and suggest fixes.