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.
git clone --depth 1 https://github.com/faeton/claude-grok-pluginWrote 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/plugins/faeton/claude-grok-plugin/grok)<a href="https://agentmods.dev/plugins/faeton/claude-grok-plugin/grok"><img src="https://agentmods.dev/badge/plugins/faeton/claude-grok-plugin/grok/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/faeton/claude-grok-plugin/grok"><img src="https://agentmods.dev/badge/plugins/faeton/claude-grok-plugin/grok.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
grok 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 yesterday.
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
{
"name": "grok",
"version": "0.6.0",
"description": "Consult xAI's Grok CLI from Claude Code for code review or arbitrary questions.",
"author": {
"name": "faeton"
}
}
What it installs
The manifest is a name and a version. 3 skills, 8 commands, 1 agent travel with it, and installing the plugin installs all of them — 231 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill grok-cli-runtime A 19 tokens
- Skill grok-prompting A 23 tokens
- Skill grok-result-handling A 18 tokens
- Command review A 14 tokens
- Command consult A 16 tokens
- Command adversarial-review A 17 tokens
- Command setup A 11 tokens
- Command rescue A 20 tokens
- Command status A 10 tokens
- Command result A 11 tokens
- Command cancel A 10 tokens
- Agent grok-consult A 62 tokens
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.
- yesterday Changed 0d42b1c18cf4
- 1mo ago First seen · 9 lines scan A 11f864f3975c
grok is a plugin published in the GitHub repository faeton/claude-grok-plugin (1 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
grok
Live X/web search, code review, and task delegation via Grok Build. Bundles a groksearch MCP tool usable by any MCP-capable coding agent.
cursor
Local Cursor Agent CLI delegation: multi family consults, Composer implementation in owned worktrees, review, resumable history, background jobs, and setup health checks.
grok-cc
Delegate and review code with the Grok CLI from Claude Code, like the codex plugin.
grok
Use Grok Build from Claude Code to review code or delegate tasks.
ai
Umbrella plugin: dispatch /ai:review|rescue|gater across configured providers, plus /ai:compare for fan-out.
gemini
Use Gemini from Claude Code to review code or delegate tasks.