grok-cli-runtime

grok-cli-runtime is a skill for Claude Code from arielaizn/grok-plugin-cc. It costs 73 tokens per session (1,327 once invoked), scanned A, original, MIT.

A reference guide to the media tools available through the Grok command-line program, including image creation, image editing, and two ways to generate video.

In plain words
What is it for?
Use it when a Grok command behaves unexpectedly, when connecting new Grok media features, or when checking which image and video tools a particular CLI version provides.
Why use it?
It prevents confusing tool names from causing failed requests, such as asking for a video tool that is not actually available. It also explains how text-to-video work is assembled from an image and an animation step.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the grok plugin — 3 skills, 9 commands, 1 agent shipped together

Install

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.

agentmods
npx agentmods add skills/arielaizn/grok-plugin-cc/grok-cli-runtime
Any agent
npx skills add arielaizn/grok-plugin-cc --skill grok-cli-runtime
Clone the repo
git clone --depth 1 https://github.com/arielaizn/grok-plugin-cc

Made for: Claude Code.

Or install grok, the plugin that ships this one along with the rest of its 3 skills, 9 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 grok-cli-runtime

README.md
[![agentmods](https://agentmods.dev/badge/skills/arielaizn/grok-plugin-cc/grok-cli-runtime.svg)](https://agentmods.dev/skills/arielaizn/grok-plugin-cc/grok-cli-runtime)
Your own site
<a href="https://agentmods.dev/skills/arielaizn/grok-plugin-cc/grok-cli-runtime"><img src="https://agentmods.dev/badge/skills/arielaizn/grok-plugin-cc/grok-cli-runtime.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,327 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 $0.00073 $0.01327
Opus 5 $0.00036 $0.00664
Sonnet 5 $0.00015 $0.00265
Haiku 4.5 $0.00007 $0.00133

Measured 5d ago against content hash 4877e93d7ce2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

grok-cli-runtime 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 5d 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/grok/skills/grok-cli-runtime/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grok CLI runtime

How this plugin talks to the Grok CLI, and the details that are easy to get wrong.

The media toolset

Grok CLI 1.0 exposes exactly four media tools:

Tool Purpose
image_gen New image from a text prompt
image_edit Modify an existing image, given one or more source images
image_to_video Animate a still into a clip
reference_to_video Generate a clip guided by a reference image

There is no video_gen. The name appears in the binary's tool table but is never offered to the agent. Asking for it by name makes the model search MCP discovery for several turns and then report 'video_gen' is not a valid MCP tool name — a confusing failure that looks like a plugin bug.

So text-to-video is a two-step run: image_gen for the opening frame, then image_to_video to animate it. That is what /grok:video does, and both artefacts are kept.

To re-check the list on a new CLI version:

grok -p "List the exact names of every tool you have available that generates or edits images or video. Output only a comma-separated list. Do not call any tool." --always-approve --output-format json

Invocation

grok -p "<prompt>" --always-approve --output-format json --cwd <dir> \
     --disallowed-tools "run_terminal_command,search_tool,use_tool,..." --max-turns 6
  • --output-format json prints one envelope: { text, sessionId, usage, total_cost_usd, num_turns }. sessionId is the key to everything below.
  • --always-approve is required; a headless run otherwise blocks on tool approval.
  • --disallowed-tools is the single biggest lever on cost and latency. Without it the agent spends turns copying files with cp and hunting for tools through search_tool. Grok silently ignores names it does not recognise, so listing both run_terminal_command and the legacy run_terminal_cmd is safe.
  • --max-turns bounds a run that goes sideways.

Where generated files land

Grok writes media into its own session folder, not the working directory:

Read the full file on GitHub · 110 lines

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. 5d ago First seen · 110 lines · 73 tokens per session scan A 4877e93d7ce2

Subscribe to this mod's changes

grok-cli-runtime is a skill published in the GitHub repository arielaizn/grok-plugin-cc (6 stars, last pushed 22d ago), licensed MIT. It adds 73 tokens to every session and 1,327 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens