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 skills add scarletkc/agents --skill grok-cligit clone --depth 1 https://github.com/scarletkc/agentsWrote 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/skills/scarletkc/agents/grok-cli)<a href="https://agentmods.dev/skills/scarletkc/agents/grok-cli"><img src="https://agentmods.dev/badge/skills/scarletkc/agents/grok-cli/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/skills/scarletkc/agents/grok-cli"><img src="https://agentmods.dev/badge/skills/scarletkc/agents/grok-cli.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00066 | $0.01250 |
| Opus 5 | $0.00033 | $0.00625 |
| Sonnet 5 | $0.00013 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
grok-cli 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grok CLI
Use Grok Build as a separate coding agent on the same machine. The bundled
client launches grok agent --no-leader stdio, keeps its ACP session open,
and returns a task ID immediately. This is an external task: it does not
appear in Codex's native spawn_agent tree or inherit its conversation.
Grok Build must already be installed and configured. Use the project's
Python 3.12+ interpreter to run scripts/grok.py; the
client uses only the standard library. If the project has no interpreter,
uv run --python 3.12 <script> ... also works. Resolve the script relative
to this installed skill, not the repository being investigated.
Delegate a task
Give Grok the goal, absolute working directory, relevant files and evidence, scope boundaries, and the check that proves completion. It cannot see the conversation that led to the assignment. Keep independent work with the supervising agent while Grok runs.
Use a UTF-8 prompt file for substantial instructions. In these examples,
<script> is the absolute path to this skill's scripts/grok.py:
python <script> start --cwd <absolute-project-path> --prompt-file <task-file>
python <script> wait <task_id> --timeout 30
python <script> status <task_id>
python <script> reply <task_id> --prompt-file <follow-up-file>
python <script> cancel <task_id>
python <script> close <task_id>
Retain the returned task_id. Use wait when there is no independent work
left; its timeout returns the current state without cancelling the task.
Use reply after the current turn finishes to continue the same Grok
session. A running turn must finish or acknowledge cancellation before a
follow-up is accepted. Close the task once no more follow-ups are needed.
The helper's --help is the command reference. For output fields, storage,
timeouts, and troubleshooting, read references/client.md.
Configuration and permissions
Inherit Grok's model, authentication, and permission configuration unless the task requires a specific override. Subscription login, API keys, and configured providers are Grok's concern; do not change the user's configuration or choose another authentication route to get past a failure. The helper uses Grok's advertised noninteractive default authentication method when available. Interactive authentication is completed separately through Grok itself.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 116 lines · 66 tokens per session scan A 62b3a6057a5f
grok-cli is a skill published in the GitHub repository scarletkc/agents (208 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 1,250 once invoked, about $0.0003 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 2026-09-12.
Other skills, from other repositories
maintaining-windows-health
Hands-on playbook for Windows 11 disk cleanup, dev-machine optimization, and proactive health alerting. Use when the PC is full or slow, when a BSOD / Kernel-Power 41 / crash dump / commit-memory pressure happened, when the user asks to free disk space, audit storage, set up disk/memory alerts, or restore the same…
prompt-engineering
Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic…
installing-cli-tools
Install, upgrade, configure, and verify developer CLI tools safely. Use when a user asks to install a new CLI, command-line app, SDK tool, package-manager binary, GitHub release binary, language runtime tool, or AI/vendor CLI; configure shell PATH/completions; run first login; set API keys, tokens, or env variables…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
fetch-url-as-markdown
Fetch a web page (URL) and return clean Markdown via local trafilatura, with Exa MCP as a fallback for JS-rendered or anti-bot pages. Use when the user asks to read, fetch, scrape, summarize, or quote a URL — prefer this over the built-in WebFetch tool. Don't use for binary files (PDFs, images, archives) or for…
intuitive-preflight
Turn a vague task, plan, issue, or "LGTM/go ahead" request into an approval-ready preflight contract before implementation starts. Use when the user wants prompt preflight, clearer scope, non-goals, context package, acceptance criteria, definition of done, verification, stop gates, the exact execution command, or…