grok-cli

grok-cli is a skill for Claude Code from amirkiarafiei/subagent-cli-skills. It costs 85 tokens per session (2,012 once invoked), scanned A, original, MIT.

A skill for handing large, multi-step coding work to the Grok command-line tool in a separate session. It passes the main task, decisions, scope, and limits so that session can work independently.

In plain words
What is it for?
Use it for multi-file changes, broad refactoring, repository exploration, batch edits, and other reasoning-heavy work. It can also limit the run or return structured results for another program to read.
Why use it?
It keeps long tasks from using up the main conversation's context and separates broad work from the current coding session. The documentation is not verified against an installed Grok CLI, so its commands should be checked first.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions OpenCode.

Good fit Use it for multi-file changes, broad refactoring, repository exploration, batch edits, and other reasoning-heavy work. It can also limit the run or return structured results for another program to read.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amirkiarafiei/subagent-cli-skills/grok-cli
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.

Any agent
npx skills add amirkiarafiei/subagent-cli-skills --skill grok-cli
Clone the repo
git clone --depth 1 https://github.com/amirkiarafiei/subagent-cli-skills

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/amirkiarafiei/subagent-cli-skills/grok-cli.svg)](https://agentmods.dev/skills/amirkiarafiei/subagent-cli-skills/grok-cli)
Your own site
<a href="https://agentmods.dev/skills/amirkiarafiei/subagent-cli-skills/grok-cli"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/subagent-cli-skills/grok-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,012 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00085 $0.02012
Opus 5 $0.00043 $0.01006
Sonnet 5 $0.00017 $0.00402
Haiku 4.5 $0.00009 $0.00201

Measured today against content hash 3e9a4a847527, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/grok-cli/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grok CLI (subagent/task delegation)

Documented, not verified. Written from xAI's published CLI docs on 2026-09-06 and not checked against an installed binary. Before trusting any flag here, run grok --help; on a mismatch use what the binary actually offers and tell the user which line in this file is wrong.

Use Grok CLI to run a separate long-horizon pass over the repo: multi-step implementation, broad refactors, batch file writes, or deep exploration—similar to handing a task to a subagent. You stay orchestrator: smaller prompts, less context burn, often lower spend than doing the same work in-session.

When to use Grok CLI

  • Large or multi-step work: several files, phases, or checkpoints (feature slice, migration, test suite, docs sweep).
  • Reasoning-heavy passes: --effort exposes a reasoning-effort control for harder problems.
  • Machine-readable results: --output-format json returns one JSON object; streaming-json emits newline-delimited events for progress.
  • Bounded runs: --max-turns caps how many agent turns a delegation may take.
  • User explicitly asks for Grok or "use Grok for this."

When not to use

  • Small / single-step tasks answerable with one or two edits or a short explanation.
  • Tight feedback loops where the user wants rapid back-and-forth refinement in one thread.
  • Secrets or policy-sensitive flows—avoid piping credentials; redact before delegating.
  • Already-loaded context where duplicating the whole plan adds no value—handle locally.
  • Low ROI (Return on Investment): if the task requires high precision over a single line, or composing the Handoff Table costs more than editing the file yourself. Delegate only when the "mental offloading" outweighs the "handoff overhead."

Delegation and context (critical)

Isolated subagent context saves tokens but splits the story: Grok does not see the main session's full thread. Poor handoffs cause misread subtasks, conflicting assumptions (stack, style, APIs), and wasted edits.

Read the full file on GitHub · 137 lines

Files

What ships with it

1 file 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.

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. today First seen · 137 lines · 85 tokens per session scan A 3e9a4a847527

Subscribe to this mod's changes

grok-cli is a skill published in the GitHub repository amirkiarafiei/subagent-cli-skills (5 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 2,012 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 2026-09-08.