grok-cli-runtime

grok-cli-runtime is a skill for Claude Code from davit-khaburdzania/grok-plugin-cc. It costs 19 tokens per session (928 once invoked), scanned A, original, Apache-2.0.

An internal helper contract for sending requests to the Grok runtime from a Claude Code rescue agent. It defines which command to call and what that agent may or may not do.

In plain words
What is it for?
Use it when forwarding diagnosis, planning, research, or fix requests to Grok from the specified rescue agent.
Why use it?
It keeps rescue requests consistent and prevents the rescue agent from inspecting the project or adding its own analysis. The result is returned directly from the helper.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the grok plugin — 3 skills, 10 commands, 1 agent, 3 hooks shipped together

Good fit Use it when forwarding diagnosis, planning, research, or fix requests to Grok from the specified rescue agent.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add davit-khaburdzania/grok-plugin-cc
Claude Code
/plugin install grok

Made for: Claude Code.

Or install grok, the plugin that ships this one along with the rest of its 3 skills, 10 commands, 1 agent, 3 hooks.

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/davit-khaburdzania/grok-plugin-cc/grok-cli-runtime/github.svg)](https://agentmods.dev/skills/davit-khaburdzania/grok-plugin-cc/grok-cli-runtime)
Your own site
<a href="https://agentmods.dev/skills/davit-khaburdzania/grok-plugin-cc/grok-cli-runtime"><img src="https://agentmods.dev/badge/skills/davit-khaburdzania/grok-plugin-cc/grok-cli-runtime/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.

agentmods 80×15 button for grok-cli-runtime

Your own site · 80×15
<a href="https://agentmods.dev/skills/davit-khaburdzania/grok-plugin-cc/grok-cli-runtime"><img src="https://agentmods.dev/badge/skills/davit-khaburdzania/grok-plugin-cc/grok-cli-runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 928 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 $0.00019 $0.00928
Opus 5 $0.00010 $0.00464
Sonnet 5 $0.00004 $0.00186
Haiku 4.5 $0.00002 $0.00093

Measured 9d ago against content hash 9fd68a688e2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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 · 51 lines

What it actually says

Grok Runtime

Use this skill only inside the grok:grok-rescue subagent.

Primary helper:

  • node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-companion.mjs" task "<raw arguments>"

Execution rules:

  • The rescue subagent is a forwarder, not an orchestrator. Its only job is to invoke task once and return that stdout unchanged.
  • Prefer the helper over hand-rolled git, direct grok CLI strings, or any other Bash activity.
  • Do not call setup, review, adversarial-review, status, result, transcript, or cancel from grok:grok-rescue.
  • Use task for every rescue request, including diagnosis, planning, research, and explicit fix requests.
  • You may use the grok-prompting skill to rewrite the user's request into a tighter Grok prompt before the single task call.
  • That prompt drafting is the only Claude-side work allowed. Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.
  • Leave --effort unset unless the user explicitly requests a specific effort.
  • Leave model unset by default. Add --model only when the user explicitly asks for one.
  • Default to a write-capable Grok run by adding --write unless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits.

How the runtime runs Grok:

  • Every task is one headless grok process (--prompt-file, --output-format streaming-json, --always-approve, --no-plan).
  • --write maps to --sandbox workspace (writes limited to the repository, /tmp, and ~/.grok). Without --write the run uses --sandbox read-only.
  • --sandbox <profile> overrides the profile (off, workspace, read-only, strict, or a custom profile from ~/.grok/sandbox.toml).
  • --max-turns <n> caps the agent loop.
  • --resume-last continues the latest tracked Grok session for this repository with grok --resume <session-id>; Grok keeps that session's original sandbox, so a read-only session cannot be resumed with --write.
  • --background hands the run to a detached worker and returns the job id immediately.

Command selection:

  • Use exactly one task invocation per rescue handoff.
  • If the forwarded request includes --background or --wait, treat that as execution control only. Strip --wait; keep --background as the task flag, and do not treat either as natural-language task text.
  • If the forwarded request includes --model, pass the model id through to task unchanged.
  • If the forwarded request includes --effort, pass it through to task.
  • If the forwarded request includes --resume, strip that token from the task text and add --resume-last.
  • If the forwarded request includes --fresh, strip that token from the task text and do not add --resume-last.
  • --resume: always use task --resume-last, even if the request text is ambiguous.
  • --fresh: always use a fresh task run, even if the request sounds like a follow-up.
  • --effort: accepted values are none, minimal, low, medium, high, xhigh, max.
  • task --resume-last: internal helper for "keep going", "resume", "apply the top fix", or "dig deeper" after a previous rescue run.

Safety rules:

  • Default to write-capable Grok work in grok:grok-rescue unless the user explicitly asks for read-only behavior.
  • Preserve the user's task text as-is apart from stripping routing flags.
  • Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
  • Return the stdout of the task command exactly as-is.
  • If the Bash call fails or Grok cannot be invoked, return nothing.
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. 9d ago First seen · 51 lines · 19 tokens per session scan A 9fd68a688e2f

Subscribe to this mod's changes

grok-cli-runtime is a skill published in the GitHub repository davit-khaburdzania/grok-plugin-cc (1 stars, last pushed 21d ago), licensed Apache-2.0. It adds 19 tokens to every session and 928 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 2026-08-31.

Related

Other skills, from other repositories