grok-cli-runtime

grok-cli-runtime is a skill for Claude Code, Codex from LovelaceLoom/grok-plugin-cc. It costs 19 tokens per session (925 once invoked), scanned A, original, Apache-2.0.

An internal helper for forwarding tasks from a Grok rescue agent to the Grok companion runtime.

In plain words
What is it for?
Use it within the Grok rescue workflow to forward one task, optionally allowing code changes when the surrounding setup explicitly permits writing.
Why use it?
It gives that rescue agent a defined way to pass along diagnosis, planning, research, or explicitly requested coding work.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the grok plugin — 8 skills, 21 commands, 2 agents, 3 hooks 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/lovelaceloom/grok-plugin-cc/grok-cli-runtime
Any agent
npx skills add LovelaceLoom/grok-plugin-cc --skill grok-cli-runtime
Clone the repo
git clone --depth 1 https://github.com/LovelaceLoom/grok-plugin-cc

Made for: Claude Code, Codex.

Or install grok, the plugin that ships this one along with the rest of its 8 skills, 21 commands, 2 agents, 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/lovelaceloom/grok-plugin-cc/grok-cli-runtime.svg)](https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-cli-runtime)
Your own site
<a href="https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-cli-runtime"><img src="https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-cli-runtime.svg" alt="Measured on agentmods" 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 925 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 $0.00019 $0.00925
Opus 5 $0.00010 $0.00463
Sonnet 5 $0.00004 $0.00185
Haiku 4.5 $0.00002 $0.00093

Measured 5d ago against content hash 01793799c5d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 · 41 lines

What it actually says

Grok Runtime

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

Primary helper:

  • node "${CLAUDE_PLUGIN_ROOT}/scripts/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, cancel, or purge 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.
  • Default to read-only Grok behavior. Add --write ONLY when the user explicitly asks for code changes.
  • --write is gated by GROK_PLUGIN_ALLOW_WRITE=1 in the environment. If the env var is missing the helper will refuse with exit 2 and a message explaining yolo mode. Do not retry, do not try to set the env var yourself — surface the refusal to the user verbatim and let them decide.
  • Leave --model unset by default. Add --model <name> only when the user explicitly requests one.
  • Leave --effort unset by default. Add --effort <level> only when the user explicitly requests one. Valid values: low, medium, high, xhigh, max.

Command selection:

  • Use exactly one task invocation per rescue handoff.
  • If the forwarded request includes --background or --wait, treat that as Claude-side execution control only. Strip it before calling task, and do not treat it as part of the natural-language task text.
  • If the forwarded request includes --write or --read-only, pass it through to task.
  • If the forwarded request includes --timeout <duration>, pass it through. Forms accepted: 300s, 5m, 1h, 500ms, or 0 to disable. The default for task is unbounded (rescue work is open-ended). Override only if the user named a specific duration. On timeout the helper exits 124 — surface that to the user rather than retrying.
  • If the forwarded request includes --session-id <id>, pass it through. Grok creates a new session if not found, or resumes it if it exists. Use this to continue a previous rescue thread instead of starting fresh.
  • If the forwarded request includes --resume=<id> or bare --resume (resume most-recent), pass it through to task. NOTE: the named form REQUIRES the inline = syntax — --resume <id> (space-separated) is parsed as bare --resume (bool) plus a stray positional, NOT as a named resume. --continue (continue most-recent session for cwd) is also a passthrough. v0.9.5+: companion's extractPolicyFlags routes these into the final grok argv via grokBaseArgs.
  • Never call purge from this subagent. /grok:purge is a destructive disk-cleanup operation the user invokes explicitly; rescue is forwarder-only.

Safety rules:

  • Default to read-only Grok work in grok:grok-rescue unless the user explicitly asks for code changes.
  • 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. 5d ago First seen · 41 lines · 19 tokens per session scan A 01793799c5d3

Subscribe to this mod's changes

grok-cli-runtime is a skill published in the GitHub repository LovelaceLoom/grok-plugin-cc (5 stars, last pushed 27d ago), licensed Apache-2.0. It adds 19 tokens to every session and 925 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.