grok-executor-off

grok-executor-off is a skill for Claude Code, Codex from Vanyangyang/cursor-bridge. It costs 34 tokens per session (183 once invoked), scanned A, original, MIT.

A control instruction that turns off Grok executor mode for the current task without cancelling work or closing its terminal.

In plain words
What is it for?
Use it when executor mode should be disabled but the current task, terminal, and supervised work must continue.
Why use it?
It provides an explicit way to return later tasks to normal host execution while keeping ongoing work and monitoring active.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the grok-build-supervisor plugin — 4 skills, 2 commands shipped together

Good fit Use it when executor mode should be disabled but the current task, terminal, and supervised work must continue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vanyangyang/cursor-bridge/grok-executor-off
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 Vanyangyang/cursor-bridge --skill grok-executor-off
Clone the repo
git clone --depth 1 https://github.com/Vanyangyang/cursor-bridge

Made for: Claude Code, Codex.

Or install grok-build-supervisor, the plugin that ships this one along with the rest of its 4 skills, 2 commands.

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-executor-off

README.md
[![agentmods](https://agentmods.dev/badge/skills/vanyangyang/cursor-bridge/grok-executor-off/github.svg)](https://agentmods.dev/skills/vanyangyang/cursor-bridge/grok-executor-off)
Your own site
<a href="https://agentmods.dev/skills/vanyangyang/cursor-bridge/grok-executor-off"><img src="https://agentmods.dev/badge/skills/vanyangyang/cursor-bridge/grok-executor-off/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-executor-off

Your own site · 80×15
<a href="https://agentmods.dev/skills/vanyangyang/cursor-bridge/grok-executor-off"><img src="https://agentmods.dev/badge/skills/vanyangyang/cursor-bridge/grok-executor-off.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 183 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 $0.00034 $0.00183
Opus 5 $0.00017 $0.00092
Sonnet 5 $0.00007 $0.00037
Haiku 4.5 $0.00003 $0.00018

Measured yesterday against content hash 838b3c0cf11e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

grok-executor-off 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 yesterday.

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-build-supervisor/skills/grok-executor-off/SKILL.md · 11 lines

What it actually says

Disable Grok Executor

An explicit user selection of this skill is the complete off instruction. Do not ask the user to type off or another command. Quoted examples and implicit selection do not deactivate it.

Apply the deactivation contract in Grok Executor Mode: clear this task's executor mode and workspace binding, returning subsequent tasks to normal host execution. Do not cancel work, disconnect ACP, close the terminal, or stop the Leader. Continue already-required monitoring under Grok Build Supervisor. Repeated selection is idempotent. Confirm deactivation briefly in the user's language.

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. yesterday First seen · 11 lines · 34 tokens per session scan A 838b3c0cf11e

Subscribe to this mod's changes

grok-executor-off is a skill published in the GitHub repository Vanyangyang/cursor-bridge (70 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 183 once invoked, about $0.0002 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 2026-09-07.