What is grokodex-run?

A command that delegates a coding task to a local Grok agent through the Grokodex connection. Grok is another AI model that can provide implementation help or a second opinion.

Use it to ask Grok to implement coding work, investigate a hard bug, or help with a multi-step refactor.

It gives you another agent’s input for difficult bugs, larger implementation tasks, or work that benefits from a separate perspective.

grokodex-run — Skill for Claude Code by anlostsheep

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 anlostsheep/grokodex --skill grokodex-run

Clone the repo

git clone --depth 1 https://github.com/anlostsheep/grokodex

Made for: Claude Code.

Or install grokodex, the plugin that ships this one along with the rest of its 6 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-run/github.svg)](https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-run)

Your own site

<a href="https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-run"><img src="https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-run/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-run"><img src="https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,345 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.

Model	Per session	Once invoked
Fable 5.1	$0.00119	$0.02345
Opus 5	$0.00060	$0.01172
Sonnet 5	$0.00024	$0.00469
Haiku 4.5	$0.00012	$0.00234

Measured 10d ago against content hash d6d361a9273a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

grokodex-run 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 10d 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/grokodex/skills/grokodex-run/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grokodex Run

Run a headless local Grok agent task through the Grokodex MCP bridge (Codex, Claude Code, or other MCP hosts).

When to use

User wants Grok’s second opinion or implementation help
Hard bugs / multi-file refactors better handled by a peer agent
Explicit “run Grok / ask Grok / delegate to Grok” requests
Not for pure read-only review of diffs (findings only, no edits) → use grokodex-review (profile=review)
Not for design challenge / approach critique only → use grokodex-critique (profile=critique)
Do not use bare grok_run (no profile) when the user only wants review without edits
Not for pure image gen → use grokodex-imagine
Not for pure X/Twitter search → use grokodex-x-search
Not for install/login diagnosis → use grokodex-setup

Tool preference (critical)

Always call MCP tool grok_run (logical name). On Claude Code the UI may show a prefixed name such as mcp__…__grok_run — use whatever /mcp lists for this server; still treat it as grok_run.
Forbidden: any terminal / shell tool to execute grok directly for the task.
Exception: only grokodex-setup install/login guidance may mention shell grok (install script / grok login). Never use shell as a bypass of grok_run.

Bridge serializes Grok processes; avoid firing parallel grok_run calls that both write the same repo. Prefer one active Grok worker at a time.

Default permissions

Do not pass permission_mode unless the user clearly asks for elevated / host-matching rights.
- Omitted / default → restricted (workspace-level writes with high-risk shell denies; no always-approve).
Do not auto-upgrade because the task “looks hard.”

Inherit + `host_sandbox` (only when user asks)

Use permission_mode=inherit only when the user explicitly wants:

“same permissions as the host” / “same as Codex” / “same as Claude”
“Full-Access” / “danger-full-access” / bypass-style full tools
matching the host session capability band

Read the full file on GitHub · 167 lines

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.

10d ago First seen · 167 lines · 119 tokens per session scan A d6d361a9273a

Subscribe to this mod's changes

grokodex-run is a skill published in the GitHub repository anlostsheep/grokodex (2 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 2,345 once invoked, about $0.0006 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.

Building agents Claude Code agent codex grok mcp plugin

plugin-publish

A release guide for publishing Zhin.js plugins to npm, the JavaScript package registry, and to the Zhin plugin marketplace. It covers package metadata, versioning, release checks, and submission requirements.

zhinjs/zhin · 58 tokens

plugin-develop

A development guide for adding features to Zhin.js plugins, such as chat commands, AI tools, middleware, scheduled tasks, and console pages. Zhin.js is the plugin system it targets.

zhinjs/zhin · 70 tokens

commands-create-slash-command

Create or update Agent Zero slash commands for the built-in Commands plugin. Use when the user asks to add, edit, duplicate, or refine a reusable /command backed by YAML config plus text/python content files.

agent0ai/agent-zero · 48 tokens

deepseek-harness

Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.

znlgis/opengis-skills · 68 tokens

grok-brand-media

Prompt recipes for Grok image/video generation from Codex (OG images, README banners, launch clips).

stdevMac/grok-in-codex · 26 tokens

grok-workflows

When and how to run Grok Rhai multi-agent workflows from Codex.

stdevMac/grok-in-codex · 20 tokens