What is codex-delegate?

A skill that sends coding, review, diagnosis, or follow-up tasks from Grok Build to the local Codex command-line tool. Codex is an AI coding assistant that can work on or review a codebase.

Setting up Codex, reviewing code, challenging an approach, investigating or fixing issues, transferring a conversation, and checking task status.

It gives you a defined way to hand work to another local coding assistant and check, retrieve, or cancel that work later.

codex-delegate — Skill for Claude Code and Codex by jinxlzc: A skill that sends coding, review, diagnosis, or follow-up…

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/jinxlzc/grok-codex-plugin/codex-delegate

Any agent

npx skills add jinxlzc/grok-codex-plugin --skill codex-delegate

Clone the repo

git clone --depth 1 https://github.com/jinxlzc/grok-codex-plugin

Made for: Claude Code, Codex.

Or install codex, the plugin that ships this one along with the rest of its 4 skills, 8 commands, 1 agent, 3 hooks, 1 MCP server.

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/jinxlzc/grok-codex-plugin/codex-delegate.svg)](https://agentmods.dev/skills/jinxlzc/grok-codex-plugin/codex-delegate)

Your own site

<a href="https://agentmods.dev/skills/jinxlzc/grok-codex-plugin/codex-delegate"><img src="https://agentmods.dev/badge/skills/jinxlzc/grok-codex-plugin/codex-delegate.svg" alt="Measured on agentmods" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 463 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.

Model	Per session	Once invoked
Fable 5	$0.00082	$0.00463
Opus 5	$0.00041	$0.00231
Sonnet 5	$0.00016	$0.00093
Haiku 4.5	$0.00008	$0.00046

Measured 4d ago against content hash 7f81c5f25e0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-delegate 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 4d 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/codex/skills/codex-delegate/SKILL.md · 41 lines

What it actually says

Delegate to local Codex

This skill is the Grok-facing entry point for the local Codex companion.

Prefer the plugin's first-class tools when they are available:

MCP tools from the codex server (codex_setup, codex_review, codex_adversarial_review, codex_rescue, codex_transfer, codex_status, codex_result, codex_cancel)
Slash commands /codex:setup, /codex:review, /codex:adversarial-review, /codex:rescue, /codex:transfer, /codex:status, /codex:result, /codex:cancel

If MCP is not attached, invoke the companion directly:

node "${GROK_PLUGIN_ROOT:-$CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" <subcommand>

Routing:

Setup / login / review-gate → setup
Ordinary code review of the working tree or a branch → review (read-only)
Challenge the design / approach → adversarial-review
Investigate, fix, implement, or continue previous Codex work → rescue via codex:codex-rescue or task --write
Move this Grok conversation into Codex → transfer
Check background work → status / result / cancel

Rules:

Do not reimplement the task yourself after a successful Codex handoff.
Return companion / MCP output verbatim.
After a review, do not apply fixes unless the user asks.
If Codex is missing or logged out, stop and tell the user to run /codex:setup.

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.

4d ago First seen · 41 lines · 82 tokens per session scan A 7f81c5f25e0d

Subscribe to this mod's changes

codex-delegate is a skill published in the GitHub repository jinxlzc/grok-codex-plugin (1 stars, last pushed 22d ago), licensed Apache-2.0. It adds 82 tokens to every session and 463 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 2026-08-31.

Building agents codex grok grok-build mcp openai-codex plugin

codex-delegate

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Delegate to local Codex

What this file has done since we first saw it

Other skills, from other repositories

grok-prompting

grok-brand-media

grok-cli-runtime

grok-workflows

grok-routing

grok-brand-media