grok-routing

grok-routing is a skill for Claude Code, Codex from stdevMac/grok-in-codex. It costs 16 tokens per session (1,076 once invoked), scanned A, original, Apache-2.0.

A routing guide for deciding when Codex should handle work itself and when to delegate it to Grok, an external coding agent.

In plain words
What is it for?
Use it to choose commands for rescue debugging, planning, design, multi-step execution, background investigations, code review, image generation, video generation, and document creation.
Why use it?
It helps match different kinds of work—such as quick fixes, architecture planning, long investigations, reviews, and media generation—to the appropriate Grok command or local workflow.

Skill for Claude CodeCodex

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/stdevmac/grok-in-codex/grok-routing
Any agent
npx skills add stdevMac/grok-in-codex --skill grok-routing
Clone the repo
git clone --depth 1 https://github.com/stdevMac/grok-in-codex

Made for: Claude Code, Codex.

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-routing

README.md
[![agentmods](https://agentmods.dev/badge/skills/stdevmac/grok-in-codex/grok-routing.svg)](https://agentmods.dev/skills/stdevmac/grok-in-codex/grok-routing)
Your own site
<a href="https://agentmods.dev/skills/stdevmac/grok-in-codex/grok-routing"><img src="https://agentmods.dev/badge/skills/stdevmac/grok-in-codex/grok-routing.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,076 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 $0.00016 $0.01076
Opus 5 $0.00008 $0.00538
Sonnet 5 $0.00003 $0.00215
Haiku 4.5 $0.00002 $0.00108

Measured 4d ago against content hash 2c1acbbdcb9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grok-routing 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/grok/skills/grok-routing/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to call Grok

Prefer Grok MCP tools

  • Substantial debugging after Codex is stuck
  • Second-opinion implementation of a non-trivial change
  • Best-of-N alternative approaches (bestOfN)
  • Risky edits that should land in a worktree (worktree)
  • Ambiguous architecturegrok_plan then implement, or grok_design
  • Multi-PR delivery from a design docgrok_execute_plan
  • Named multi-agent recipesgrok_workflow
  • PR CI/review babysittinggrok_babysit
  • Image/video generation (grok_image, grok_video)
  • Documents (grok_document with type pdf|docx|pptx)
  • Structured or adversarial code review before shipping
  • Long-running investigation better as a background job

Prefer staying in Codex

  • Quick questions, renames, one-line fixes
  • Tiny edits with obvious answers
  • Pure conversation without repo mutation

Intent → tool

User intent Prefer
Stuck on a bug / implement a fix grok_rescue (+ worktree + check)
Unclear approach before coding grok_plan
Architecture / design doc + PR plan grok_design
Ship a design doc’s PR DAG grok_execute_plan (or latest=true after design)
Multi-dimension structured fan-out grok_workflow
Ship quality on a branch/PR grok_review (+ postPending for GH)
Challenge design assumptions grok_adversarial_review
Watch / fix open PRs grok_babysit
Deck / PDF / Word grok_document
Brand stills / clips grok_image / grok_video
Find past Grok work grok_sessions

Depth pipeline (multi-PR / ambiguous product work)

Prefer this sequence over a single giant rescue:

  1. grok_plan — explore + plan.md when the approach is unclear (artifacts under .grok-plans/).
  2. grok_design — consensus design doc + PR Plan → artifacts under .grok-designs/.
  3. grok_execute_plan with latest=true (or explicit designDoc) — implement the PR DAG in worktrees.
  4. grok_review / grok_babysit — quality and CI/review loop.

Read the full file on GitHub · 109 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.

  1. 4d ago First seen · 109 lines · 16 tokens per session scan A 2c1acbbdcb9f

Subscribe to this mod's changes

grok-routing is a skill published in the GitHub repository stdevMac/grok-in-codex (22 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,076 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 2026-08-30.

Related

Other skills, from other repositories

ima2

Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.

lidge-jun/ima2-gen · 25 tokens

ima2-front

Frontend implementation skill for ima2 users. Use for any frontend, web UI, or visual implementation work — building, styling, or redesigning pages/components, responsive layouts, motion, component architecture, and production-surface polish. Pairs with ima2-uiux: load it first when design direction is vague; this…

lidge-jun/ima2-gen · 149 tokens

ima2-uiux

Design direction discovery and UX judgment for ima2 users. Use for UI/UX direction and design judgment — vague visual briefs, onboarding, empty/error/loading states, layout vocabulary, typography breaks, favicons, logos, and brand identity choices. Pairs with ima2-front: this skill decides the design direction, then…

lidge-jun/ima2-gen · 118 tokens

grok-routing

When to reach for Grok Build rather than doing the work in Claude Code — the routing tiers (manual, second-opinion, reach, offload-first, delegate-write), what each one covers, what it costs, and how to call it. Load this before offloading work, before asking for a second opinion, and before delegating anything to…

kai-wedekind/claude-code-grok-bridge · 92 tokens

grok-cli-runtime

How to delegate tasks to the Grok CLI from Claude Code via the grok-companion runtime. Use when forwarding a coding, debugging, or review task to Grok, when driving grok headlessly, or when the grok-rescue subagent or /grok-cc:rescue command needs to invoke the companion. Covers task vs read-only runs, foreground vs…

zachdunn/grok-plugin-claude-code · 89 tokens

local-image-gen

Generate or edit local images using Codex, Grok, or Gemini/Antigravity subscriptions when logged in, with optional API keys for the same models. Use when the user asks to 生图, 画图, 生成图片, 文生图, 改图, 编辑图片, 配图, 插图, 封面, 海报, image generation, image edit, inpaint, gpt-image-2, grok-imagine, nano banana, or wants to pick model…

DandreYang/local-image-gen · 126 tokens