grok-fan-out

grok-fan-out is a skill for Claude Code from LovelaceLoom/grok-plugin-cc. It costs 107 tokens per session (804 once invoked), scanned A, original, Apache-2.0.

A multi-angle review skill that asks Grok to examine a task from several expert viewpoints and combine the results. The viewpoints can cover areas such as security, correctness, research, and testing.

In plain words
What is it for?
Use it for broad audits of code or plans, such as checking correctness, security, architecture, research evidence, and test coverage before receiving one consolidated verdict.
Why use it?
It gathers several kinds of review in one analysis, which helps reveal problems that a single review might miss. It is intended for substantial audits rather than one simple question.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the grok plugin — 8 skills, 21 commands, 2 agents, 3 hooks shipped together

Good fit Use it for broad audits of code or plans, such as checking correctness, security, architecture, research evidence, and test coverage before receiving one consolidated verdict.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add LovelaceLoom/grok-plugin-cc
Claude Code
/plugin install grok

Made for: Claude Code.

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-fan-out

README.md
[![agentmods](https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-fan-out/github.svg)](https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-fan-out)
Your own site
<a href="https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-fan-out"><img src="https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-fan-out/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-fan-out

Your own site · 80×15
<a href="https://agentmods.dev/skills/lovelaceloom/grok-plugin-cc/grok-fan-out"><img src="https://agentmods.dev/badge/skills/lovelaceloom/grok-plugin-cc/grok-fan-out.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 804 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 $0.00107 $0.00804
Opus 5 $0.00053 $0.00402
Sonnet 5 $0.00021 $0.00161
Haiku 4.5 $0.00011 $0.00080

Measured 11d ago against content hash d60683d522ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

grok-fan-out 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 11d 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-fan-out/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grok — Fan-Out (Multi-Angle Analysis)

Use this skill when one angle isn't enough — when the user wants something looked at from multiple specialties at once (correctness, security, tests, architecture, research) and a single consolidated verdict. The plugin runs one Grok analysis per angle in parallel, then a synthesis call that reconciles them — so you get broad coverage and real depth from a single command (deeper than a plain grok-ask). It makes several real Grok calls, so it's heavier — prefer it for substantial, multi-faceted tasks.

When to use

  • "Audit / review this from every angle", "find everything wrong with X", "do a thorough multi-perspective analysis".
  • A question that genuinely spans specialties: e.g. "is this auth module correct, secure, and well-tested?".
  • You want a deeper second opinion than grok-ask gives, without orchestrating multiple calls yourself.

Do not use this skill for:

  • A simple one-off question → grok-ask.
  • Pure source-grounded research on a topic → grok-research.
  • Long-form coding / fixing / refactoring → grok-rescue.
  • Image generation → grok-imagine.

How to invoke

Run exactly one bash command. Default to read-only (the subagents analyze; they don't edit):

node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" fan-out "<the user's task, properly quoted>"

CLAUDE_PLUGIN_ROOT is set by both Claude Code and Codex CLI.

Choosing the angles

  • Default angles (no flag): researcher, reviewer, security-auditor, test-writer.
  • --personas a,b,c — pick a subset of the built-in angle names (researcher, reviewer, security-auditor, test-writer, implementer, design-doc-writer, design-doc-reviewer). Keep it to 3–4 angles unless the user explicitly asks for more — each angle adds analysis depth (and tokens). The plugin caps the total.
  • --agents-json '<json array>' — advanced: name custom angles via a JSON array (each object needs a name). Only use when the built-in angle names don't fit the task.

Read the full file on GitHub · 49 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. 11d ago First seen · 49 lines · 107 tokens per session scan A d60683d522ef

Subscribe to this mod's changes

grok-fan-out is a skill published in the GitHub repository LovelaceLoom/grok-plugin-cc (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 107 tokens to every session and 804 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

architect

This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design".

Joncik91/ucai · 56 tokens

backend

This skill should be used when the user asks to "design REST APIs", "optimize database queries", "implement authentication", "build microservices", "review backend code", "set up GraphQL", "handle database migrations", or "load test APIs".

Joncik91/ucai · 54 tokens

ucai-patterns

Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.

Joncik91/ucai · 42 tokens

frontend-design

Use when user asks to build a web component, page, or application, or when the task involves frontend design, HTML/CSS generation, or UI layout. Applies specific rules for typography, OKLCH color, layout, motion, interaction, and UX writing to produce distinctive, production-grade interfaces that avoid generic AI…

harnessprotocol/harness-kit · 68 tokens

lineage

Use when user invokes /lineage with a column name (optionally qualified with table/schema). Also triggers on "trace this column", "where does X come from", "what reads from Y table". Traces column-level data lineage through SQL, Kafka, Spark, JDBC, and ORM codebases. Produces a structured lineage path with confidence…

harnessprotocol/harness-kit · 94 tokens

dependabot-sweep

Use when the user wants to fix, address, clear, or resolve open Dependabot security/vulnerability alerts for a repository, end to end. Fetches open alerts via the gh CLI, fixes them per ecosystem (pnpm/npm overrides + lockfile regen, cargo update, pip/go/bundler), verifies with audit and frozen-lockfile installs, then…

harnessprotocol/harness-kit · 149 tokens