What is legnext-midjourney?

An image-generation workflow that sends text descriptions to Midjourney, an AI service that creates images from prompts, through the Legnext API, a web service for accessing it.

Use it to create images from natural-language descriptions or Midjourney-style requests. It requires a Legnext API key.

It handles the steps of submitting an image request, checking its progress, and retrieving the result instead of requiring you to manage those steps manually.

legnext-midjourney — Skill for Claude Code and Codex by leggiemint

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 leggiemint/legnext-skills --skill legnext-midjourney

Clone the repo

git clone --depth 1 https://github.com/leggiemint/legnext-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/leggiemint/legnext-skills/legnext-midjourney/github.svg)](https://agentmods.dev/skills/leggiemint/legnext-skills/legnext-midjourney)

Your own site

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

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,278 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	$0.00062	$0.02278
Opus 5.5	$0.00025	$0.00911
Sonnet 5.5	$0.00012	$0.00456
Haiku 4.5	$0.00006	$0.00228

Measured 2mo ago against content hash ac2d305c230a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

legnext-midjourney 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 2mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/generate_and_wait.py, scripts/get_task.py, scripts/imagine.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

legnext-midjourney/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Legnext Midjourney

Generate professional AI images using Midjourney's capabilities through the Legnext API.

Setup

CRITICAL: This skill requires a Legnext API key. Before running, check if the user has configured their API key:

Check for existing configuration:

Look for a .env file in the project directory or parent directories
Check for LEGNEXT_API_KEY=<key> in the .env file
Or check environment variable: echo $LEGNEXT_API_KEY

If not found, inform the user they need to:

Option 1: Create a .env file (recommended)

# Create .env file in the project root
echo "LEGNEXT_API_KEY=your-api-key-here" > .env

Option 2: Set environment variable

export LEGNEXT_API_KEY=your-api-key-here

Get an API key from:

https://legnext.ai/app/api-keys

Verify API key:

python scripts/verify_api_key.py

The scripts will automatically detect the .env file and provide clear error messages if the API key is missing or invalid.

Quick Start

For simple image generation requests:

python scripts/generate_and_wait.py "a beautiful sunset over mountains --v 7 --ar 16:9"

This handles the complete workflow: submit task → poll status → return results.

Complete Workflow

1. Understand the User's Request

Identify what type of image the user wants:

Subject matter (people, landscapes, objects, abstract)
Style (photographic, illustrated, artistic)
Mood and atmosphere
Technical requirements (aspect ratio, quality)

2. Craft the Prompt

Transform the user's natural language request into an effective Midjourney prompt.

Use the 7-Element Framework for systematic prompts:

Subject, Medium, Environment, Lighting, Color, Mood, Composition

Quick structure:

[Subject] [Description] [Environment] [Lighting] [Style] [Parameters]

Example transformations:

User request: "I need a professional headshot" → Prompt: professional headshot, studio lighting, neutral background, sharp focus, 85mm lens --ar 2:3 --style raw

Read the full file on GitHub · 302 lines

Files

What ships with it

9 files 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.

2mo ago First seen · 302 lines · 62 tokens per session scan A ac2d305c230a

Subscribe to this mod's changes

legnext-midjourney is a skill published in the GitHub repository leggiemint/legnext-skills (4 stars, last pushed 10mo ago), licensed MIT. It adds 62 tokens to every session and 2,278 once invoked, about $0.0002 per session on Opus 5.5. 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.

Creative and media claude-code-plugin claude-code-skills

legnext-midjourney next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
legnext-midjourneyleggiemint/legnext-skills	Skill	4	10mo ago	MIT	A	62	Claude Code, Codex
top-designwondelai/skills	Skill	2.6k	4d ago	MIT	A	113	Claude Code, Codex
add-cloud-flowmicrosoft/power-platform-skills	Skill	1.1k	yesterday	MIT	A	91	Claude Code
configure-env-variablesmicrosoft/power-platform-skills	Skill	1.1k	yesterday	MIT	A	119	Claude Code
edit-sitemicrosoft/power-platform-skills	Skill	1.1k	yesterday	MIT	A	104	Claude Code
deploy-sitemicrosoft/power-platform-skills	Skill	1.1k	yesterday	MIT	A	91	Claude Code
create-businesswondelai/skills	Skill	2.6k	4d ago	MIT	A	211	Claude Code