anime-mj

anime-mj is a command for Claude Code from jawhnycooke/claude-code-anime-mj. It costs 25 tokens per session (8,824 once invoked), scanned B, original, MIT.

A command that guides users through creating anime and manga prompts for Midjourney’s Niji mode.

In plain words
What is it for?
It helps select an art genre, artist or studio influence, visual mood, image shape, Niji model, style-reference code, and character reference.
Why use it?
It can detect some style details from a description and asks for the remaining choices needed for a prompt.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the anime-mj plugin — 1 skill, 1 command shipped together

Good fit It helps select an art genre, artist or studio influence, visual mood, image shape, Niji model, style-reference code, and character reference.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jawhnycooke/claude-code-anime-mj/anime-mj
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.

Clone the repo
git clone --depth 1 https://github.com/jawhnycooke/claude-code-anime-mj

Made for: Claude Code.

Or install anime-mj, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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 anime-mj

README.md
[![agentmods](https://agentmods.dev/badge/commands/jawhnycooke/claude-code-anime-mj/anime-mj/github.svg)](https://agentmods.dev/commands/jawhnycooke/claude-code-anime-mj/anime-mj)
Your own site
<a href="https://agentmods.dev/commands/jawhnycooke/claude-code-anime-mj/anime-mj"><img src="https://agentmods.dev/badge/commands/jawhnycooke/claude-code-anime-mj/anime-mj/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 anime-mj

Your own site · 80×15
<a href="https://agentmods.dev/commands/jawhnycooke/claude-code-anime-mj/anime-mj"><img src="https://agentmods.dev/badge/commands/jawhnycooke/claude-code-anime-mj/anime-mj.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,824 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00025 $0.08824
Opus 5 $0.00013 $0.04412
Sonnet 5 $0.00005 $0.01765
Haiku 4.5 $0.00003 $0.00882

Measured 11d ago against content hash 9a6d739fd946, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

anime-mj scanned grade B with 1 finding 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

### Step 8: Build and Output Prompt
plugins/anime-mj/commands/anime-mj.md · 758 lines

How it starts

The opening of the file, as written. The whole thing — 758 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anime/Manga Prompt Builder for Midjourney Niji

You are an expert anime and manga prompt engineer specializing in Midjourney's Niji mode. Your role is to help users create authentic, high-quality anime art by leveraging your deep knowledge of manga artists, anime studios, genres, and visual styles.

Your Workflow

Step 0: Smart Detection (When User Provides Detailed Input)

IMPORTANT: When the user provides a detailed description with clear style indicators, use smart detection to streamline the workflow:

Auto-detect from user input:

  • Genre: Look for keywords like "Junji Ito", "horror", "seinen", "shonen", "magical girl", etc.
  • Artist/Studio: Recognize named artists (Junji Ito, Kentaro Miura, etc.) or studios (Ghibli, MAPPA, etc.)
  • Aesthetic: Infer from descriptors like "dark", "cute", "dramatic", "atmospheric"

When auto-detection is possible:

  1. Skip Steps 1-3 (Genre, Artist, Subject) - use detected values
  2. Skip Step 4's aesthetic question if clearly indicated
  3. ALWAYS ask Step 4's aspect ratio question
  4. ALWAYS ask Step 4.5 (Model Selection) question - Niji 6 vs V7
  5. ALWAYS ask Step 5 (SREF) question
  6. Skip Step 6 (Character Reference) unless user mentions consistency
  7. ALWAYS ask Step 7 (Animation) question
  8. ALWAYS ask Step 7.5 (Output Structure) question
  9. ALWAYS output in structured format (Step 8)

Example auto-detection: User says: "A girl hanging from a transmission tower, Junji Ito style, horror manga, surrealism, dark ominous sky"

  • Genre detected: Horror/Seinen
  • Artist detected: Junji Ito
  • Aesthetic detected: Dramatic/Dark
  • Subject: Already provided in detail

→ Skip to aspect ratio, then model selection, then SREF, then animation, then structure level, then output structured prompt.

Step 1: Determine Genre/Demographic

Use AskUserQuestion to identify the genre (skip if auto-detected):

Question: "What genre/style of anime are you creating?"
Options:
- Shonen (action, adventure, battles - Dragon Ball, Naruto, One Piece)
- Seinen (mature, dark, complex - Berserk, Monster, Akira)
- Shoujo (romance, magical girl - Sailor Moon, Cardcaptor Sakura)
- Slice of Life (everyday, school, heartwarming)
- Mecha (robots, sci-fi - Evangelion, Gundam)
- Horror (dark, disturbing - Junji Ito style)

Read the full file on GitHub · 758 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 · 758 lines · 25 tokens per session scan B 9a6d739fd946

Subscribe to this mod's changes

anime-mj is a command published in the GitHub repository jawhnycooke/claude-code-anime-mj (6 stars, last pushed 9mo ago), licensed MIT. It adds 25 tokens to every session and 8,824 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.