What is midjourney-cc-skill AGENTS.md?

A reference for creating and evaluating Midjourney image prompts. It explains prompt-writing practices and scores results across seven areas such as subject, lighting, and color.

Use it to write Midjourney prompts, review generated images, score each result, and compare improvements across iterations.

It provides a consistent way to assess whether an image matches the requested intent and to identify what needs refinement.

How JustinPerea/midjourney-cc-skill configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to JustinPerea/midjourney-cc-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/JustinPerea/midjourney-cc-skill/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/JustinPerea/midjourney-cc-skill

Made for: Codex, OpenCode.

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/instructions/justinperea/midjourney-cc-skill/agents-md/github.svg)](https://agentmods.dev/instructions/justinperea/midjourney-cc-skill/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/justinperea/midjourney-cc-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/justinperea/midjourney-cc-skill/agents-md/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/instructions/justinperea/midjourney-cc-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/justinperea/midjourney-cc-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16,847 This file is loaded in full into every session.

When invoked 16,847 The same file — it is already loaded in full.

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	$0.16847	$0.16847
Opus 5.5	$0.06739	$0.06739
Sonnet 5.5	$0.03369	$0.03369
Haiku 4.5	$0.01685	$0.01685

Measured 2mo ago against content hash eb2ce9e92f9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

midjourney-cc-skill AGENTS.md 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.

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.

AGENTS.md · 1,407 lines

How it starts

The opening of the file, as written. The whole thing — 1,407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Midjourney Prompt Learning System — Complete Reference

Auto-generated from rules/ directory. Do not edit directly. Regenerate with: ./scripts/build.sh

Core Prompt Engineering

Assessment Scoring Guide

How to score Midjourney outputs on 7 standard dimensions, handle agent confidence levels, and work around known limitations.

Score Scale

Score	Meaning
0.0-0.2	Completely wrong / not present
0.3-0.4	Vaguely there but wrong execution
0.5-0.6	Partially correct, needs significant work
0.7-0.8	Close, needs refinement
0.9-1.0	Nailed it

Standard Scoring Dimensions (Always Use All 7)

Every iteration must be scored on all 7 dimensions. This ensures batch averages are comparable across iterations and sessions. If a dimension isn't relevant to the intent (e.g., spatial_relationships for a flat graphic), score it 1.0 with a note "not applicable — no spatial element in intent."

Dimension	Key	What to Assess
Subject	`subject`	Does the main subject/form match intent?
Lighting	`lighting`	Is the lighting setup correct? (direction, color, intensity, atmosphere)
Color	`color`	Are the colors, palette, temperature, saturation correct?
Mood	`mood`	Does the overall feeling/emotion match?
Composition	`composition`	Is the framing, layout, subject position, depth correct?
Material	`material`	Are materials, textures, surface qualities correct?
Spatial Relationships	`spatial`	Are grounding, floating, scale, contact points, physics correct?

Score JSON format (use this exact structure for every image):

{
  "subject": 0.85, "lighting": 0.90, "color": 0.88,
  "mood": 0.90, "composition": 0.80, "material": 0.92,
  "spatial": 0.75, "avg": 0.86,
  "notes": "Concrete observations for each dimension"
}

Agent Confidence Flags

For each dimension, the agent should self-assess confidence. Flag dimensions where confidence is low so the user knows where to focus validation:

Read the full file on GitHub · 1,407 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.

2mo ago First seen · 1,407 lines · 16,847 tokens per session scan A eb2ce9e92f9f

Subscribe to this mod's changes

midjourney-cc-skill AGENTS.md is an instructions file published in the GitHub repository JustinPerea/midjourney-cc-skill (16 stars, last pushed 9mo ago), licensed MIT. It adds 16,847 tokens to every session, about $0.0674 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

midjourney-cc-skill AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
midjourney-cc-skill AGENTS.mdJustinPerea/midjourney-cc-skill	Instructions file	16	9mo ago	MIT	A	16,847	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

midjourney-cc-skill: Instructions file for Codex