midjourney-cc-skill: Command for Claude Code

.claude/commands/apply-knowledge.md

apply-knowledge is a command for Claude Code from JustinPerea/midjourney-cc-skill. It costs 0 tokens per session (1,175 once invoked), scanned A, original, MIT.

A command that examines a description or intent and builds a prompt using matching patterns learned from earlier image-generation work. It groups clues such as lighting, materials, shapes, colors, mood, and style.

In plain words
What is it for?
Use it when describing an image, visual style, or production requirement and you want applicable stored patterns identified and included in a prompt.
Why use it?
It helps turn a loose visual idea into a prompt that reflects relevant previous guidance instead of requiring the same decisions from scratch.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions Claude Code.

This is JustinPerea/midjourney-cc-skill's own configuration. It tells Claude Code how to work on midjourney-cc-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything midjourney-cc-skill configures →

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/.claude/commands/apply-knowledge.md
Clone the repo
git clone --depth 1 https://github.com/JustinPerea/midjourney-cc-skill

Made for: Claude Code.

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 apply-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/commands/justinperea/midjourney-cc-skill/apply-knowledge/github.svg)](https://agentmods.dev/commands/justinperea/midjourney-cc-skill/apply-knowledge)
Your own site
<a href="https://agentmods.dev/commands/justinperea/midjourney-cc-skill/apply-knowledge"><img src="https://agentmods.dev/badge/commands/justinperea/midjourney-cc-skill/apply-knowledge/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 apply-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/commands/justinperea/midjourney-cc-skill/apply-knowledge"><img src="https://agentmods.dev/badge/commands/justinperea/midjourney-cc-skill/apply-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,175 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 $0.00000 $0.01175
Opus 5 $0.00000 $0.00588
Sonnet 5 $0.00000 $0.00235
Haiku 4.5 $0.00000 $0.00118

Measured 8d ago against content hash f3c479fc8f5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

apply-knowledge 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 8d 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.

.claude/commands/apply-knowledge.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply Knowledge

Given a reference description or intent, show which learned patterns would apply and construct a prompt using accumulated knowledge.

Instructions

  1. Verify database access. Run SELECT COUNT(*) FROM sessions via sqlite-simple MCP. If the query fails, tell the user: "Database not available. Run claude mcp add sqlite-simple -- npx @anthropic-ai/sqlite-simple-mcp mydatabase.db then restart Claude Code." Do not proceed without database access.

  2. Analyze the user's input to identify relevant categories. The input could be:

    • A description of what they want ("glowing organic form with dual-tone lighting")
    • A reference to a visual style ("like that glass sculpture look")
    • A set of requirements ("commercial product shot, clean, minimal")
  3. Extract category tags from the input. Map descriptions to categories:

    • Mentions of light, glow, shadow, bright, dark → lighting
    • Mentions of glass, metal, wood, fabric, ceramic → materials
    • Mentions of shape, form, organic, geometric → forms
    • Mentions of color names, warm, cool, vibrant → color
    • Mentions of mood, feeling, vibe → mood
    • Mentions of render, 3D, photo, illustration → style
    • Mentions of framing, layout, position → composition
  4. Query candidate patterns:

    SELECT * FROM patterns
    WHERE is_active = 1 AND category IN (...extracted categories...)
    AND confidence IN ('medium', 'high')
    ORDER BY confidence DESC, success_rate DESC
    
  5. Score each pattern for relevance to this specific task. Not every pattern in a matching category is equally useful. For each candidate pattern, assess:

    a. Context match — Does the pattern's problem description match the current situation? A lighting pattern for "soft ambient" is irrelevant when the user wants "harsh directional." Read the pattern's problem, example_bad, example_good, and notes fields to judge fit.

    b. Specificity alignment — Prefer patterns whose specificity level matches the task:

    • universal patterns always apply (prompt structure rules, parameter basics)
    • general patterns apply when the category matches
    • specific patterns apply only when the exact context matches (check notes and tags for conditional context like "works when subject is organic" or "only for V7")
    • user-preference patterns apply when the same user's style preferences are relevant

Read the full file on GitHub · 98 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. 8d ago First seen · 98 lines · 0 tokens per session scan A f3c479fc8f5c

Subscribe to this mod's changes

apply-knowledge is a command published in the GitHub repository JustinPerea/midjourney-cc-skill (11 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,175 tokens. 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.