style-reference-prompt

style-reference-prompt is a skill for Claude Code from ur-grue/autopunk-media-skills. It costs 46 tokens per session (1,955 once invoked), scanned A, original, MIT.

A Midjourney prompt based on a chosen visual style, such as a photographer, art movement, film, television show, or decade. It translates that reference into words the image generator can use.

In plain words
What is it for?
Use it to create imagery for editorial, social media, marketing, or other projects that need a defined artistic style.
Why use it?
It helps describe a specific aesthetic when broad terms like “modern” or “cinematic” are too unclear. It can also support a consistent look across multiple images.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the autopunk-media-skills plugin — 187 skills shipped together

Good fit Use it to create imagery for editorial, social media, marketing, or other projects that need a defined artistic style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ur-grue/autopunk-media-skills/style-reference-prompt
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 ur-grue/autopunk-media-skills --skill style-reference-prompt
Clone the repo
git clone --depth 1 https://github.com/ur-grue/autopunk-media-skills

Made for: Claude Code.

Or install autopunk-media-skills, the plugin that ships this one along with the rest of its 187 skills.

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 style-reference-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/style-reference-prompt/github.svg)](https://agentmods.dev/skills/ur-grue/autopunk-media-skills/style-reference-prompt)
Your own site
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/style-reference-prompt"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/style-reference-prompt/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 style-reference-prompt

Your own site · 80×15
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/style-reference-prompt"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/style-reference-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,955 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00046 $0.01955
Opus 5 $0.00023 $0.00978
Sonnet 5 $0.00009 $0.00391
Haiku 4.5 $0.00005 $0.00196

Measured 7d ago against content hash d0d78093f92e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

style-reference-prompt 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 7d 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.

skills/image-prompting/midjourney/style-reference-prompt/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Style Reference Prompt

What This Skill Does

Builds a Midjourney prompt that precisely captures a defined visual style or artistic reference — translating a style description, reference image context, or artistic period into the specific prompt language Midjourney responds to.

When To Use This Skill

  • You have a clear visual style in mind (a photographer's aesthetic, an art movement, a film's cinematography) and need a Midjourney prompt that reliably produces that look
  • You are art-directing a content series and need consistent visual style across multiple generated images
  • You have a style reference image and want to generate original images in the same aesthetic without directly copying the reference
  • You are producing imagery for editorial, social media, or marketing and need to describe an aesthetic with precision

What You Need To Provide

Required:

  • A description of the visual style you want to achieve — can be a named photographer/artist, an art movement, a film or TV show, a decade's aesthetic, or a detailed verbal description of the look
  • What the image should depict (subject matter, scene, or concept)

Optional:

  • Aspect ratio or intended format (e.g., 16:9 for YouTube thumbnail, 4:5 for Instagram, square)
  • Midjourney model version if you have a preference (defaults to latest)
  • Any style elements to exclude (e.g., "no digital art feel," "no oversaturation")
  • Whether you want multiple prompt variations to test (2–3 alternatives)
  • The specific use case (social media post, magazine cover, documentary still, podcast artwork)

How the Assistant Approaches This

  1. Identifies the core visual attributes of the stated style: lighting quality, color palette, texture, composition tendencies, grain or surface quality, subject-camera relationship
  2. Translates those attributes into Midjourney's prompt grammar: combines subject, style descriptors, technical photography or art terms, and quality/finish parameters
  3. Adds the appropriate camera, lens, or medium reference if the style implies specific photographic or artistic technique (e.g., "shot on 35mm Kodak Portra 400," "gouache on textured paper," "Leica M6 wide-open")
  4. Sets aspect ratio parameter and adds --stylize value suggestion appropriate to the style (higher for painterly/artistic, lower for documentary/editorial)
  5. Optionally generates 2–3 variations that explore the style from slightly different angles (different subject, same aesthetic)
  6. Closes with a "Next Step" note: how many generations to run at this --s value before adjusting, whether to try the alternative prompts if the primary doesn't land, and whether character-consistency-prompt should be run if a recurring figure also needs to appear in this aesthetic

Read the full file on GitHub · 112 lines

Files

What ships with it

1 file 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.

  1. 7d ago First seen · 112 lines · 46 tokens per session scan A d0d78093f92e

Subscribe to this mod's changes

style-reference-prompt is a skill published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 11d ago), licensed MIT. It adds 46 tokens to every session and 1,955 once invoked, about $0.0002 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 2026-09-04.

Related

Other skills, from other repositories

seedance-style

This skill should be used when the user asks for visual style, art direction, render feel, period aesthetic, texture, animation style, realism level, or style-safe alternatives to studio or franchise references.

1370998960-del/https-github.com-Emily2040-seedance-2.0 · 44 tokens

seedance-style

This skill should be used when the user asks for visual style, art direction, render feel, period aesthetic, texture, animation style, realism level, or style-safe alternatives to studio or franchise references.

Emily2040/seedance-2.0 · 44 tokens

frontend-slides

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

gooseworks-ai/goose-skills · 63 tokens

create-workflow-diagram

Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.

gooseworks-ai/goose-skills · 45 tokens

create-imessage-mockup

Render pixel-accurate iMessage screenshot mockups (DM or group) from a thread JSON. Supports minimal, with-keyboard, and full iPhone 15 Pro frame variants. Outputs HTML + PNG.

gooseworks-ai/goose-skills · 49 tokens

logo-design

Generate logo variants for a brand, producing multiple production-grade marks across different architectures (wordmark, lockup, symbol-only, letterform-as-symbol, monogram) with rationale, application specs, and decision-ready presentation. Distinct from brand-identity, which produces the complete system (logo plus…

rampstackco/claude-skills · 201 tokens