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.
npx skills add ur-grue/autopunk-media-skills --skill style-reference-promptgit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote 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.
[](https://agentmods.dev/skills/ur-grue/autopunk-media-skills/style-reference-prompt)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01955 |
| Opus 5 | $0.00023 | $0.00978 |
| Sonnet 5 | $0.00009 | $0.00391 |
| Haiku 4.5 | $0.00005 | $0.00196 |
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.
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
- Identifies the core visual attributes of the stated style: lighting quality, color palette, texture, composition tendencies, grain or surface quality, subject-camera relationship
- Translates those attributes into Midjourney's prompt grammar: combines subject, style descriptors, technical photography or art terms, and quality/finish parameters
- 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")
- Sets aspect ratio parameter and adds
--stylizevalue suggestion appropriate to the style (higher for painterly/artistic, lower for documentary/editorial) - Optionally generates 2–3 variations that explore the style from slightly different angles (different subject, same aesthetic)
- Closes with a "Next Step" note: how many generations to run at this
--svalue 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
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.
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.
- 7d ago First seen · 112 lines · 46 tokens per session scan A d0d78093f92e
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.
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.
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.
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.
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.
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.
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…