style-from-images

style-from-images is a skill for Claude Code, Codex from vinsonconsulting/limner. It costs 46 tokens per session (993 once invoked), scanned A, original, Apache-2.0.

A workflow for studying a user’s reference images and creating new images with a similar visual style. It can record the style as a reusable profile or pass an image directly as a reference.

In plain words
What is it for?
Use it when creating images that should match a user’s artwork, photos, or moodboard, either for one close match or for a consistent batch.
Why use it?
It turns a visual example into repeatable guidance, helping new images keep a consistent palette, medium, and overall look.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when creating images that should match a user’s artwork, photos, or moodboard, either for one close match or for a consistent batch.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vinsonconsulting/limner/style-from-images
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 vinsonconsulting/limner --skill style-from-images
Clone the repo
git clone --depth 1 https://github.com/vinsonconsulting/limner

Made for: Claude Code, Codex.

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-from-images

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinsonconsulting/limner/style-from-images/github.svg)](https://agentmods.dev/skills/vinsonconsulting/limner/style-from-images)
Your own site
<a href="https://agentmods.dev/skills/vinsonconsulting/limner/style-from-images"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/style-from-images/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-from-images

Your own site · 80×15
<a href="https://agentmods.dev/skills/vinsonconsulting/limner/style-from-images"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/style-from-images.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 993 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 $0.00046 $0.00993
Opus 5 $0.00023 $0.00496
Sonnet 5 $0.00009 $0.00199
Haiku 4.5 $0.00005 $0.00099

Measured 9d ago against content hash 8b7e81dfc837, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

style-from-images 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 9d 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.

packages/limner-agent/skills/style-from-images/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Style from user images

Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.

Use this skill when a user brings their own images and wants new work to match. Limner carries the style across two ways: you describe the references into a style profile so the look is reusable, and you pass a reference image to a generator directly so it borrows the look without words. Describe for a consistent batch; pass the image for a close one-off match. The reference at the end states the profile shape and the rules.

Procedure

  1. Look at the references. Name the palette (a few hex colors), the descriptors (style keywords), and the medium.
  2. Write the profile. Use upsertStyleProfile to save them to the project's style profile, set provenance.source to style-from-images, and list the user's images under references (kind image).
  3. Match directly for a close one-off. Pass a reference image URL to a generator (a Midjourney style reference with --sref, a DALL·E edit, or a Recraft image-to-image).
  4. Generate in the style. Shape each prompt from the profile's descriptors and medium, and set pipelinePrefs so a batch stays consistent.
  5. Hold the look fixed. Keep palette and descriptors constant across the set and vary only the subject.

Judgment

  • Capture the few attributes that define the look, not every detail; a tight profile generates more consistently than a long one.
  • Use native image input for a close single match; use the described profile to keep a whole batch consistent.
  • Record the user's images under references so the profile's origin is traceable.
  • The style profile is the shared shape the brand-kit and art-research skills also read, so a style captured here flows straight into them.

Reference

The text below is generated from the Limner guidance core (@limner/core), the same source the MCP style-from-images prompt serves, so this skill and that prompt cannot drift. Do not edit the generated region by hand; run pnpm --filter @limner/limner-agent gen:skills instead.

Read the full file on GitHub · 77 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. 9d ago First seen · 77 lines · 46 tokens per session scan A 8b7e81dfc837

Subscribe to this mod's changes

style-from-images is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 28d ago), licensed Apache-2.0. It adds 46 tokens to every session and 993 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 2026-08-31.