recraft

recraft is a skill for Claude Code, Codex from vinsonconsulting/limner. It costs 44 tokens per session (995 once invoked), scanned A, original, Apache-2.0.

A procedure for using Recraft through Limner, a third-party image pipeline, to create or transform vector and raster artwork.

In plain words
What is it for?
Generating SVG logos, icons, and other scalable artwork, or transforming an existing image with a chosen style.
Why use it?
It helps choose compatible visual styles and settings for artwork that may need to scale cleanly or match a source image.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/vinsonconsulting/limner/recraft
Any agent
npx skills add vinsonconsulting/limner --skill recraft
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 recraft

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinsonconsulting/limner/recraft.svg)](https://agentmods.dev/skills/vinsonconsulting/limner/recraft)
Your own site
<a href="https://agentmods.dev/skills/vinsonconsulting/limner/recraft"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/recraft.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.00995
Opus 5 $0.00022 $0.00498
Sonnet 5 $0.00009 $0.00199
Haiku 4.5 $0.00004 $0.00100

Measured 5d ago against content hash 43f6fa38d5f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recraft 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 5d 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/recraft/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recraft prompt builder

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

Recraft is Limner's brand-and-vector pipeline. Its defining feature is vector-from-scratch: a vector style yields resolution-independent SVG. This skill is the procedure for driving it; the recipe at the end lists the styles, substyles, and other knobs.

Procedure

  1. Pick the style family first, then a substyle that exists within it. When unsure, omit the substyle; an unmatched pair is rejected upstream.
  2. For scalable brand art (logos, icons), choose the vector style so the output is SVG rather than a raster.
  3. Put painting media (oil, gouache, watercolor) in the prompt text, not the substyle, and pair painterly prompts with the realistic-image style.
  4. Describe the subject, then set the size and model for the use.
  5. To transform an existing image rather than start fresh, pass it as a source image URL and tune strength: low stays close to the source, high follows the prompt more.
  6. For a consistent set, hold style and substyle fixed and vary only the subject. Hand SVG output to a vector editor for cleanup and print prep (see the external-tools skill).

Knob reference

The recipe below is generated from the Limner guidance core (@limner/core), the same source the MCP recraft-builder 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.

Recraft prompt recipe

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

Recraft is Limner’s brand-and-vector pipeline: it generates raster or true vector (SVG) art and supports fine style control. Its defining feature is vector-from-scratch: pick a vector style and Recraft produces resolution-independent SVG you can refine in a vector editor (see the external-tools reference). Style is the broad family; substyle narrows it.

Read the full file on GitHub · 76 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. 5d ago First seen · 76 lines · 44 tokens per session scan A 43f6fa38d5f7

Subscribe to this mod's changes

recraft is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 24d ago), licensed Apache-2.0. It adds 44 tokens to every session and 995 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.