recraft-image-design

recraft-image-design is a skill for Claude Code, Codex from calesthio/generative-media-skills. It costs 80 tokens per session (10,291 once invoked), scanned A, original, MIT.

A guide to Recraft’s API for creating and editing raster images and SVG artwork, including image transformations, vectorization, backgrounds, palettes, and typography.

In plain words
What is it for?
It is for producing branded graphics, editing images, creating SVG artwork, removing or changing backgrounds, and turning raster images into vectors.
Why use it?
It helps developers match the API operation to the required deliverable, such as an editable vector file or a finished bitmap, and verify the actual output.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit It is for producing branded graphics, editing images, creating SVG artwork, removing or changing backgrounds, and turning raster images into vectors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/calesthio/generative-media-skills/recraft-image-design
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 calesthio/generative-media-skills --skill recraft-image-design
Clone the repo
git clone --depth 1 https://github.com/calesthio/generative-media-skills

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-image-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/calesthio/generative-media-skills/recraft-image-design/github.svg)](https://agentmods.dev/skills/calesthio/generative-media-skills/recraft-image-design)
Your own site
<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/recraft-image-design"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/recraft-image-design/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 recraft-image-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/recraft-image-design"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/recraft-image-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,291 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 104
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Data Exfiltration · line 277
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00080 $0.10291
Opus 5 $0.00040 $0.05146
Sonnet 5 $0.00016 $0.02058
Haiku 4.5 $0.00008 $0.01029

Measured 9d ago against content hash 3fef0d468711, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

recraft-image-design scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

All examples are examples, not mandatory formulas. They assume `curl`, Python 3, `Pillow`, `defusedxml`, and an environment variable named `RECRAFT_API_TOKEN`.
skills/providers/image-generation/recraft-image-design/SKILL.md · 656 lines

How it starts

The opening of the file, as written. The whole thing — 656 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recraft image design

Use Recraft as a design-production system, not as a generic prompt box. Choose the model and operation from the required output contract, make only documented API calls, save returned assets immediately, and inspect the actual raster or SVG before delivery.

Evidence labels and freshness

Interpret labels literally:

  • Documented — stated in a first-party Recraft API reference, OpenAPI document, model page, legal page, or trust page.
  • Inference — a conclusion derived from documented behavior but not promised by Recraft.
  • Production heuristic — a practical workflow recommendation; test it on the current account and brief.

Volatile API facts in this skill were checked 2026-07-09. Recheck model IDs, compatibility, pricing, limits, retention, and terms before a costly or regulated run. The human-readable API guide is the contract to prefer. The official Swagger specification sometimes exposes extra aliases or fields not explained in the guide; do not depend on those without a small validation request.

Establish the production contract

Before calling the API, record:

  1. deliverable: raster or editable SVG;
  2. target aspect/size and final-use resolution;
  3. exact copy that must appear, if any;
  4. brand palette, forbidden colors, and style references;
  5. what must remain unchanged in an edit;
  6. rights/consent status for references, people, marks, and copy;
  7. commercial use, provenance/disclosure, privacy, and retention requirements;
  8. exploration budget and acceptance checks.

If a downstream tool requires true paths, request a vector model. A raster image that merely looks like vector art is not a substitute for SVG.

Select a current model

Documented, verified 2026-07-09: POST /v1/images/generations defaults to recraftv4_1. The public guide accepts these proprietary model IDs:

Family Raster Vector Use
V4.1 expressive, standard recraftv4_1 recraftv4_1_vector Current default for concepting, polished art direction, typography, illustration, and general production
V4.1 expressive, Pro recraftv4_1_pro recraftv4_1_pro_vector Same line at roughly 4 MP / higher output size for print and dense detail
V4.1 Utility, standard recraftv4_1_utility recraftv4_1_utility_vector Cleaner, flatter, front-facing, predictable work such as product shots and mockup source imagery
V4.1 Utility, Pro recraftv4_1_utility_pro recraftv4_1_utility_pro_vector Utility behavior with higher output size
V4 recraftv4 recraftv4_vector Previous design-forward generation family
V4 Pro recraftv4_pro recraftv4_pro_vector Previous high-resolution family
V3 recraftv3 recraftv3_vector Keep for curated/custom styles, localized edit routes, text layout, negative prompts, and artistic-level controls
V2 recraftv2 recraftv2_vector Legacy styles/effects that exist only in V2

Read the full file on GitHub · 656 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. 9d ago First seen · 656 lines · 80 tokens per session scan A 3fef0d468711

Subscribe to this mod's changes

recraft-image-design is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 10,291 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

cliptalk-graphics-packager

Adds task-local graphic text layers such as title cards, top labels, product tags, price or parameter callouts, watermarks, and CTA overlays to an existing timeline.

GML-MMGroup/ClipTalk · 41 tokens

sage-review

Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.

kirodotdev/KiroCrew · 68 tokens

design-critique

Run a heuristic evaluation of a UI design (image, HTML, Figma, URL, or flow) the way an experienced designer would. Evaluates 4 categories (Visual & hierarchy, Usability & interaction, Accessibility, Content) using recognized frameworks, NN/g 0-4 severity, and evaluability-aware prioritization that never judges what…

kirodotdev/KiroCrew · 131 tokens

theme-pack-authoring

Build, validate, and install Kiro Crew theme packs -- pack anatomy, the 56-variable palette, role-tagged fonts, the overrides.css allowlist (what installs vs what actually renders), and the install-verify cycle. Use when the user wants to create or edit a theme pack.

kirodotdev/KiroCrew · 64 tokens

image-authoring

Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.

kirodotdev/KiroCrew · 45 tokens

web-design

Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.

Prism-Shadow/penguin-harness · 51 tokens