multi-size-export

multi-size-export is a skill for Claude Code, Codex from vinsonconsulting/limner. It costs 43 tokens per session (983 once invoked), scanned A, original, Apache-2.0.

An export workflow that turns one finished image into several sizes and file formats for websites, apps, and social media. It resizes and converts each variant according to its destination.

In plain words
What is it for?
Use it to create web, app, thumbnail, social, or interface-image variants, choose WebP, AVIF, PNG, or JPEG, crop to target boxes, and preserve the full image with padding when needed.
Why use it?
It removes repetitive manual resizing and format conversion while accounting for cropping, transparency, image weight, and quality.

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/multi-size-export
Any agent
npx skills add vinsonconsulting/limner --skill multi-size-export
Clone the repo
git clone --depth 1 https://github.com/vinsonconsulting/limner

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge for your README with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them.

agentmods badge for multi-size-export

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinsonconsulting/limner/multi-size-export.svg)](https://agentmods.dev/skills/vinsonconsulting/limner/multi-size-export)
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 983 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 $0.00043 $0.00983
Opus 5 $0.00022 $0.00491
Sonnet 5 $0.00009 $0.00197
Haiku 4.5 $0.00004 $0.00098

Measured 3d ago against content hash 7e162924ec69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-size-export 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 3d 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/multi-size-export/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-size and format export

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

Use this skill to turn one finished image into the set of sizes and formats each destination needs. Compose's resize and convert ops do the work locally; you decide the targets and the format per destination. The reference at the end lists common targets and the fit and format rules.

Procedure

  1. List the targets. Write down each destination with its size and aspect, and confirm the current spec for any social platform.
  2. Pick the format per target. WebP or AVIF for web and app weight, PNG for transparency or interface marks, JPEG for photographs.
  3. Resize to each size. Use the compose resize op. It fills the target box and crops the overflow, so confirm the source aspect matches the target or expect a crop.
  4. Letterbox when needed. If a target must keep the whole image, use the Cloudflare Images transform with the contain or pad fit, on Workers.
  5. Convert and set quality. Use the convert op to reach the target format; lower the quality for thumbnails, keep it high for hero images.
  6. Deliver the set. Emit each variant through its own capability URL, named by destination and size.

Judgment

  • Resize from the largest size first so every smaller variant stays consistent.
  • Reach for WebP or AVIF by default on the web; fall back to JPEG or PNG only when compatibility or transparency demands it.
  • Watch the crop. A square source forced into a wide box loses the top and bottom; recrop the subject or letterbox on Workers instead.

Reference

The table below is generated from the Limner guidance core (@limner/core), the same source the MCP multi-size-export 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.

Multi-size and format export

Read the full file on GitHub · 84 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. 3d ago First seen · 84 lines · 43 tokens per session scan A 7e162924ec69

Subscribe to this mod's changes

multi-size-export is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 22d ago), licensed Apache-2.0. It adds 43 tokens to every session and 983 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.