What is upscale-image?

A skill for enlarging images with AI by two, three, or four times. It is intended to recover or add visual detail when starting files are small.

Use it to enlarge image files or folders, including old photos and small AI images; choose regular resizing instead for simple non-AI enlargement.

It helps prepare low-resolution photos, screenshots, and AI-generated images for larger displays or printing without generating a new image from a prompt.

upscale-image — Skill for Claude Code by danielrosehill

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 danielrosehill/Claude-Image-Production-Plugin --skill upscale-image

Clone the repo

git clone --depth 1 https://github.com/danielrosehill/Claude-Image-Production-Plugin

Made for: Claude Code.

Or install image-production, the plugin that ships this one along with the rest of its 29 skills, 19 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/upscale-image/github.svg)](https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/upscale-image)

Your own site

<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/upscale-image"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/upscale-image/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/upscale-image"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/upscale-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,505 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

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.

Model	Per session	Once invoked
Fable 5.1	$0.00098	$0.01505
Opus 5.5	$0.00039	$0.00602
Sonnet 5.5	$0.00020	$0.00301
Haiku 4.5	$0.00010	$0.00151

Measured 2mo ago against content hash 7e3eba9a131a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

upscale-image 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 2mo 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.

skills/upscale-image/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upscale Image (Upscayl)

AI upscaling via upscayl-bin — the CLI shipped with the Upscayl GUI. Same Vulkan-accelerated realesrgan-ncnn-vulkan engine as standalone, but with Upscayl's curated model selection bundled.

When to use

Low-res source needs to be enlarged for print or display.
AI-generated image at 1024px wants 4096px output without re-prompting.
Old photos / screenshots need detail recovery.

Do not use this skill when:

The source is already large enough — upscaling rarely improves a 4K-native image.
The user wants traditional bicubic / lanczos upscaling — fast-resize is the right tool (much faster, no AI).
The image is text/document-heavy — upscalers can hallucinate glyph detail; consider tesseract re-OCR + re-typeset instead.

Inputs

Input — file or directory. Required.
Scale — 2, 3, or 4 (Upscayl's bundled models are 4× natively; 2× and 3× are produced by post-resize). Default 4.
Model — one of:
- upscayl-standard-4x (default — best general-purpose photo upscaler).
- upscayl-lite-4x (faster, lower quality, good for batches).
- realesrgan-x4plus (classic, slightly different texture handling).
- realesrgan-x4plus-anime (illustrations, line art, anime).
- remacri-4x / ultramix-balanced-4x (alternative photo models if installed).
- Or --model-path <dir> --model-name <name> to point at a custom model.
Output dir — default: <input-dir>/upscaled/. Skill never overwrites originals.
Output format — default png (lossless preserves the upscale fidelity). jpg option for size-sensitive batches (uses quality 92).
Recursive — --recursive for directory descent.
GPU — default auto-detect. --gpu <n> to pick a specific GPU. --cpu to force CPU (slow — only for headless boxes).

Procedure

Locate the binary. Check in order:
- which upscayl-bin
- /opt/Upscayl/resources/bin/upscayl-bin
- ~/.var/app/org.upscayl.Upscayl/data/bin/upscayl-bin (Flatpak)
- which realesrgan-ncnn-vulkan (fallback — same syntax, smaller model selection)

Read the full file on GitHub · 108 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.

2mo ago First seen · 108 lines · 98 tokens per session scan A 7e3eba9a131a

Subscribe to this mod's changes

upscale-image is a skill published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (21 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 1,505 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.

Creative and media

upscale-image next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
upscale-imagedanielrosehill/Claude-Image-Production-Plugin	Skill	21	yesterday	MIT	A	98	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code