upscale-image

upscale-image is a skill for Claude Code from danielrosehill/Claude-Image-Production-Plugin. It costs 98 tokens per session (1,505 once invoked), scanned A, original, MIT.

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.

In plain words
What is it for?
Use it to enlarge image files or folders, including old photos and small AI images; choose regular resizing instead for simple non-AI enlargement.
Why use it?
It helps prepare low-resolution photos, screenshots, and AI-generated images for larger displays or printing without generating a new image from a prompt.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the image-production plugin — 29 skills, 19 commands shipped together

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

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danielrosehill/claude-image-production-plugin/upscale-image
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.

agentmods badge for upscale-image

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/upscale-image.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.svg" alt="Measured on agentmods" 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.01505
Opus 5 $0.00049 $0.00753
Sonnet 5 $0.00020 $0.00301
Haiku 4.5 $0.00010 $0.00151

Measured 8d ago against content hash 7e3eba9a131a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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

  1. Input — file or directory. Required.
  2. Scale2, 3, or 4 (Upscayl's bundled models are 4× natively; 2× and 3× are produced by post-resize). Default 4.
  3. 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.
  4. Output dir — default: <input-dir>/upscaled/. Skill never overwrites originals.
  5. Output format — default png (lossless preserves the upscale fidelity). jpg option for size-sensitive batches (uses quality 92).
  6. Recursive--recursive for directory descent.
  7. GPU — default auto-detect. --gpu <n> to pick a specific GPU. --cpu to force CPU (slow — only for headless boxes).

Procedure

  1. 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.

  1. 8d 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 (16 stars, last pushed 21d ago), licensed MIT. It adds 98 tokens to every session and 1,505 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens