image

image is a skill for Claude Code, Codex from mazumba/opencode-dockerized. It costs 39 tokens per session (653 once invoked), scanned A, original, MIT.

An image-processing workflow using libvips, a command-line library for handling images. It supports common conversions, resizing, cropping, thumbnails, and batch optimisation.

In plain words
What is it for?
Use it to convert images to formats such as AVIF, WebP, or JPEG, resize and crop them, create thumbnails, and process image files in batches.
Why use it?
It provides a defined way to process images in an environment that does not have ImageMagick or the Python libvips package.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to convert images to formats such as AVIF, WebP, or JPEG, resize and crop them, create thumbnails, and process image files in batches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mazumba/opencode-dockerized/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 mazumba/opencode-dockerized --skill image
Clone the repo
git clone --depth 1 https://github.com/mazumba/opencode-dockerized

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 image

README.md
[![agentmods](https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/image/github.svg)](https://agentmods.dev/skills/mazumba/opencode-dockerized/image)
Your own site
<a href="https://agentmods.dev/skills/mazumba/opencode-dockerized/image"><img src="https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/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.

agentmods 80×15 button for image

Your own site · 80×15
<a href="https://agentmods.dev/skills/mazumba/opencode-dockerized/image"><img src="https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 653 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.
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 $0.00039 $0.00653
Opus 5.5 $0.00016 $0.00261
Sonnet 5.5 $0.00008 $0.00131
Haiku 4.5 $0.00004 $0.00065

Measured 15d ago against content hash d729e7f1b3f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 15d 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.

docker/plugins/image/image.skills/image/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The container has the libvips CLI (vips, vipsthumbnail, vipsheader), version 8.14. There is no ImageMagick and no pyvips. Use the CLI.

Options and formats

Save options go in brackets after the output filename, and the suffix picks the format: out.avif[Q=50,strip]. Quote the filename in the shell. To list a saver's options, run vips heifsave, vips webpsave or vips jpegsave with no arguments.

Target Command Notes
AVIF vips copy in.png 'out.avif[Q=50,effort=4]' Q 45–60 suits photos. effort (0–9) costs CPU time: effort 4 on a 4 MP image takes about 3 s, effort 2 about 0.5 s.
WebP vips copy in.png 'out.webp[Q=80]' Use [lossless] for UI art or screenshots, preset=drawing for flat colour.
JPEG vips copy in.png 'out.jpg[Q=85,strip]'

Loaders also cover PNG, GIF, TIFF, HEIC, JXL, SVG and PDF. For PDFs and animations, pick a page or frame with in.pdf[page=0,dpi=150].

Resizing

  • Use vips thumbnail in.jpg 'out.webp[Q=80]' 800. The number is the target width. Add --height 600 to bound both sides, --crop attention to fill the box exactly, and --size down so smaller images are never upscaled.
  • thumbnail applies the EXIF orientation. copy does not, so camera photos come out sideways. For a format conversion without resizing, run vips autorot in.jpg rotated.v first, then vips copy rotated.v 'out.avif[Q=50]'.
  • strip drops EXIF and GPS data. Use it for anything you publish.

Batches

To process many files, use vipsthumbnail -s 1200x -o '%s.avif[Q=50,strip]' *.jpg. In the -o pattern, %s is the input file's base name, and a relative output path is resolved against each input's directory, not the working directory. For a separate output directory, give an absolute path such as -o '/abs/out/%s.webp[Q=80]'.

After a batch, check one result with vipsheader -a out.avif and compare file sizes with ls -l. A result larger than its source means Q is too high or lossless is on.

Read the full file on GitHub · 31 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. 15d ago First seen · 31 lines · 39 tokens per session scan A d729e7f1b3f2

Subscribe to this mod's changes

image is a skill published in the GitHub repository mazumba/opencode-dockerized (6 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 653 once invoked, about $0.0002 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 2026-10-24.

Related

image compared with skills from other repositories

image next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
imagemazumba/opencode-dockerizedSkill62d agoMITA39Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code