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.
npx skills add dutchbase/img-converter --skill img-convertergit clone --depth 1 https://github.com/dutchbase/img-converterWrote 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.
[](https://agentmods.dev/skills/dutchbase/img-converter/img-converter)<a href="https://agentmods.dev/skills/dutchbase/img-converter/img-converter"><img src="https://agentmods.dev/badge/skills/dutchbase/img-converter/img-converter/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.
<a href="https://agentmods.dev/skills/dutchbase/img-converter/img-converter"><img src="https://agentmods.dev/badge/skills/dutchbase/img-converter/img-converter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00096 | $0.04551 |
| Opus 5.5 | $0.00038 | $0.01820 |
| Sonnet 5.5 | $0.00019 | $0.00910 |
| Haiku 4.5 | $0.00010 | $0.00455 |
Grade A, and why
img-convert 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
img-convert
Sharp-based image converter. This guide covers v2 of the CLI (img-convert --version prints 2.x). Prefer the CLI; the MCP server and Node API are covered briefly at the end.
Rules for agents
- Always pass
--jsonand parse stdout. Progress and warnings go to stderr. - Parse stdout even when the exit code is 1. Exit 1 means some items failed; the JSON array still lists every item. Check each item's
ok. - Exit 2 means the command itself was wrong (bad flag, unknown format, no matching files, bad manifest). With
--json, stdout is{"error":{"code","message"}}. Fix the command; don't retry it unchanged. - Read the
outputpath from the JSON. Don't predict it: filenames are sanitized (my photo.jpg→my_photo.webp). - Quote glob patterns (
"imgs/*.png","imgs/**/*.png"where**recurses into subfolders,"*.{jpg,png}") so the CLI expands them, not the shell. Prefer absolute paths. - Run
img-convert infofirst on images you know nothing about (alpha, animation, size). - For different settings per file, use a
batchmanifest (img-convert batch - --jsonreads it from stdin) instead of a shell loop. - No in-place edits: writing to the input's own path is refused (
OUTPUT_IS_INPUT). Write to another directory with-o, then move the file if needed. - Metadata (including GPS) is kept by default. Pass
--no-metadatato strip it.
Recipes
# Convert one file (output goes next to the input: photo.webp)
img-convert /abs/photo.jpg -f webp --json
# Web-optimize a folder into another folder
img-convert "/abs/site/img/*.{jpg,png}" -f webp -q 80 --no-metadata -o /abs/site/img-webp --json
# Exact-size square thumbnail (crops to fill)
img-convert /abs/photo.jpg -f webp --width 200 --height 200 --fit cover -o /abs/thumbs --json
# Fit inside a box, keep aspect ratio (default --fit inside; never enlarges)
img-convert /abs/banner.png -f jpeg --width 1280 --height 720 --json
# Stay under an upload limit (highest quality that fits; jpeg/webp/avif only)
img-convert /abs/photo.png -f jpeg --max-size 200KB --json
# Strip EXIF/GPS but keep the format: write elsewhere, then move.
# This re-encodes the image, so use a high -q to avoid visible quality loss.
img-convert /abs/photo.jpg -f jpeg -q 95 --no-metadata -o /abs/clean --json && mv /abs/clean/photo.jpg /abs/photo.jpg
# iPhone HEIC → JPEG (HEIC must be a local .heic/.heif file or stdin)
img-convert /abs/IMG_0001.HEIC -f jpeg --json
# Transparent PNG → JPEG (transparency becomes white; choose another fill with --background)
img-convert /abs/logo.png -f jpeg --background "#000000" --json
# Crop a region (left,top,width,height in pixels of the upright source), then resize
img-convert /abs/shot.png -f png --crop 100,50,800,600 --width 400 -o /abs/out --json
# Keep animation (GIF/WebP → GIF/WebP only)
img-convert /abs/anim.gif -f webp --json
# From a URL (saved in the current directory unless -o is given)
img-convert https://example.com/pic.png -f avif -o /abs/downloads --json
# Pipe: stdin → stdout (no JSON; errors on stderr, exit 1)
cat in.png | img-convert -f webp > out.webp
# Inspect a folder
img-convert info "/abs/imgs/*"
# Whole tree, recursively (quote the glob)
img-convert "/abs/imgs/**/*.png" -f webp -o /abs/out --json
# Same filenames in different folders (a/x.png, b/x.png) would collide in one -o dir
# (DUPLICATE_OUTPUT). Keep them apart by giving each item its own outputDir:
find /abs/imgs -name '*.png' | jq -R '{input: ., format: "webp", outputDir: ("/abs/out" + (. | ltrimstr("/abs/imgs") | sub("/[^/]*$"; "")))}' \
| jq -s . | img-convert batch - --json
# Preview a big job without writing anything
img-convert "/abs/imgs/**/*.png" -f avif -o /abs/out --dry-run --json
# Different settings per file
echo '[{"input":"/abs/a.png","format":"webp","width":800},{"input":"/abs/b.png","format":"jpeg","maxSize":"100KB"}]' \
| img-convert batch - --json
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.
- 1mo ago Changed · -271 lines · +23 tokens per session 69334499677d
- 1mo ago First seen · 532 lines · 73 tokens per session scan A f5ac1c0bb007
img-convert is a skill published in the GitHub repository dutchbase/img-converter (3 stars, last pushed 19d ago), licensed MIT. It adds 96 tokens to every session and 4,551 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 2026-08-31.
Other skills, from other repositories
opencli-usage
Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.
tokf-filter
This skill should be used when the user asks to "create a filter", "write a tokf filter", "add a filter for ", "how do I filter output", or needs guidance on tokf filter step types, templates, pipes, or placement conventions.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.