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 | $0.00073 | $0.04294 |
| Opus 5 | $0.00036 | $0.02147 |
| Sonnet 5 | $0.00015 | $0.00859 |
| Haiku 4.5 | $0.00007 | $0.00429 |
Grade A, and why
img-convert scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
const stdout = execSync('img-convert batch jobs.json --json 2>/dev/null', { encoding: 'utf8' }) How it starts
The opening of the file, as written. The whole thing — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.
img-convert Skill
img-convert is a Sharp-based image conversion tool available as a CLI, Node.js API, and MCP server. This skill covers how to use each interface correctly, choose between them, and build reliable agent workflows.
Interface Selection
Choose the right interface for the context:
| Situation | Use |
|---|---|
| Shell task, build script, CI pipeline | CLI (img-convert) |
| Node.js code that needs the output buffer | Node.js API (import { convert } from '@dutchbase/img-convert') |
| Claude Code or MCP-enabled AI agent | MCP tools (convert_image, get_image_info) |
| Browser or external HTTP client | REST API (POST /api/convert) |
| Multiple files with different settings each | CLI batch subcommand or API batch() |
Inspect Before Converting
Always run info first on unknown images. It reveals format, dimensions, alpha, EXIF, animation, and color space — all of which affect conversion decisions.
img-convert info photo.jpg
{
"format": "jpeg",
"width": 4032,
"height": 3024,
"filesize": 3891200,
"hasAlpha": false,
"hasExif": true,
"colorSpace": "srgb",
"isAnimated": false,
"channels": 3,
"density": 72
}
Key decisions driven by info:
hasAlpha: true+ converting to JPEG → must pass--background "#ffffff"or pixels go blackisAnimated: true→ only GIF→WebP preserves animation; all other targets capture frame 1 onlycolorSpace: "cmyk"→ convert tosrgbfirst for web usewidth × height > 25_000_000→ tool will reject withIMAGE_TOO_LARGE; resize first
CLI Reference
Convert (default command)
img-convert [files...] -f <format> [options]
files accepts paths, glob patterns, and HTTP/HTTPS URLs.
All flags
| Flag | Default | Description |
|---|---|---|
-f, --format |
— | Required. jpeg png webp avif gif tiff |
-q, --quality <n> |
85 |
1–100. JPEG/WebP/AVIF/TIFF. PNG uses derived compression. GIF ignores it. |
--width <n> |
— | Resize width in pixels. Maintains aspect ratio. |
--height <n> |
— | Resize height in pixels. Maintains aspect ratio. |
--no-metadata |
— | Strip EXIF/XMP/IPTC. ICC profile always kept. |
-o, --output <dir> |
input dir | Output directory. Created if absent. |
-c, --concurrency <n> |
4 |
Parallel workers. |
--json |
— | Data → stdout as JSON. Progress/errors → stderr. |
--dry-run |
— | Preview without writing. |
--quiet |
— | Suppress per-file lines. |
--grayscale |
— | Desaturate to greyscale. |
--rotate <n> |
— | Rotate by degrees. Empty corners filled with --background. |
--flip |
— | Horizontal mirror (left–right). |
--flop |
— | Vertical mirror (top–bottom). |
--background <color> |
— | Fill color: #ffffff, rgba(0,0,0,0), etc. |
--blur <sigma> |
— | Gaussian blur, sigma 0.3–1000. |
--sharpen |
— | Unsharp mask with default parameters. |
--normalize |
— | Stretch contrast to full range. Good for scans. |
--trim |
— | Remove uniform-color border pixels. |
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.
- 11d 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 4d ago), licensed MIT. It adds 73 tokens to every session and 4,294 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
wechat-delivery
A workflow for preparing WeChat Official Account articles, images, covers, and publishing files in Chinese. WeChat Official Accounts are channels used by organizations to publish articles to followers.
ai-image-to-pptx
A workflow that creates a set of related images with AI and places them into a real PowerPoint file. The resulting .pptx file can be opened and edited in PowerPoint, Keynote, or WPS.
html-ppt-viewer
A simple HTML viewer that presents a set of existing images like a slide deck. It includes a side panel, large image display, page controls, and keyboard navigation, but does not create the images.