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 lossless-group/lossless-agent-skills --skill prep-images-for-embedgit clone --depth 1 https://github.com/lossless-group/lossless-agent-skillsWrote 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/lossless-group/lossless-agent-skills/prep-images-for-embed)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/prep-images-for-embed"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/prep-images-for-embed/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/lossless-group/lossless-agent-skills/prep-images-for-embed"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/prep-images-for-embed.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 | $0.00189 | $0.03766 |
| Opus 5 | $0.00095 | $0.01883 |
| Sonnet 5 | $0.00038 | $0.00753 |
| Haiku 4.5 | $0.00019 | $0.00377 |
Grade B, and why
prep-images-for-embed scanned grade B 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# ~/.secrets (chmod 600) — same pattern as generate-consistent-og-images How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prep Images for Embed
The one thing to remember: upload JPEG, not WebP. ImageKit converts to WebP for browsers that accept it and falls back to JPEG for those that don't. Upload WebP and the fallback becomes a PNG up to 3× larger. Measured, not assumed — see Format.
When to use this skill
- The user drops screenshots and wants them in a changelog entry, splash page, spec, or any markdown surface
- "Add these screenshots", "put these in the changelog", "upload these"
- Local image references need converting to CDN URLs
- An image is destined to become an
og:image - Any markdown surface should become image-heavy without the user manually uploading and pasting links
Why this exists
Screenshots arrive as Screenshot 2026-08-14 at 9.11.31 PM.png — 400KB of PNG
with a filename that is useless to a search engine and a reader. Getting one into
a changelog properly means renaming it, resizing it, stripping metadata,
hosting it somewhere with correct headers, and writing alt text. That's six steps
of tedium per image, which is why posts end up with no images at all.
This skill makes it one call.
Prior art worth knowing: content-farm/plugin-modules/image-gin already does
ImageKit upload — but from inside Obsidian, via a modal, on a note you have open.
This skill is the agent-callable path. The auth pattern here (Basic base64(privateKey + ':')) is lifted from image-gin's imagekitService.ts
deliberately, so the two don't diverge.
Prerequisites
# ~/.secrets (chmod 600) — same pattern as generate-consistent-og-images
IMAGEKIT_PRIVATE_KEY="private_..."
IMAGEKIT_PUBLIC_KEY="public_..."
IMAGEKIT_URL_ENDPOINT="https://ik.imagekit.io/<id>"
Tooling: sips (macOS built-in) does resize and JPEG. exiftool strips
metadata. cwebp is only needed for the discouraged --format webp path.
The call
node scripts/prep-images.mjs \
--slug plane-first-deploy \
--repo self-host-stack \
--src "~/Desktop/Screenshot 2026-08-14 at 9.11.31 PM.png" \
--name "Railway__Usage-By-Project" \
--alt "Railway usage dashboard showing \$46.59 current usage broken out across six client projects" \
--emit html
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 327 lines · 189 tokens per session scan B 7a02237d0c40
prep-images-for-embed is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 18d ago), licensed MIT. It adds 189 tokens to every session and 3,766 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…
infographics
Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.
paper-2-web
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
remotion-upgrade
Upgrade Remotion, and related packages.
remotion-docs
Search and fetch Remotion documentation pages.
aws-wechat-article-assets
A local library for storing business descriptions, product images, and reusable writing or design presets for WeChat articles. It organizes these materials by product so other article tools can reuse them.