Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/S3YED/appie-kitnpx agentmods add skills/s3yed/appie-kit/thumbnailsWrote 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/s3yed/appie-kit/thumbnails)<a href="https://agentmods.dev/skills/s3yed/appie-kit/thumbnails"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/thumbnails/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/s3yed/appie-kit/thumbnails"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/thumbnails.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 | $0.00021 | $0.01046 |
| Opus 5 | $0.00010 | $0.00523 |
| Sonnet 5 | $0.00004 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
thumbnails 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 9d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL.md - YouTube Thumbnail Generator
Generate YouTube thumbnails from approved portrait assets, HTML templates, and the project brand guidelines.
Assets Location
- Approved portraits:
$THUMBNAIL_PHOTO_DIRcloseup.jpg- Close-up face shot, best for thumbnailsspeaking.jpg- Speaking/presenting poseframe-01.jpg- source video frameframe-02.jpg- source video framewebcam.png- webcam screenshot
- HTML templates:
$THUMBNAIL_TEMPLATE_DIRclient-success.html- For client story videos (revenue numbers + face)interview.html- For interview/conversation videoseducational.html- For tutorial/how-to videos
- Generator script:
$THUMBNAIL_GENERATOR - Full brand system:
$THUMBNAIL_BRAND_SYSTEM
How to Generate a Thumbnail
Method 1: Puppeteer Script (Preferred)
cd "$THUMBNAIL_WORKDIR"
chmod +x generate-thumbnail.sh
./generate-thumbnail.sh <template> <output> --text-main "TEXT" --text-sub "TEXT" --face "$THUMBNAIL_FACE_IMAGE"
Examples:
# Client success story
./generate-thumbnail.sh client-success ./output/new-thumb.jpg \
--text-main '$0 to $8K' --text-sub 'IN 30 DAYS' \
--face $THUMBNAIL_FACE_IMAGE
# Interview thumbnail
./generate-thumbnail.sh interview ./output/interview.jpg \
--text-main 'How I Built 3 AI Agents' --text-sub 'LIVE DEMO' \
--face $THUMBNAIL_FACE_IMAGE
# Educational tutorial
./generate-thumbnail.sh educational ./output/tutorial.jpg \
--text-main 'n8n + AI' --text-sub 'FULL TUTORIAL' \
--face $THUMBNAIL_FACE_IMAGE
Method 2: AI Image Generation
When the Puppeteer script isn't enough (custom layouts, special effects), use the image_generate tool:
Prompt formula:
YouTube thumbnail, 1280x720, [SCENE DESCRIPTION].
Left side: photo of the approved presenter portrait,
wearing [OUTFIT]. Right side: bold white text "[3-5 WORDS]" on dark green
background (#031D16). Gold accent (#DFB771) highlight on key word.
Bottom right: small "<BRAND>" text in gold. High contrast, professional,
clean composition. No em dashes.
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.
- 9d ago First seen · 115 lines · 21 tokens per session scan A 6c309d5a40d6
thumbnails is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 17d ago), licensed MIT. It adds 21 tokens to every session and 1,046 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
content-distribution
Content distribution as a discipline. Owned channels (newsletter, blog, social), earned channels (PR, syndication, mentions), paid channels (boosted posts, syndication networks), and the channel-fit decisions that distinguish strategic distribution from spam-everywhere. Audience-channel matching, content-channel…
review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…
agents-md-protocol
Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a custom harness needs a predictable context file.
investment-memo-generator
Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.
python-memory-safe-scripts
Memory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allocator purge (mimalloc/glibc malloctrim), HTTP response lifecycle, DataFrame cleanup, thread-local connection reuse, and periodic GC cadence. Battle-tested through 5 OOM optimization cycles on production GPU…