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 Varnan-Tech/opendirectory --skill graphic-gifgit clone --depth 1 https://github.com/Varnan-Tech/opendirectoryWrote 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/varnan-tech/opendirectory/graphic-gif)<a href="https://agentmods.dev/skills/varnan-tech/opendirectory/graphic-gif"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/graphic-gif/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/varnan-tech/opendirectory/graphic-gif"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/graphic-gif.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 85 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00082 | $0.03216 |
| Opus 5 | $0.00041 | $0.01608 |
| Sonnet 5 | $0.00016 | $0.00643 |
| Haiku 4.5 | $0.00008 | $0.00322 |
Grade A, and why
graphic-gif 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 10d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
graphic-gif
Generates an animated looping GIF from CSS animations or an AI image-to-video API. Output: animation.gif.
Unlike every other graphic- skill that outputs a static PNG or PDF, this skill outputs an animated .gif. Uses CSS @keyframes animations captured frame-by-frame via Playwright and the Web Animations API (Option A, default), or an AI image-to-video pipeline via Kling (Option B).
Critical Rules (read before every generation)
- Default is css-animated. Never use
ai-generatedunless explicitly requested. - Canvas is 800×800px square. All
clamp()values computed at 800px (1vw = 8px). - Single self-contained HTML. All CSS inline in
<style>. Font CDN<link>only external dependency. - Never dump HTML in chat. Save to file, show summary only.
- Frame capture uses Web Animations API seeking. NOT
setTimeoutloops, NOTanimation-delaytricks. - Exact frame count:
Math.floor(duration_seconds * fps)frames. The frame att=duration_msMUST NOT be captured — it duplicatest=0and causes a visible stutter at the loop point. - No placeholder boxes. CSS-generated visuals only. No "image goes here" elements.
- Simpler palettes = smaller files. Use:
clean-slate,terminal,electric-burst,brutalist. - No animation-delay for stagger. Bake stagger into
@keyframespercentages — frame seeking handles timing. - Commit to design direction before writing CSS. Tone, signature element, motion style, unforgettable detail — all decided before first line of code.
Step 1: Intake
Required: prompt (content description AND motion brief)
Optional with defaults:
| Parameter | Default | Options |
|---|---|---|
| animation_type | css-animated | css-animated / ai-generated |
| duration | 3.0 | seconds |
| fps | 12 | frames per second |
| loop | true | true / false |
| style | clean-slate | clean-slate / terminal / electric-burst / brutalist |
| dimensions | 800x800 | WxH in pixels |
| optimization | balanced | quality / balanced / filesize |
What ships with it
6 files 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.
- 10d ago First seen · 314 lines · 82 tokens per session scan A be7a73896a8b
graphic-gif is a skill published in the GitHub repository Varnan-Tech/opendirectory (637 stars, last pushed 24d ago), licensed MIT. It adds 82 tokens to every session and 3,216 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
marketing-collateral-design
Use this skill to create professional static promotional graphics whose typography, claims, and contact details must remain exact. The core production rule is hybrid, not one-shot: generate or source imagery separately, then compose real text and vector elements deterministically in HTML/CSS/SVG. Image models are art…
animated-portfolio-sites
Build a one-page animated personal or portfolio site (canvas starfield, rotating galaxies with mouse parallax, hidden accordion/card content, anchor nav) and publish it free on GitHub Pages. Covers the canvas technique and the Pages permission wall, not just one task.
blog-cover-image
Generate and revise raster cover images for blog posts and articles from a title, brief, draft, local file, URL content supplied by the user, or reference images. Use when Codex needs to create a blog cover, article hero/header image, editorial thumbnail, Open Graph/social preview visual, or a channel-specific cover…
chanjing-one-click-video-creation
An automated workflow for turning a topic or production plan into a finished short video, including the script, shot plan, digital-person narration, and AI-generated visuals.
chanjing-tts-voice-clone
Use Chanjing TTS API to synthesize speech from text with a user-provided cloned voice (reference audio via public URL).
chanjing-avatar
Use Chanjing Avatar API for lip-syncing video generation (upload audio/video, create tasks, poll results).