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 divinevideo/divine-mobile --skill art-directgit clone --depth 1 https://github.com/divinevideo/divine-mobileWrote 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/divinevideo/divine-mobile/art-direct)<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/art-direct"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/art-direct/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/divinevideo/divine-mobile/art-direct"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/art-direct.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Supply Chain · line 450 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Data Exfiltration · line 400 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.
- medium Data Exfiltration · line 450 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 | $0.00073 | $0.04546 |
| Opus 5.5 | $0.00029 | $0.01818 |
| Sonnet 5.5 | $0.00015 | $0.00909 |
| Haiku 4.5 | $0.00007 | $0.00455 |
Grade A, and why
art-direct 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://queue.fal.run/fal-ai/flux-pro/v1.1" \ How it starts
The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Art Direct
Turn content into visual direction. Point this at anything — a deck, a document, an essay, a brief, a webpage — and get back a creative direction you can actually execute.
When to Use
- User shares a file (any format) and needs visuals for it
- Developing visual identity for content before building/designing
- Translating written material into photography/illustration direction
- Creating image prompts for AI generation tools
- Art directing a presentation, document, report, or website
- Reviewing existing visuals against content intent (critique mode)
Supported Inputs
Read content from whatever the user provides:
| Format | How to read |
|---|---|
.txt, .md |
Read tool directly |
.html |
Read tool, strip tags to extract text + structure |
.pdf |
Read tool with pages parameter |
.docx |
Extract via python3 -c "import docx; ..." or textutil -convert txt on macOS |
.pptx |
Extract via python3 -c "from pptx import Presentation; ..." |
.rtf |
textutil -convert txt on macOS |
| URL | WebFetch tool |
If a format doesn't extract cleanly, ask the user to paste the text.
The Workflow
INGEST CONTENT → ANALYSE → PROPOSE 2-3 DIRECTIONS → USER SELECTS → VISUAL BRIEF + PROMPTS
Stage 1: Content Ingestion & Analysis
Read the full content. Extract:
- Structure — What are the units? (slides, sections, chapters, paragraphs, pages)
- Core themes — The 2-3 big ideas the content is actually about
- Narrative arc — Does it build? Contrast? Layer? List?
- Audience — Who receives this? What do they expect to see?
- Tone — Authoritative? Inspirational? Intimate? Provocative? Technical?
- Key moments — Which sections carry the most weight, demand the strongest visuals?
- Existing visual language — If the content already has images, assess what's working and what isn't
Output a brief content summary before proceeding. Keep it tight — this is for alignment, not a book report.
What ships with it
5 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.
- 1mo ago First seen · 534 lines · 73 tokens per session scan A fea25131a9ef
art-direct is a skill published in the GitHub repository divinevideo/divine-mobile (264 stars, last pushed today), licensed MPL-2.0. It adds 73 tokens to every session and 4,546 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.