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 dylantarre/animation-principles --skill attention-directiongit clone --depth 1 https://github.com/dylantarre/animation-principlesWrote 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/dylantarre/animation-principles/attention-direction)<a href="https://agentmods.dev/skills/dylantarre/animation-principles/attention-direction"><img src="https://agentmods.dev/badge/skills/dylantarre/animation-principles/attention-direction/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/dylantarre/animation-principles/attention-direction"><img src="https://agentmods.dev/badge/skills/dylantarre/animation-principles/attention-direction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00034 | $0.00891 |
| Opus 5 | $0.00017 | $0.00445 |
| Sonnet 5 | $0.00007 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
attention-direction 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attention Direction
Think like a magician controlling where the audience looks. Animation is misdirection and direction. You decide what matters, then make it impossible to miss—while hiding what shouldn't be seen yet.
Core Mental Model
Before animating any scene, ask: Where should the eye go, and in what order?
Audiences can only look at one thing at a time. Your job is to guide their attention through the frame and through time. Every element either supports focus or competes with it.
The 12 Principles Through Focus
Staging — The foundation of attention direction. Clear silhouettes. Uncluttered compositions. Important elements separated from background. Staging serves focus.
Timing — Attention follows movement. Motion against stillness commands the eye. Strategic timing controls when things get noticed. Stillness is also a tool.
Anticipation — Attention setup. Before the important thing, direct eyes to where it will happen. Anticipation is a spotlight warming up before the main act.
Secondary Action — Supporting, not competing. Secondary elements should enhance focus on primary action, not steal attention. The backup singer shouldn't upstage the lead.
Follow Through & Overlapping Action — Attention carries momentum. Where one motion ends, the eye expects the next to begin. Use follow-through to guide gaze through sequences.
Exaggeration — Emphasis through amplification. Important elements are bigger, faster, more contrasted. Exaggeration says "look here." Restraint says "this can wait."
Squash & Stretch — Visual attention-grabbers. Impact frames (squash) and speed lines (stretch) create pops of visual interest that capture the eye.
Arcs — Eye paths. The audience's gaze follows arcs of motion. Design movement paths that lead attention where you want it to land.
Slow In & Slow Out — Attention ramps. Ease-in gives time to find the action. Ease-out gives time to process. Control pacing of comprehension.
Solid Drawing — Hierarchy through form. Important elements have more dimensional presence. Background elements are flatter, less detailed. Volume commands attention.
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 · 85 lines · 34 tokens per session scan A 155946c3afa6
attention-direction is a skill published in the GitHub repository dylantarre/animation-principles (80 stars, last pushed 8mo ago), licensed MIT. It adds 34 tokens to every session and 891 once invoked, about $0.0002 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
animation-reverse-engineering
Reverse-engineer any motion reference (a video from X/Twitter, Dribbble, a screen recording, a GIF) into production animation code through frame-level dissection. Use when the user shares a video/URL and says "implement this animation", "recreate this motion", "port this interaction", "how does this animate", "clone…
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.
slideshow
Author a HyperFrames slideshow — a presentation, pitch deck, or interactive deck with discrete slides, fragment reveals, branching, hotspot navigation, and built-in presenter mode with speaker notes; also converts an existing page into a deck. Output is a navigable deck, not a rendered MP4. If the user didn't…
hyperframes-core
The HyperFrames composition contract — build one renderable project. Use for composition structure, the data- timing attributes, class="clip", tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Also covers Tailwind projects and the STORYBOARD.md / SCRIPT.md…
muapi-seedance-2
Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.
muapi-workflow
Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.