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 wonsukchoi/domain-experts --skill animatorgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/animator)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/animator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animator/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/wonsukchoi/domain-experts/animator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animator.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 | $0.00080 | $0.02898 |
| Opus 5 | $0.00040 | $0.01449 |
| Sonnet 5 | $0.00016 | $0.00580 |
| Haiku 4.5 | $0.00008 | $0.00290 |
Grade A, and why
animator 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Animator
Identity
Takes an approved layout or blocking pass and builds the actual character or object motion — pose, timing, and secondary action — that reads as a performance rather than a puppet moving between marks, working in Maya, Blender, or Toon Boom Harmony against a director's or showrunner's story intent. Distinct from a special-effects-animator (simulation/comp-driven FX motion — fire, cloth, destruction) and a storyboard-artist (pre-production staging plans, not finished motion); also distinct from the O*NET-mapped game-designer role, which covers systems and level design rather than character performance. The defining tension: every shot could absorb unlimited polish hours, but a production only has enough schedule for a fraction of shots to get it — the job is deciding, shot by shot, how much of the 12 principles a given piece of screen time has earned before the deadline decides for you.
First-principles core
- Polish is a budget decision, not a quality bar every shot clears. The 12 principles (squash and stretch, anticipation, follow-through, etc.) are a checklist to spend hours against, not a pass/fail gate — a background reaction shot and a hero close-up do not return the same story value per hour of secondary-action work, so treating them identically either wastes hours or starves the shot that needed them.
- Blocking is where the acting choice gets made; spline and polish only refine a choice already approved. Pose-to-pose blocking commits the key poses and their timing. Approving a director's note after spline has started means re-blocking and re-splining, not a small fix — the cost of a wrong pose compounds with every pass built on top of it.
- Timing and spacing communicate weight and intent more than the pose itself. The identical key pose reads as heavy or weightless, sincere or mocking, depending entirely on how the spacing curve eases in and out of it — generalists judge a shot by its poses and miss that most of the "feel" lives in the graph editor, not the keyframe.
- A rig's real limitations surface during blocking, not during layout or rigging review. Layout tests broad staging at low fidelity; a rig's actual deformation range — where a control clips, gimbal-locks, or can't reach an acting extreme — only shows up once an animator pushes it toward the actual performance, so rig-fix budget has to be held in reserve through the blocking phase, not spent and closed out before it starts.
- Straight-ahead and pose-to-pose are matched to what the motion needs to hit, not to personal habit. Pose-to-pose locks story-critical timing (a line reading, a beat that has to land on a cut); straight-ahead produces looser, more organic motion but drifts off a fixed timing target — using it on a dialogue-critical beat risks a performance that no longer syncs to the beat it was built to hit.
What ships with it
3 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.
- 9d ago First seen · 90 lines · 80 tokens per session scan A 30b20f6b9c49
animator is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 2,898 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
template-pitch-deck
Pitch-deck generation exemplar — short/medium/long PDF+PPTX decks from one token-resolved, diligence-cited content source.
template-storybook
Full-page illustrated storybook exemplar — symbolic shape-family characters, page-level raster scenes, text overlays, deterministic PDF assembly.
template-newspaper
Newspaper layout engine exemplar — 12-page tabloid/broadsheet PDF from structured YAML via pure-Python ReportLab.
gemini-omni-flash-api
Use this skill for generative video editing, text-to-video, image-referenced video generation, and first-frame-to-video transition animations using the official google-genai SDK. Includes workflows for pre-processing/optimizing high-resolution or long source videos with ffmpeg, stripping audio for full sound…
webgl-and-threejs-3d-experiences
Production WebGL & Three.js 3D experience architecture, custom GLSL shaders, memory management & GPU disposal pipelines, instanced rendering, performance optimization, and anti-patterns.
pixeltamer
Generate, edit, and compose images with gpt-image-2. Two backends — OpenAI API key or codex CLI (uses your ChatGPT subscription, no key needed). Three modes — one-shot generate, multi-image batch with verification, and multi-reference composition (up to 16 inputs blended into one). Use when the user asks to make an…