html-anime-cel

html-anime-cel is a skill for Claude Code, Codex from blixvip/html-anime. It costs 63 tokens per session (544 once invoked), scanned A, original, MIT.

A drawing guide for painting individual frames of an anime in SVG or HTML. It defines flat colors, outlines, hard shadows, layered backgrounds, rain, and a fixed color script.

In plain words
What is it for?
It helps draw characters, backgrounds, blades, weather, lighting, and other frame elements for an HTML anime film.
Why use it?
It gives code-generated artwork consistent visual rules and avoids introducing colors or effects that were not requested.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps draw characters, backgrounds, blades, weather, lighting, and other frame elements for an HTML anime film.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blixvip/html-anime/html-anime-cel
Install

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.

Any agent
npx skills add blixvip/html-anime --skill html-anime-cel
Clone the repo
git clone --depth 1 https://github.com/blixvip/html-anime

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for html-anime-cel

README.md
[![agentmods](https://agentmods.dev/badge/skills/blixvip/html-anime/html-anime-cel/github.svg)](https://agentmods.dev/skills/blixvip/html-anime/html-anime-cel)
Your own site
<a href="https://agentmods.dev/skills/blixvip/html-anime/html-anime-cel"><img src="https://agentmods.dev/badge/skills/blixvip/html-anime/html-anime-cel/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.

agentmods 80×15 button for html-anime-cel

Your own site · 80×15
<a href="https://agentmods.dev/skills/blixvip/html-anime/html-anime-cel"><img src="https://agentmods.dev/badge/skills/blixvip/html-anime/html-anime-cel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 544 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.00544
Opus 5.5 $0.00025 $0.00218
Sonnet 5.5 $0.00013 $0.00109
Haiku 4.5 $0.00006 $0.00054

Measured yesterday against content hash 7a4856a47bd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

html-anime-cel 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 yesterday.

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.

skills/html-anime-cel/SKILL.md · 44 lines

What it actually says

Cel

A frame is flat paint plus a line. Build the hero frame of each shot at full opacity before any tween.

Paint

Use only the hexes on the sheet. A highlight is line, moon, or practical. It is not a new hex.

  • Sky may be a gradient between sky and ink. Characters, cloth, and the blade are flat.
  • One shadow shape per character, hard-edged, ink at about 20% over the local color. No airbrush, no soft light on skin.
  • The eye white is sclera. The iris is iris. Pupil is hair or ink. Two catchlights maximum, cut from line or moon, window-shaped.
  • Hair is two or three masses. Bangs are chunks. One hard sheen band in moon or line. Not strands, not a glow.
  • Line sits on top. At 1080px tall, outer contour about 6px, interior lines about 3px. Taper by drawing the path, not with a blur filter.

Depth, back to front

  1. Sky
  2. Far silhouette — lighter, lower contrast, few windows in practical
  3. Ground and the wide-shot figure
  4. Rain, on its own layer
  5. Close figure
  6. Type

Wide shots are silhouettes. Detail belongs to the close shot. One practical light in the shot (window, moon rim, or blade), drawn as a flat shape.

Effects

  • Rain is a field of straight strokes in line, on its own layer. Positions are written out or come from a seeded series. Never Math.random().
  • A blade trail is one tapered shape in practical, plus one smear drawing behind a fast arc. Not a stack of glow circles.
  • Speed lines are few, straight, and only inside the sakuga shot.

Type

The line sits in the bottom third, in the clear, off the eyes and off the blade. Letterbox bars may hold it. No title, logo, or credit unless the sheet's logline is a title.

Order

For each shot: sky, silhouette, local color, shadow shape, line, effects, type. Then timing.

Changes

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.

  1. yesterday First seen · 44 lines · 63 tokens per session scan A 7a4856a47bd3

Subscribe to this mod's changes

html-anime-cel is a skill published in the GitHub repository blixvip/html-anime (18 stars, last pushed 7d ago), licensed MIT. It adds 63 tokens to every session and 544 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-14.

Related

Other skills, from other repositories

figma

Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link…

heygen-com/hyperframes · 89 tokens

motion-graphics

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…

heygen-com/hyperframes · 139 tokens

agent-reels

Find animation and video references on 1human, consult a human-agent shared library, and contribute public creations only with prior owner permission.

sickn33/agentic-awesome-skills · 31 tokens

pixel2motion

Turn a raster logo (PNG/JPG/WebP/screenshot) into a clean minimal SVG with edge smoothness as the primary hard gate and IoU optimized as high as reasonably possible without a fixed global threshold, then into a choreographed logo animation delivered as standalone JS-rendered HTML, applying Disney's 12 animation…

nolangz/pixel2motion · 163 tokens

Design Resources

This skill provides a curated design reference library for all Maxim design agents. It contains typography scales, color systems, component patterns, animation specs, accessibility checklists, critique frameworks, and the 9-section DESIGN.md standard template.

skillmds/skillmd · 2 tokens

web3-accessibility-guide

Guide to W3AG (Web3 Accessibility Guidelines) — accessibility standards and patterns for Web3 applications. Covers wallet connect UX, transaction confirmation patterns, error handling, screen reader support, and inclusive design for dApps. Making DeFi usable by everyone.

nirholas/three.ws · 57 tokens