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 DwDestiny/codex-visual-asset-skills --skill transparent-visual-assetsgit clone --depth 1 https://github.com/DwDestiny/codex-visual-asset-skillsWrote 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/dwdestiny/codex-visual-asset-skills/transparent-visual-assets)<a href="https://agentmods.dev/skills/dwdestiny/codex-visual-asset-skills/transparent-visual-assets"><img src="https://agentmods.dev/badge/skills/dwdestiny/codex-visual-asset-skills/transparent-visual-assets/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/dwdestiny/codex-visual-asset-skills/transparent-visual-assets"><img src="https://agentmods.dev/badge/skills/dwdestiny/codex-visual-asset-skills/transparent-visual-assets.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 | $0.00061 | $0.01003 |
| Opus 5 | $0.00030 | $0.00502 |
| Sonnet 5 | $0.00012 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
transparent-visual-assets 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.
What it actually says
Transparent Visual Assets
核心判断
先让 Codex 生图得到“容易抠干净”的图,再用脚本做确定性清理。不要要求模型直接画棋盘格透明背景;棋盘格会变成图像内容。优先让模型使用纯色背景,例如 #FF00FF 或 #00FF00,并明确主体不能使用接近背景的颜色。
适合输出:透明 PNG、网页素材、贴纸、图标、单帧 sprite、角色/物体素材。
不适合输出:多帧动画、spritesheet、视频;这些转给 $sprite-animation-assets。
典型使用场景
- 网站设计素材:Landing page、产品官网、博客插画、功能区装饰、空状态插画。
- PPT / 汇报图表:路演页、数据页、业务复盘、图表旁的视觉解释元素。
- App / 产品引导:onboarding、权限说明、功能引导、发布说明里的产品插画。
- 电商 / 社媒贴纸:商品页角标、促销贴纸、社媒封面、公众号配图元素。
- 游戏 / 互动 UI:小角色、道具、背包图标、按钮素材、单帧 sprite。
- 视频 / 海报叠加:封面人物、栏目贴片、透明 logo-like 装饰、片头片尾元素。
工作流
- 明确素材用途、尺寸、主体边界和禁用元素。
- 调用 Codex 生图能力生成带纯色背景的候选图。
- 目视检查:主体完整、没有阴影地面、没有漂浮杂点、主体颜色不接近背景色。
- 用
scripts/prepare_transparent_asset.py清理纯色背景、裁切透明边缘、输出 PNG。 - 打开结果或检查报告,确认透明角落、主体不被误删。
生图提示词要点
使用简短、强约束的提示词:
Create a single centered web asset of <subject>.
Use a perfectly flat #FF00FF background for later chroma key removal.
The subject must not contain magenta, pink, or colors close to #FF00FF.
No shadows, floor, scenery, text, labels, checkerboard pattern, glow, blur, or detached decorative particles.
Keep the full subject inside the canvas with clear spacing.
如果主体天然包含粉色或品红,换成 #00FF00、#00FFFF 或其他不会出现在主体里的纯色。
更多提示词和 QA 细节见 references/prompt-and-cleanup.md。
清理脚本
python "${CODEX_HOME:-$HOME/.codex}/skills/transparent-visual-assets/scripts/prepare_transparent_asset.py" \
--input /absolute/path/source.png \
--output /absolute/path/asset.png \
--background "#FF00FF" \
--threshold 24 \
--feather-threshold 48 \
--trim \
--padding 8 \
--report /absolute/path/report.json
参数说明:
--background:要移除的纯色背景;不传时用四角颜色估算。--threshold:颜色容差。背景边缘残留就调大;主体被吃掉就调小或重生图换背景色。--feather-threshold:可选的边缘柔化容差,用来淡化生图抗锯齿留下的背景色毛边。--trim和--padding:裁掉透明边缘并保留一点安全留白。
脚本只做背景清理,不会补画、重绘、扩图或创造新素材。
验收标准
- 输出必须是
.png,并带 alpha 透明通道。 - 四角应透明,主体边缘不缺块。
- 主体外没有阴影、地面、光晕、漂浮符号、文字或背景色残留。
- 素材在深色、浅色、棋盘格背景上都能读清。
- 如果清理后主体明显破损,重新生图或换背景色,不要靠脚本硬修。
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.
- 10d ago First seen · 79 lines · 61 tokens per session scan A 1d362f2459fe
transparent-visual-assets is a skill published in the GitHub repository DwDestiny/codex-visual-asset-skills (60 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 1,003 once invoked, about $0.0003 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
generate-meme-gif-pack
A workflow for creating a pack of animated Chinese meme stickers for WeChat from a reference image or text idea. It targets 16 or 24 entries, each as a 240-by-240 GIF.
animation-patterns
Comprehensive animation recipe book for the Excalimate MCP server. Use when adding keyframe animations to Excalidraw diagrams — covers fade-in reveals, slide-in movements, pop-in scale effects, arrow draw-on strokes, camera pan/zoom, staggered multi-element sequences, and timing/easing selection. Essential for…
export-optimization
Optimize Excalimate diagram exports for different formats and platforms. Use when asked to export animations, set up camera framing, choose output format, adjust aspect ratios, or prepare diagrams for specific destinations like presentations, social media, documentation, or video — even if the user just says "export"…
mind-maps
Create animated mind maps and concept diagrams using the Excalimate MCP server. Use when asked to brainstorm, visualize concepts, create idea trees, knowledge maps, feature maps, topic clusters, or any radial/hierarchical concept exploration — even if the user just says "map out the ideas" or "brainstorm this.".
animated-presentations
Create multi-scene animated presentations with smooth camera transitions using the Excalimate MCP server. Use when asked to create presentations, pitch decks, animated slide shows, demo walkthroughs, keynote-style reveals, or any sequential multi-scene visual narrative — even if the user says "slides" or "deck.".
data-pipelines
Create animated data pipeline and ETL flow diagrams using the Excalimate MCP server. Use when asked to visualize data pipelines, ETL/ELT processes, streaming architectures, data warehousing flows, ML pipelines, Kafka/event streaming topologies, or any data transformation workflow — even if the user just says "data…