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 rojim666/SztuCode --skill livestream-postergit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/livestream-poster)<a href="https://agentmods.dev/skills/rojim666/sztucode/livestream-poster"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/livestream-poster/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/rojim666/sztucode/livestream-poster"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/livestream-poster.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 | $0.00098 | $0.00804 |
| Opus 5.5 | $0.00039 | $0.00322 |
| Sonnet 5.5 | $0.00020 | $0.00161 |
| Haiku 4.5 | $0.00010 | $0.00080 |
Grade A, and why
livestream-poster 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 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.
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
Livestream Poster — 直播海报生成
本技能用于生成直播宣传海报。文件创建/打开、工具调用、画布 schema 和基础验证以 ardot-design-core 为准；本技能负责工作流选择和直播海报业务规则。
工作流选择
| 条件 | 加载的 workflow |
|---|---|
| 用户上传设计风格图，并明确说「作为风格参考」「按这个风格」或「参考这个设计风格」 | workflows/style-reference.md |
| 其他：引用风格文件、选择视觉大类、无风格偏好 | workflows/style-selection.md |
风格参考图工作流必须同时满足：
- 用户上传了图片
- 用户明确表示该图片是背景/设计风格参考，而不是人物照片
仅上传图片但未说明用途时，按人物照片处理，使用风格选择工作流。
每次任务只加载一个 workflow。 确定后按该 workflow 顺序执行，不要同时加载两个工作流。
共享参考（按 workflow 指示加载）
| 文件 | 用途 |
|---|---|
| references/render-and-compose.md | 两个工作流共享的建文件、生图、画布排版和验证 |
| references/adaptive-sizing.md | 无风格文件或使用风格参考图时的自适应构图 |
| references/person-size-control.md | 人物/IP 画面占比控制 |
| references/prompt-examples.md | 单人替换与多人 prompt 示例 |
全局硬规则
- ImageGen 默认调用 1 次；仅严重构图问题允许重生 1 次
- 有用户人物照片时必须通过 ImageGen
image1、image2、image3参数融合，不能直接贴到画布 - 人物参考图失败时不得静默移除
image1、image2、image3，否则无法保证人物一致性 - Logo 不传给 ImageGen；在 Ardot 中作为独立图层上传
- 不改用户提供的文案；溢出时调整字号、宽度或排版
- 对话中不暴露
.md、内部路径、DSL、batch_edit等实现细节 - 禁止 spawn 子 agent；遵循
ardot-design-core的文件门禁和验证规则 - 底图与 Part A 背景装饰均由 ImageGen 生成；Ardot 只做底图 fill、文字、Logo，以及风格文件
## Icons的功能性 SVG icon（禁止把背景 prompt 描述画成 SVG/rectangle） - 素材收集与
AskUserQuestion选项以所加载 workflow 的 Step 1 为准，不得跳过、合并或改写
What ships with it
6 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 · 51 lines · 98 tokens per session scan A c9f4a7cc8af2
livestream-poster is a skill published in the GitHub repository rojim666/SztuCode (110 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 804 once invoked, about $0.0004 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 2026-09-12.
Other skills, from other repositories
design-skill
Use BEFORE building or restyling anything a user will see — web/mobile UIs, landing pages, dashboards, components, emails, AND creative work like Three.js/WebGL/canvas/SVG scenes, data-viz, games, and animations — to make it look intentional and polished, not generic; covers tokens, type, color, layout, motion…
frontend-design
Designs and builds distinctive, production-quality frontend interfaces in HTML/CSS, React, or Tailwind: websites, landing pages, marketing pages, dashboards, web applications, interface components, and style overhauls. Classifies the surface as expressive, conventional, or governed by an existing design system, then…
ui-reviewer
Review rendered UI screenshots for hierarchy, spacing, readability, states, consistency, and visual slop.
design-system
DESIGN.md integration for Forge — ensures visual consistency across all UI tasks through standardized design specifications.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
iot-ai-web-visual-quality
Bounded visual-quality guidance for websites, dashboards, frontend UI, design systems and graphic prompts.