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 agentmods add skills/freestylefly/wesight/seedreamnpx skills add freestylefly/wesight --skill seedreamgit clone --depth 1 https://github.com/freestylefly/wesightWrote 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/freestylefly/wesight/seedream)<a href="https://agentmods.dev/skills/freestylefly/wesight/seedream"><img src="https://agentmods.dev/badge/skills/freestylefly/wesight/seedream.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.04085 |
| Opus 5 | $0.00028 | $0.02042 |
| Sonnet 5 | $0.00011 | $0.00817 |
| Haiku 4.5 | $0.00006 | $0.00409 |
Grade A, and why
seedream 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 4d 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.
This is a copy
91% identical to seedream — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seedream 图片生成
使用火山引擎 Seedream 模型生成高质量 AI 图片，支持文本生成图片（T2I）、图片编辑（I2I）、多图融合、组图生成、联网搜索等多种创作模式。
✨ Node.js 版本：此脚本使用 Node.js 实现，无需 Python 环境。通过入口脚本自动检测 Node.js 运行时（优先使用系统 node，回退到 WeSight 内置运行时），Windows 和 Mac 用户都可以开箱即用。
配置
- Base URL:
https://ark.cn-beijing.volces.com/api/v3 - API Key: 从环境变量
ARK_API_KEY读取 - 认证方式:
Authorization: Bearer {API_KEY} - SDK: 兼容火山方舟 Python SDK
快速开始
第一步：设置 API Key
# macOS / Linux - 当前终端临时生效（立即使用）
export ARK_API_KEY="你的API密钥"
# Windows PowerShell - 当前会话临时生效
$env:ARK_API_KEY="你的API密钥"
# 验证设置成功（macOS/Linux）
echo $ARK_API_KEY
# 验证设置成功（Windows）
echo $env:ARK_API_KEY
第二步：生成你的第一张图片
bash "$SKILLS_ROOT/seedream/scripts/generate-image.sh" \
--prompt "一只可爱的橘色小猫"
如何配置 API Key
方式一：通过环境变量配置（推荐）
在终端中设置环境变量：
# macOS/Linux
export ARK_API_KEY="你的API密钥"
# 或者添加到 ~/.zshrc 或 ~/.bashrc 以永久生效
echo 'export ARK_API_KEY="你的API密钥"' >> ~/.zshrc
source ~/.zshrc
# Windows PowerShell
$env:ARK_API_KEY="你的API密钥"
# 或者设置系统环境变量以永久生效
[System.Environment]::SetEnvironmentVariable('ARK_API_KEY', '你的API密钥', 'User')
方式二：通过 WeSight 启动时注入
WeSight 会自动读取系统环境变量，确保在启动 WeSight 前已设置 ARK_API_KEY。
如何获取 API Key：
- 访问火山方舟控制台：https://console.volcengine.com/ark/region:ark+cn-beijing/apikey
- 创建新的 API Key
- 复制密钥并设置为环境变量
前置检查
无需安装任何依赖！ 该脚本已兼容 Node.js 内置模块。
WeSight 已包含 Node.js 运行时，所有必要的依赖已被自动打包。Windows 和 Mac 用户无需额外配置。
工作流程
Seedream 图片生成采用同步模式，流程简单高效：
- 提交请求 - 调用 API 提交图片生成请求
- 等待生成 - API 直接处理并生成图片（通常 30-60 秒）
- 下载图片 - 从返回的 URL 下载生成的图片文件
相比异步模式，同步模式更简单直接，无需轮询任务状态。
配额和限制
免费额度
所有 Seedream 模型提供免费额度，具体请参见火山方舟控制台。
限流限制
- IPM（每分钟图片数）: 500 张/分钟（Seedream 4.5, 4.0）
- 不同模型的限流不同，请参见官方文档
图片保存时间
⚠️ 重要提醒：
- 任务数据（包括图片URL）仅保留 24 小时
- 超时后会被自动清除
- 务必及时下载保存生成的图片
使用示例
路径说明：下面的示例使用 $SKILLS_ROOT 环境变量来引用脚本路径。WeSight 会自动设置这个变量，指向实际的 SKILLs 目录位置，因此无需手动修改路径。
1. 文本生成图片（T2I）
根据文字描述生成图片，适合创意激发和概念设计。
bash "$SKILLS_ROOT/seedream/scripts/generate-image.sh" \
--prompt "充满活力的特写编辑肖像，模特眼神犀利，头戴雕塑感帽子，色彩拼接丰富，景深较浅，Vogue杂志封面美学风格" \
--output portrait.png
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.
- 4d ago First seen · 449 lines · 56 tokens per session scan A a96e284cf227
seedream is a skill published in the GitHub repository freestylefly/wesight (908 stars, last pushed 10d ago), licensed MIT. It adds 56 tokens to every session and 4,085 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to seedream, differing in 10 lines, and is treated as a copy.
Other skills, from other repositories
hyperframes
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation…
hyperframes-cli
HyperFrames CLI tool — hyperframes init, lint, preview, render, transcribe, tts, doctor, browser, info, upgrade, compositions, docs, benchmark. Use when scaffolding a project, linting or validating compositions, previewing in the studio, rendering to video, transcribing audio, generating TTS, or troubleshooting the…
weftcut
Drive the WeftCut video editor over its MCP tools. Use BEFORE calling any weftcut MCP tool — when the user wants to edit video in WeftCut (cut, trim, arrange a timeline, add captions or voiceover) or author/update a Motif (animated overlay).
gsap
GSAP animation reference for HyperFrames. Covers gsap.to(), from(), fromTo(), easing, stagger, defaults, timelines (gsap.timeline(), position parameter, labels, nesting, playback), and performance (transforms, will-change, quickTo). Use when writing GSAP animations in HyperFrames compositions.
tbh-feature-showcase
Capture screenshots (and optionally a short video) of a new TBH Companion feature and compose a player-facing announcement. Run after a feature is implemented and QA passes. Produces screenshots saved under docs/showcase/ and a Discord-ready announcement draft. Pairs with docs/agent/CHANGELOG-RELEASE.md for release…
ai-image-generation-master
Expert-level guide to AI image generation across Midjourney, DALL-E, and Stable Diffusion covering prompt engineering for visual output, style control, composition techniques, upscaling workflows, and production pipelines for consistent, high-quality results. Use when the user asks about ai image generation master…